The goal of this data exploration is to determine which variable has the greatest impact on sale price along with any secondary influences. From there, the objective is to conclude what changes could be made when searching for houses to help buyers find desirable homes at a reasonable price.
Additionally, we want to understand the strength of our models and what potential changes we can make to improve our overall predictability.
# Add libraries
library(tidyverse)
library(ggplot2)
library(lubridate)
library(cowplot)
library(leaps)
library(DAAG)
library(MASS)
Before importing to R, a visual inspection was completed to ensure
our data was consistent and accurate. Through this inspection, the
following issues were addressed:
- Duplicate entries were removed (not exact match, but still
duplicate).
- Contributor column was removed (not relevant to this analysis).
- Empty and null values were updated to show as “NA” values.
- Measurements were standardized (i.e., house sizes converted to square
feet).
As detailed below, additional data clean up was completed before
starting our analysis. This clean up included:
- Renaming column headers.
- Updating data types.
- Adding additional quantitative data.
- Evaluating and managing NA values.
# Import data
housing <- read.csv("BANA 7038 Course Data Files/BANA7038_Housing_Data.csv",
h = T)
# Update column names
colnames(housing) <- c("address", "zip", "price_sold", "date_sold",
"num_of_bedrooms", "num_of_bathrooms", "year_built",
"square_feet", "lot_size", "num_parking_spots")
# Update data type to numeric (where needed)
housing$num_parking_spots = as.numeric(housing$num_parking_spots)
# Add month column and house age (in years)
housing <- housing %>%
mutate(month_sold = month(date_sold), # month sold
house_age = (year(Sys.Date()) - year_built)) # house age in years
head(housing)
## address zip price_sold date_sold
## 1 2442 Elderberry Ct, Cincinnati, OH 45239 214300 2023-12-08
## 2 2444 Madison Rd UNIT 904, Cincinnati, OH 45208 339900 2023-11-15
## 3 3004 Glenmore Ave UNIT 314,Cincinnati,OH 45238 90000 2024-01-11
## 4 5644 Springdale Rd, Cincinnati, OH 45251 178000 2023-11-27
## 5 5921 Squirrelsnest Ln, Cincinnati, OH 45252 585000 2023-10-03
## 6 7844 Gapstow Brg #303, Cincinnati, OH 45231 269900 2024-01-05
## num_of_bedrooms num_of_bathrooms year_built square_feet lot_size
## 1 2 3 2006 1456 NA
## 2 2 2 1967 1800 NA
## 3 2 1 1983 882 NA
## 4 2 2 1980 1150 NA
## 5 3 4 NA NA NA
## 6 3 3 1988 1848 NA
## num_parking_spots month_sold house_age
## 1 2 12 18
## 2 0 11 57
## 3 3 1 41
## 4 1 11 44
## 5 NA 10 NA
## 6 NA 1 36
Before we can start our data analysis, we need to decide how to handle our missing values. To do this, we can use imputation by looking at a variety of potential replacements.For this data set, we will review how our data would be impacted by replacing NA values with 0, the mean of the column data, the median of the column data, and removing the data all together. From there we can select the option with the least impact to our original data as our replacement.
# Check for missing values
colSums(is.na(housing))
## address zip price_sold date_sold
## 0 0 3 3
## num_of_bedrooms num_of_bathrooms year_built square_feet
## 9 8 26 28
## lot_size num_parking_spots month_sold house_age
## 70 276 3 26
Evaluating NA values for Number of Parking Spots
We can see from the distribution that there is minimal impact to our original data when we use the mean or median as our replacement for our NA values. We do see an impact when using zero as our replacement. Since there is such minimal difference between the mean and median, we will use the mean as our replacement value.
# Create data frame of imputation options - number of parking spots
park_imputed_values <- data.frame(
original = housing$num_parking_spots,
imputed_zero = replace(housing$num_parking_spots,
is.na(housing$num_parking_spots), 0),
imputed_mean = replace(housing$num_parking_spots,
is.na(housing$num_parking_spots),
mean(housing$num_parking_spots, na.rm = TRUE)),
imputed_median = replace(housing$num_parking_spots,
is.na(housing$num_parking_spots),
median(housing$num_parking_spots, na.rm = TRUE))
)
# NA value change for each option
head(park_imputed_values)
## original imputed_zero imputed_mean imputed_median
## 1 2 2 2.000000 2
## 2 0 0 0.000000 0
## 3 3 3 3.000000 3
## 4 1 1 1.000000 1
## 5 NA 0 1.798077 2
## 6 NA 0 1.798077 2
# Create histogram for each option
park_h1 <- ggplot(park_imputed_values, aes(x = original)) +
geom_histogram(bins = 20, fill = "red3") +
labs(title = "Original distribution", x = "Original")
park_h2 <- ggplot(park_imputed_values, aes(x = imputed_zero)) +
geom_histogram(bins = 20, fill = "green3") +
labs(title = "Zero-imputed distribution", x = "Imputed Zero")
park_h3 <- ggplot(park_imputed_values, aes(x = imputed_mean)) +
geom_histogram(bins = 20, fill = "blue4") +
labs(title = "Mean-imputed distribution", x = "Imputed Mean")
park_h4 <- ggplot(park_imputed_values, aes(x = imputed_median)) +
geom_histogram(bins = 20, fill = "yellow3") +
labs(title = "Median-imputed distribution", x = "Imputed Median")
# Plot grid of each histogram
plot_grid(park_h1, park_h2, park_h3, park_h4, nrow = 2, ncol = 2)
# Replace NA values with median for number of parking spots
housing$num_parking_spots[is.na(housing$num_parking_spots)] <-
mean(housing$num_parking_spots, na.rm = T)
Evaluating NA values for Size of Lot
We can see from the distribution that there is likely outliers present that are heavily skewing our data. As a result, it is hard to tell from our histograms what the right replacement is. While having a 0 lot size doesn’t make sense and our mean is likely heavily impacted by outliers, using our median is likely our best approach.
# Create data frame of imputation options - size of lot
lot_imputed_values <- data.frame(
original = housing$lot_size,
imputed_zero = replace(housing$lot_size,
is.na(housing$lot_size), 0),
imputed_mean = replace(housing$lot_size,
is.na(housing$lot_size),
mean(housing$lot_size, na.rm = TRUE)),
imputed_median = replace(housing$lot_size,
is.na(housing$lot_size),
median(housing$lot_size, na.rm = TRUE))
)
# NA value change for each option
head(lot_imputed_values)
## original imputed_zero imputed_mean imputed_median
## 1 NA 0 829287.1 8820.5
## 2 NA 0 829287.1 8820.5
## 3 NA 0 829287.1 8820.5
## 4 NA 0 829287.1 8820.5
## 5 NA 0 829287.1 8820.5
## 6 NA 0 829287.1 8820.5
# Create histogram for each option
lot_h1 <- ggplot(lot_imputed_values, aes(x = original)) +
geom_histogram(bins = 20, fill = "red3") +
labs(title = "Original distribution", x = "Original")
lot_h2 <- ggplot(lot_imputed_values, aes(x = imputed_zero)) +
geom_histogram(bins = 20, fill = "green3") +
labs(title = "Zero-imputed distribution", x = "Imputed Zero")
lot_h3 <- ggplot(lot_imputed_values, aes(x = imputed_mean)) +
geom_histogram(bins = 20, fill = "blue4") +
labs(title = "Mean-imputed distribution", x = "Imputed Mean")
lot_h4 <- ggplot(lot_imputed_values, aes(x = imputed_median)) +
geom_histogram(bins = 20, fill = "yellow3") +
labs(title = "Median-imputed distribution", x = "Imputed Median")
# Plot grid of each histogram
plot_grid(lot_h1, lot_h2, lot_h3, lot_h4, nrow = 2, ncol = 2)
# Replace NA values with median for size of lot
housing$lot_size[is.na(housing$lot_size)] <-
median(housing$lot_size, na.rm = T)
Evaluating NA values for Square Feet
We see some variability between the mean, median, and zero histograms. Zero has the largest impact, although small. Between mean and median, we see the least impact with the mean even though we see some variability across all options. For this data set we will go with the mean to keep the impact minimized.
# Create data frame of imputation options - square feet
sqrft_imputed_values <- data.frame(
original = housing$square_feet,
imputed_zero = replace(housing$square_feet,
is.na(housing$square_feet), 0),
imputed_mean = replace(housing$square_feet,
is.na(housing$square_feet),
mean(housing$square_feet, na.rm = TRUE)),
imputed_median = replace(housing$square_feet,
is.na(housing$square_feet),
median(housing$square_feet, na.rm = TRUE))
)
# NA value change for each option
head(sqrft_imputed_values)
## original imputed_zero imputed_mean imputed_median
## 1 1456 1456 1456.000 1456
## 2 1800 1800 1800.000 1800
## 3 882 882 882.000 882
## 4 1150 1150 1150.000 1150
## 5 NA 0 2210.193 1820
## 6 1848 1848 1848.000 1848
# Create histogram for each option
sqrft_h1 <- ggplot(sqrft_imputed_values, aes(x = original)) +
geom_histogram(bins = 20, fill = "red3") +
labs(title = "Original distribution", x = "Original")
sqrft_h2 <- ggplot(sqrft_imputed_values, aes(x = imputed_zero)) +
geom_histogram(bins = 20, fill = "green3") +
labs(title = "Zero-imputed distribution", x = "Imputed Zero")
sqrft_h3 <- ggplot(sqrft_imputed_values, aes(x = imputed_mean)) +
geom_histogram(bins = 20, fill = "blue4") +
labs(title = "Mean-imputed distribution", x = "Imputed Mean")
sqrft_h4 <- ggplot(sqrft_imputed_values, aes(x = imputed_median)) +
geom_histogram(bins = 20, fill = "yellow3") +
labs(title = "Median-imputed distribution", x = "Imputed Median")
# Plot grid of each histogram
plot_grid(sqrft_h1, sqrft_h2, sqrft_h3, sqrft_h4, nrow = 2, ncol = 2)
# Replace NA values with mean for square feet
housing$square_feet[is.na(housing$square_feet)] <-
mean(housing$square_feet, na.rm = T)
Evaluating NA values for Number of Bedrooms
We see almost some variability across all options when looking at the number of bedrooms. For this case, we will go with the median as it has the minimum impact.
# Create data frame of imputation options - number of bedrooms
beds_imputed_values <- data.frame(
original = housing$num_of_bedrooms,
imputed_zero = replace(housing$num_of_bedrooms,
is.na(housing$num_of_bedrooms), 0),
imputed_mean = replace(housing$num_of_bedrooms,
is.na(housing$num_of_bedrooms),
mean(housing$num_of_bedrooms, na.rm = TRUE)),
imputed_median = replace(housing$num_of_bedrooms,
is.na(housing$num_of_bedrooms),
median(housing$num_of_bedrooms, na.rm = TRUE))
)
# NA value change for each option
head(beds_imputed_values)
## original imputed_zero imputed_mean imputed_median
## 1 2 2 2 2
## 2 2 2 2 2
## 3 2 2 2 2
## 4 2 2 2 2
## 5 3 3 3 3
## 6 3 3 3 3
# Create histogram for each option
bed_h1 <- ggplot(beds_imputed_values, aes(x = original)) +
geom_histogram(bins = 20, fill = "red3") +
labs(title = "Original distribution", x = "Original")
bed_h2 <- ggplot(beds_imputed_values, aes(x = imputed_zero)) +
geom_histogram(bins = 20, fill = "green3") +
labs(title = "Zero-imputed distribution", x = "Imputed Zero")
bed_h3 <- ggplot(beds_imputed_values, aes(x = imputed_mean)) +
geom_histogram(bins = 20, fill = "blue4") +
labs(title = "Mean-imputed distribution", x = "Imputed Mean")
bed_h4 <- ggplot(beds_imputed_values, aes(x = imputed_median)) +
geom_histogram(bins = 20, fill = "yellow3") +
labs(title = "Median-imputed distribution", x = "Imputed Median")
# Plot grid of each histogram
plot_grid(bed_h1, bed_h2, bed_h3, bed_h4, nrow = 2, ncol = 2)
# Replace NA values with median for number of bedrooms
housing$num_of_bedrooms[is.na(housing$num_of_bedrooms)] <-
median(housing$num_of_bedrooms, na.rm = T)
Evaluating NA values for Number of Bathrooms
We again here see some variability in our distribution. We can choose the median as our replacement as it has the least impact.
# Create data frame of imputation options - number of bathrooms
baths_imputed_values <- data.frame(
original = housing$num_of_bathrooms,
imputed_zero = replace(housing$num_of_bathrooms,
is.na(housing$num_of_bathrooms), 0),
imputed_mean = replace(housing$num_of_bathrooms,
is.na(housing$num_of_bathrooms),
mean(housing$num_of_bathrooms, na.rm = TRUE)),
imputed_median = replace(housing$num_of_bathrooms,
is.na(housing$num_of_bathrooms),
median(housing$num_of_bathrooms, na.rm = TRUE))
)
# NA value change for each option
head(baths_imputed_values)
## original imputed_zero imputed_mean imputed_median
## 1 3 3 3 3
## 2 2 2 2 2
## 3 1 1 1 1
## 4 2 2 2 2
## 5 4 4 4 4
## 6 3 3 3 3
# Create histogram for each option
bath_h1 <- ggplot(baths_imputed_values, aes(x = original)) +
geom_histogram(bins = 20, fill = "red3") +
labs(title = "Original distribution", x = "Original")
bath_h2 <- ggplot(baths_imputed_values, aes(x = imputed_zero)) +
geom_histogram(bins = 20, fill = "green3") +
labs(title = "Zero-imputed distribution", x = "Imputed Zero")
bath_h3 <- ggplot(baths_imputed_values, aes(x = imputed_mean)) +
geom_histogram(bins = 20, fill = "blue4") +
labs(title = "Mean-imputed distribution", x = "Imputed Mean")
bath_h4 <- ggplot(baths_imputed_values, aes(x = imputed_median)) +
geom_histogram(bins = 20, fill = "yellow3") +
labs(title = "Median-imputed distribution", x = "Imputed Median")
# Plot grid of each histogram
plot_grid(bath_h1, bath_h2, bath_h3, bath_h4, nrow = 2, ncol = 2)
# Replace NA values with median for number of bathrooms
housing$num_of_bathrooms[is.na(housing$num_of_bathrooms)] <-
round(median(housing$num_of_bathrooms, na.rm = T), 0)
Removing NA Values
Due to the variability in price sold, the unpredictability of year built, and the minimum number of records missing from date sold, these 3 columns had any remaining NA values removed from the data set.
# Reviewing imputation histograms to determine how to handle NA values
# Remove NA price sold values from the data set
housing <- housing %>% drop_na(price_sold)
# Remove NA year built sold from data set
housing <- housing %>% drop_na(year_built)
# Remove NA date sold from data set
housing <- housing %>% drop_na(date_sold)
# Check for missing values
colSums(is.na(housing))
## address zip price_sold date_sold
## 0 0 0 0
## num_of_bedrooms num_of_bathrooms year_built square_feet
## 0 0 0 0
## lot_size num_parking_spots month_sold house_age
## 0 0 0 0
# Snapshot of cleaned data
head(housing)
## address zip price_sold date_sold
## 1 2442 Elderberry Ct, Cincinnati, OH 45239 214300 2023-12-08
## 2 2444 Madison Rd UNIT 904, Cincinnati, OH 45208 339900 2023-11-15
## 3 3004 Glenmore Ave UNIT 314,Cincinnati,OH 45238 90000 2024-01-11
## 4 5644 Springdale Rd, Cincinnati, OH 45251 178000 2023-11-27
## 5 7844 Gapstow Brg #303, Cincinnati, OH 45231 269900 2024-01-05
## 6 7909 Cheviot Rd UNIT 18,Cincinnati,OH 45247 170000 2024-01-12
## num_of_bedrooms num_of_bathrooms year_built square_feet lot_size
## 1 2 3 2006 1456 8820.5
## 2 2 2 1967 1800 8820.5
## 3 2 1 1983 882 8820.5
## 4 2 2 1980 1150 8820.5
## 5 3 3 1988 1848 8820.5
## 6 2 3 1991 2400 8820.5
## num_parking_spots month_sold house_age
## 1 2.000000 12 18
## 2 0.000000 11 57
## 3 3.000000 1 41
## 4 1.000000 11 44
## 5 1.798077 1 36
## 6 1.000000 1 33
Below are some plots to help visualize our data.
# Histogram
ggplot(housing, aes(x = price_sold)) +
geom_histogram(fill = "blue4") +
labs(title = "Price Sold", x = "Price")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(housing, aes(x = log(price_sold))) +
geom_histogram(fill = "blue4") +
labs(title = "Price Sold", x = "Price")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
# Plot pairs
pairs(housing[c(3,5:6,8:10,12)], pch = 20)
# Plot points
plot1 <- ggplot(housing, aes(x = num_of_bedrooms, y = price_sold)) +
geom_point(color = "red3") +
labs(Title = "Price Sold vs. Bedroom Count", x = "# of Bedrooms", y = "Sale Price")
plot2 <- ggplot(housing, aes(x = num_of_bathrooms, y = price_sold)) +
geom_point(color = "green3") +
labs(Title = "Price Sold vs. Bathroom Count", x = "# of Bathrooms", y = "Sale Price")
plot3 <- ggplot(housing, aes(x = square_feet, y = price_sold)) +
geom_point(color = "blue4") +
labs(Title = "Price Sold vs. Square Feet", x = "Square Feet", y = "Sale Price")
plot4 <- ggplot(housing, aes(x = lot_size, y = price_sold)) +
geom_point(color = "yellow3") +
labs(Title = "Price Sold vs. Lot Size", x = "Lot Size", y = "Sale Price")
plot5 <- ggplot(housing, aes(x = house_age, y = price_sold)) +
geom_point(color = "orange3") +
labs(Title = "Price Sold vs. House Age", x = "House Age", y = "Sale Price")
plot6 <- ggplot(housing, aes(x = num_parking_spots, y = price_sold)) +
geom_point(color = "pink3") +
labs(Title = "Price Sold vs. Parking Spots", x = "# of Parking Spots", y = "Sale Price")
# Create grid of different key plots
plot_grid(plot1, plot2, plot3, plot4, plot5, plot6, nrow = 2, ncol = 3)
Below we create our first model that includes all potential independent variables using our original data set.
# Create model
housing_model1 <- lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + lot_size + num_parking_spots + house_age,
data = housing)
Evaluate Outliers: Using Residuals
Next, we need to evaluate our model for outliers. There are 3 measures we can look at regarding residuals that help us check the adequacy of our model and ensure our model fits our data well. They can also be used to help identify outliers in our data set.
Measure 1: Residuals vs. Response and Independent Variables
Measure one looks at the residuals against the response variable and the residuals against the independent variables. When looking at residuals vs. the response variable, we are checking for linearity, equal variance, and potential outliers. Here, we do not see a equal distribution around zero, but a funnel indicating we may have outliers.
Looking at the residuals against the independent variable we see a fairly random distribution of number of bedrooms and number of bathrooms. However, we again see a funnel with square feet indicating it lacks “randomness”. Additionally, we see a heavy skew of data for our lot size.
# Get residuals
head(housing_model1$residuals)
## 1 2 3 4 5 6
## -143943.98 16052.33 58808.73 -22604.05 -116330.04 -364505.01
# Create scatter plots with the residuals and price sold
ggplot(housing, aes(x = price_sold, y = housing_model1$residuals)) +
geom_point(color = "blue4") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. Price Sold", x = "Price Sold", y = "Residuals")
# Mean of residuals
mean(housing_model1$residuals)
## [1] -2.064841e-11
# Check residuals against the independent variables
# Plot the relationships
bed_res <- ggplot(housing, aes(num_of_bedrooms, housing_model1$residuals)) +
geom_point(color = "red3") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. # of Bedrooms", x = "# of Bedrooms", y = "Residuals")
bath_res <- ggplot(housing, aes(num_of_bathrooms, housing_model1$residuals)) +
geom_point(color = "green3") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. # of Bathrooms", x = "# of Bathrooms", y = "Residuals")
sqrft_res <- ggplot(housing, aes(square_feet, housing_model1$residuals)) +
geom_point(color = "blue4") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. Square Feet", x = "Square Feet", y = "Residuals")
lot_res <- ggplot(housing, aes(lot_size, housing_model1$residuals)) +
geom_point(color = "yellow3") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. Lot Size", x = "Lot Size", y = "Residuals")
park_res <- ggplot(housing, aes(num_parking_spots, housing_model1$residuals)) +
geom_point(color = "orange3") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. # of Parking Spots", x = "# of Parking Spots", y = "Residuals")
age_res <- ggplot(housing, aes(house_age, housing_model1$residuals)) +
geom_point(color = "pink3") +
geom_hline(yintercept = 0, col = "black") +
labs(Title = "Residuals vs. House Age", x = "House Age", y = "Residuals")
plot_grid(bed_res, bath_res, sqrft_res,lot_res, park_res, age_res,
nrow = 2, ncol = 3)
Measure 2: Residual Normality Assumption
Measure 2 uses QQ-plots to evaluate the normal distribution and evaluates if there are potential outliers. We see a little bit of curve at the beginning and end of our qq-plot. This variability isn’t ideal, but not bad as majority of the data follows a normal distribution. The value at the far right of the graph also looks to be an outlier.
# Create histogram
hist(housing_model1$residuals, col = "blue4")
hist(housing_model1$residuals, breaks = 30, col = "blue4")
# QQ-Plots
qqnorm(housing_model1$residuals, col = "blue4")
qqline(housing_model1$residuals, col = "blue4")
Measure 3: Identifying Outliers using Residuals
Measure 3 looks at residuals to determine if there are outliers.
From our results, we identify 23 outliers that fall outside of the normal distribution of our data (+- 3 standard deviations). Based on this, we can remove these 22 outliers. First, lets take a look at cooks distance.
# Get Residuals
head(housing_model1$residuals)
## 1 2 3 4 5 6
## -143943.98 16052.33 58808.73 -22604.05 -116330.04 -364505.01
# Get sigma - estimator of the standard deviation of our residuals
summary(housing_model1)$sigma
## [1] 300619.3
# standardize residuals
stdRes = housing_model1$residuals / summary(housing_model1)$sigma
head(stdRes)
## 1 2 3 4 5 6
## -0.47882488 0.05339753 0.19562530 -0.07519162 -0.38696802 -1.21251381
# Combine data points with standardized residuals
housing_residuals = cbind(housing, stdRes)
head(housing_residuals)
## address zip price_sold date_sold
## 1 2442 Elderberry Ct, Cincinnati, OH 45239 214300 2023-12-08
## 2 2444 Madison Rd UNIT 904, Cincinnati, OH 45208 339900 2023-11-15
## 3 3004 Glenmore Ave UNIT 314,Cincinnati,OH 45238 90000 2024-01-11
## 4 5644 Springdale Rd, Cincinnati, OH 45251 178000 2023-11-27
## 5 7844 Gapstow Brg #303, Cincinnati, OH 45231 269900 2024-01-05
## 6 7909 Cheviot Rd UNIT 18,Cincinnati,OH 45247 170000 2024-01-12
## num_of_bedrooms num_of_bathrooms year_built square_feet lot_size
## 1 2 3 2006 1456 8820.5
## 2 2 2 1967 1800 8820.5
## 3 2 1 1983 882 8820.5
## 4 2 2 1980 1150 8820.5
## 5 3 3 1988 1848 8820.5
## 6 2 3 1991 2400 8820.5
## num_parking_spots month_sold house_age stdRes
## 1 2.000000 12 18 -0.47882488
## 2 0.000000 11 57 0.05339753
## 3 3.000000 1 41 0.19562530
## 4 1.000000 11 44 -0.07519162
## 5 1.798077 1 36 -0.38696802
## 6 1.000000 1 33 -1.21251381
# Number of rows with outliers
NROW(housing_residuals %>% filter(stdRes > 3 | stdRes < -3))
## [1] 22
# Create list of outliers
housing_outliers <- housing_residuals %>%
filter(stdRes > 3 | stdRes < -3)
housing_outliers
## address zip price_sold date_sold
## 31 3026 Woodburn Ave, Cincinnati OH 45206 2050000 2023-11-20
## 35 3900 West St #301/3, Cincinnati, OH 45227 2275000 2023-12-20
## 37 3900 West St UNIT 203, Cincinnati, OH 45227 1650000 2023-07-28
## 39 3900 West Street #301/3, Cincinnati OH 45227 2275000 2023-12-20
## 105 8705 Camargo Dr, Cincinnati, OH 45243 3500000 2023-07-27
## 108 9200 Old Indian Hill Rd, Cincinnati, OH 45243 3500000 2023-11-21
## 158 805 Tusculum Ave, Cincinnati, OH 45226 2525000 2021-06-30
## 164 2501 Grandin Rd, Cincinnati, OH 45208 3850000 2023-02-24
## 167 7995 Ayers Rd, Cincinnati, OH 45255 45255 7500000 2023-07-12
## 172 10 Gradin Ln, Cincinnati, OH 45208 3600000 2021-10-12
## 175 10 Grandin Ln, Cincinnati, OH 45208 3650000 2021-10-12
## 191 9200 Old Indian Hill Rd, Cincinnati, OH 45243 3500000 2023-11-21
## 194 7886 Ayers Rd, Cincinnati, OH 45255 2495000 2023-05-31
## 210 2 Taft Road Ln, Cincinnati, OH 45206 2800000 2022-12-16
## 228 1269 Balmoral Dr, Cincinnati, OH 45233 697600 2021-04-30
## 264 7640 Demar Rd, Cincinnati, OH 45243 2200000 2023-06-23
## 293 1240 W Rookwood Dr, Cincinnati, OH 45208 1900000 2023-04-19
## 328 6473 Beechmont Ave, Cincinnati, OH 45230 350000 2023-07-26
## 337 3980 Rose Hill Ave, Cincinnati, OH 45229 609000 2022-01-13
## 535 1722 Wolfangel Rd 45255 110111 2023-06-22
## 613 1059 Celestial St, Cincinnati, OH 45202 3025000 2021-06-18
## 837 1056 Bluejay Dr, Cincinnati 45231 215000 2023-12-22
## num_of_bedrooms num_of_bathrooms year_built square_feet lot_size
## 31 6 2 1886 3921 8820.5
## 35 4 5 2014 4592 8820.5
## 37 3 3 2014 3288 8820.5
## 39 4 5 2014 4592 8820.5
## 105 5 8 1929 7980 334540.0
## 108 5 8 1935 10119 264409.0
## 158 6 5 1869 5255 178596.0
## 164 5 6 1958 7091 143748.0
## 167 4 6 2016 7370 132422.0
## 172 5 6 1925 8374 129373.0
## 175 5 6 1925 8374 126324.0
## 191 5 8 1999 10119 87555.0
## 194 4 5 2016 6552 87120.0
## 210 5 5 2001 7537 64469.0
## 228 6 7 1964 7875 52708.0
## 264 5 6 2012 4976 43560.0
## 293 4 4 1939 4413 30492.0
## 328 6 4 1917 7874 23522.0
## 337 6 7 1903 7586 22216.0
## 535 3 1 1940 12170 12632.0
## 613 4 4 2017 6778 10585.0
## 837 4 2 1956 7620 7620.0
## num_parking_spots month_sold house_age stdRes
## 31 1 11 138 5.063546
## 35 5 12 10 4.121264
## 37 2 7 10 3.361515
## 39 5 12 10 4.121264
## 105 3 7 95 5.141399
## 108 3 11 89 3.868778
## 158 2 6 155 4.742521
## 164 3 2 66 7.592333
## 167 1 7 8 19.412750
## 172 3 10 99 5.978702
## 175 3 10 99 6.145026
## 191 4 11 25 3.917128
## 194 3 5 8 3.653819
## 210 3 12 23 4.226332
## 228 6 4 60 -3.529289
## 264 3 6 12 3.392602
## 293 2 4 85 3.266123
## 328 6 7 107 -3.596462
## 337 2 1 121 -3.745484
## 535 2 6 84 -6.354153
## 613 3 6 7 5.653408
## 837 0 12 68 -3.532621
Evaluate Outliers: Using Cooks Distance to find outliers
Using cooks distance, we can determine how impactful or influential each of the values in our data set are and how great the impact would be to keep or remove them from the data set.
As outlined below, there are only three values that are great than one, indicating they will have significant influence depending on whether we keep them or remove them from our data.
# Cooks distance
head(cooks.distance(housing_model1))
## 1 2 3 4 5 6
## 1.586563e-04 2.049027e-06 3.025714e-05 2.377928e-06 3.813411e-05 1.058249e-03
# Combine with original data and filter for values over one
cbind(housing, cooks = cooks.distance(housing_model1)) %>%
filter(cooks >= 1)
## address zip price_sold date_sold
## 66 2635 Struble Rd. Cincinnati, OH 45231 160000 2023-07-10
## 167 7995 Ayers Rd, Cincinnati, OH 45255 45255 7500000 2023-07-12
## 535 1722 Wolfangel Rd 45255 110111 2023-06-22
## num_of_bedrooms num_of_bathrooms year_built square_feet lot_size
## 66 3 2 1951 1080 943030440
## 167 4 6 2016 7370 132422
## 535 3 1 1940 12170 12632
## num_parking_spots month_sold house_age cooks
## 66 1.798077 7 73 17.533746
## 167 1.000000 7 8 1.151670
## 535 2.000000 6 84 1.038217
Evaluating Results & Removing Outliers
After investigation, we see that the second house listed, 1722 Wolfangel Rd., was incorrectly captured. Our first steps is to correct this.
The other two are both true outliers. One being a high end home sold for 7.5 million dollars and the other being on a 943030440 lot size; both highly uncommon.
Once we correct the first, we can remove the 22 remaining outliers found using our residuals and cooks distance.
# Correct incorrect data
housing$square_feet[housing$address == "1722 Wolfangel Rd"] <- 1270
# Remove corrected data from outliers list
housing_outliers <- housing_outliers %>%
filter(address != "1722 Wolfangel Rd")
# Add Struble Rd. to outliers
housing_outliers <- housing_outliers %>%
rbind(c("2635 Struble Rd. Cincinnati, OH", 45231, 160000, "2023-07-10", 3, 2,
1951, 1080, 943030440, 2, 7, 73, NA))
# Remove outliers from housing data
clean_housing <- housing %>%
filter(!(address %in% housing_outliers$address))
# Create new model
housing_model2 <- lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + lot_size + num_parking_spots + house_age,
data = clean_housing)
# Review new model
summary(housing_model2)
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -643581 -95423 -13986 74081 988217
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.094e+05 2.280e+04 -4.796 1.8e-06 ***
## num_of_bedrooms -1.968e+04 6.787e+03 -2.900 0.00379 **
## num_of_bathrooms 9.000e+04 7.231e+03 12.446 < 2e-16 ***
## square_feet 1.307e+02 6.991e+00 18.694 < 2e-16 ***
## lot_size 6.569e-03 6.388e-03 1.028 0.30395
## num_parking_spots 8.542e+03 5.481e+03 1.558 0.11936
## house_age 1.847e+02 1.394e+02 1.325 0.18537
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179700 on 1359 degrees of freedom
## Multiple R-squared: 0.625, Adjusted R-squared: 0.6234
## F-statistic: 377.5 on 6 and 1359 DF, p-value: < 2.2e-16
To determine which variables we should use in our model, we will walk through each of the 3 techniques to determine our potential models.
Adjusted R-Squared
When looking at the adjusted r-squared, we see the model with the highest adjusted r-squared would include all potential covariates and would give us a 62.32% adjusted r-squared. This means that we can explain 62.32% of the variability in our model. Since our this is the same as our second model we created, no new model will be created here.
However, when looking at our p-values, we see that lot size, number of parking spots, and house age all have greater than 5% indicating that we would likely encounter a type 1 error for these covariates using this model.
# Create a model for all potential combinations
allModels <- leaps(x = clean_housing[,c(5:6, 8:10, 12)], y = clean_housing[,3],
method = "adjr2")
# Combine the new model with the adjusted r-squared for a better visual
cbind(allModels$which, adjrsq = allModels$adjr2)
## 1 2 3 4 5 6 adjrsq
## 1 0 0 1 0 0 0 0.578668556
## 1 0 1 0 0 0 0 0.514210635
## 1 1 0 0 0 0 0 0.220757580
## 1 0 0 0 0 1 0 0.113732220
## 1 0 0 0 0 0 1 0.028689108
## 1 0 0 0 1 0 0 0.004691932
## 2 0 1 1 0 0 0 0.620963018
## 2 0 0 1 0 0 1 0.580318909
## 2 0 0 1 0 1 0 0.580306517
## 2 0 0 1 1 0 0 0.578613268
## 2 1 0 1 0 0 0 0.578380785
## 2 0 1 0 0 1 0 0.521802117
## 2 1 1 0 0 0 0 0.516953243
## 2 0 1 0 0 0 1 0.515633047
## 2 0 1 0 1 0 0 0.515615676
## 2 1 0 0 0 1 0 0.271141182
## 3 1 1 1 0 0 0 0.622836599
## 3 0 1 1 0 1 0 0.621317501
## 3 0 1 1 1 0 0 0.621106795
## 3 0 1 1 0 0 1 0.620794889
## 3 0 0 1 0 1 1 0.581281670
## 3 0 0 1 1 0 1 0.580164420
## 3 0 0 1 1 1 0 0.580081922
## 3 1 0 1 0 0 1 0.580052550
## 3 1 0 1 0 1 0 0.580011995
## 3 1 0 1 1 0 0 0.578329066
## 4 1 1 1 0 1 0 0.623190011
## 4 1 1 1 1 0 0 0.622944711
## 4 1 1 1 0 0 1 0.622808914
## 4 0 1 1 1 1 0 0.621320048
## 4 0 1 1 0 1 1 0.621284137
## 4 0 1 1 1 0 1 0.620982152
## 4 0 0 1 1 1 1 0.581028308
## 4 1 0 1 0 1 1 0.581002963
## 4 1 0 1 1 0 1 0.579901293
## 4 1 0 1 1 1 0 0.579789019
## 5 1 1 1 0 1 1 0.623357027
## 5 1 1 1 1 1 0 0.623163675
## 5 1 1 1 1 0 1 0.622977308
## 5 0 1 1 1 1 1 0.621320860
## 5 1 0 1 1 1 1 0.580751344
## 5 1 1 0 1 1 1 0.526869388
## 6 1 1 1 1 1 1 0.623372977
# Look at the summary of the model with the largest adjusted r-squared
summary(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + lot_size + num_parking_spots + house_age,
data = clean_housing))
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -643581 -95423 -13986 74081 988217
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.094e+05 2.280e+04 -4.796 1.8e-06 ***
## num_of_bedrooms -1.968e+04 6.787e+03 -2.900 0.00379 **
## num_of_bathrooms 9.000e+04 7.231e+03 12.446 < 2e-16 ***
## square_feet 1.307e+02 6.991e+00 18.694 < 2e-16 ***
## lot_size 6.569e-03 6.388e-03 1.028 0.30395
## num_parking_spots 8.542e+03 5.481e+03 1.558 0.11936
## house_age 1.847e+02 1.394e+02 1.325 0.18537
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179700 on 1359 degrees of freedom
## Multiple R-squared: 0.625, Adjusted R-squared: 0.6234
## F-statistic: 377.5 on 6 and 1359 DF, p-value: < 2.2e-16
Stepwise Regression - Forward Selection
When using stepwise regression (forward selection), we take the approach of starting with an empty model and adding independent variables based on the results we see. Here, we see that the convariates number of bathrooms, number of bedrooms, and square feet are the best performers. The p-values for lot size, number of parking spots, and house age are greater than 5%, we hold off from adding any additional covariates to our new model, model 3.
# Start with an empty model
add1(lm(price_sold ~ 1, data = clean_housing), price_sold ~ num_of_bedrooms +
num_of_bathrooms + square_feet + lot_size + num_parking_spots +
house_age, test = "F")
## Single term additions
##
## Model:
## price_sold ~ 1
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 1.1705e+14 34390
## num_of_bedrooms 1 2.5906e+13 9.1142e+13 34050 387.7014 < 2.2e-16 ***
## num_of_bathrooms 1 6.0229e+13 5.6819e+13 33404 1445.8598 < 2.2e-16 ***
## square_feet 1 6.7768e+13 4.9280e+13 33210 1875.7297 < 2.2e-16 ***
## lot_size 1 6.3453e+11 1.1641e+14 34384 7.4347 0.00648 **
## num_parking_spots 1 1.3388e+13 1.0366e+14 34226 176.1666 < 2.2e-16 ***
## house_age 1 3.4413e+12 1.1361e+14 34351 41.3173 1.785e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Add the covariate with the highest f-value and lowest p-value and repeat
add1(lm(price_sold ~ square_feet, data = clean_housing), price_sold ~ num_of_bedrooms +
num_of_bathrooms + square_feet + lot_size + num_parking_spots +
house_age, test = "F")
## Single term additions
##
## Model:
## price_sold ~ square_feet
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.9280e+13 33210
## num_of_bedrooms 1 2.4952e+09 4.9277e+13 33212 0.0690 0.79281
## num_of_bathrooms 1 4.9793e+12 4.4300e+13 33066 153.2006 < 2e-16 ***
## lot_size 1 2.9667e+10 4.9250e+13 33211 0.8210 0.36504
## num_parking_spots 1 2.2757e+11 4.9052e+13 33206 6.3234 0.01203 *
## house_age 1 2.2902e+11 4.9051e+13 33206 6.3638 0.01176 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Add the next covariate with the highest f-value and lowest p-value and repeat
add1(lm(price_sold ~ square_feet + num_of_bathrooms, data = clean_housing),
price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet + lot_size +
num_parking_spots + house_age, test = "F")
## Single term additions
##
## Model:
## price_sold ~ square_feet + num_of_bathrooms
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.4300e+13 33066
## num_of_bedrooms 1 2.5132e+11 4.4049e+13 33061 7.7708 0.005384 **
## lot_size 1 4.9294e+10 4.4251e+13 33067 1.5172 0.218255
## num_parking_spots 1 7.3902e+10 4.4226e+13 33066 2.2759 0.131631
## house_age 1 1.2866e+10 4.4287e+13 33068 0.3957 0.529432
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Add the next covariate with the highest f-value and lowest p-value and repeat
add1(lm(price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
data = clean_housing), price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + lot_size + num_parking_spots + house_age, test = "F")
## Single term additions
##
## Model:
## price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.4049e+13 33061
## lot_size 1 4.4959e+10 4.4004e+13 33061 1.3905 0.2385
## num_parking_spots 1 7.3586e+10 4.3975e+13 33060 2.2774 0.1315
## house_age 1 2.9111e+10 4.4020e+13 33062 0.9000 0.3429
# Create a model for the selected covariates
summary(lm(price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
data = clean_housing))
##
## Call:
## lm(formula = price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
## data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -639756 -95345 -14342 73654 990772
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -85198.344 18285.022 -4.659 3.48e-06 ***
## square_feet 133.825 6.832 19.587 < 2e-16 ***
## num_of_bathrooms 88131.166 6931.618 12.714 < 2e-16 ***
## num_of_bedrooms -18809.275 6747.451 -2.788 0.00538 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179800 on 1362 degrees of freedom
## Multiple R-squared: 0.6237, Adjusted R-squared: 0.6228
## F-statistic: 752.4 on 3 and 1362 DF, p-value: < 2.2e-16
housing_model3 <- lm(price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
data = clean_housing)
Stepwise Regression - Backward Selection
When using stepwise regression (backward selection), we take the approach of starting with a complete model and removing independent variables based on the results we see. Here, we see that the same covariates of number of bathrooms, number of bedrooms, and square feet are the winner so we continue with model 3.
# Start with a full model
drop1(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + lot_size + num_parking_spots + house_age,
data = clean_housing), test = "F")
## Single term deletions
##
## Model:
## price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet +
## lot_size + num_parking_spots + house_age
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.3889e+13 33062
## num_of_bedrooms 1 2.7161e+11 4.4161e+13 33068 8.4102 0.003791 **
## num_of_bathrooms 1 5.0028e+12 4.8892e+13 33207 154.9067 < 2.2e-16 ***
## square_feet 1 1.1286e+13 5.5176e+13 33372 349.4744 < 2.2e-16 ***
## lot_size 1 3.4156e+10 4.3924e+13 33061 1.0576 0.303947
## num_parking_spots 1 7.8438e+10 4.3968e+13 33062 2.4288 0.119360
## house_age 1 5.6704e+10 4.3946e+13 33061 1.7558 0.185373
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Remove the covariates with the lowest f-value and highest p-value and repeat
drop1(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet + num_parking_spots + house_age,
data = housing), test = "F")
## Single term deletions
##
## Model:
## price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet +
## num_parking_spots + house_age
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 1.2059e+14 34973
## num_of_bedrooms 1 1.9964e+12 1.2259e+14 34993 22.8796 1.909e-06 ***
## num_of_bathrooms 1 5.4026e+12 1.2599e+14 35031 61.9167 7.181e-15 ***
## square_feet 1 3.4219e+13 1.5481e+14 35317 392.1690 < 2.2e-16 ***
## num_parking_spots 1 7.1055e+10 1.2066e+14 34971 0.8143 0.3670
## house_age 1 1.4646e+10 1.2060e+14 34971 0.1679 0.6821
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Remove the next covariates with the lowest f-value and highest p-value and repeat
drop1(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet +
num_parking_spots, data = clean_housing), test = "F")
## Single term deletions
##
## Model:
## price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet +
## num_parking_spots
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.3975e+13 33060
## num_of_bedrooms 1 2.5100e+11 4.4226e+13 33066 7.7683 0.005391 **
## num_of_bathrooms 1 5.0751e+12 4.9051e+13 33208 157.0693 < 2.2e-16 ***
## square_feet 1 1.1616e+13 5.5592e+13 33379 359.5184 < 2.2e-16 ***
## num_parking_spots 1 7.3586e+10 4.4049e+13 33061 2.2774 0.131502
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Remove the next covariates with the lowest f-value and highest p-value and repeat
drop1(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet, data = clean_housing), test = "F")
## Single term deletions
##
## Model:
## price_sold ~ num_of_bedrooms + num_of_bathrooms + square_feet
## Df Sum of Sq RSS AIC F value Pr(>F)
## <none> 4.4049e+13 33061
## num_of_bedrooms 1 2.5132e+11 4.4300e+13 33066 7.7708 0.005384 **
## num_of_bathrooms 1 5.2282e+12 4.9277e+13 33212 161.6552 < 2.2e-16 ***
## square_feet 1 1.2408e+13 5.6457e+13 33398 383.6432 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Create a model for the selected covariates - Same as forward approach
summary(lm(price_sold ~ num_of_bedrooms + num_of_bathrooms +
square_feet, data = housing))
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet, data = housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1200674 -112274 -11350 87062 5781909
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -108876.42 29744.32 -3.660 0.000261 ***
## num_of_bedrooms -51965.48 10877.42 -4.777 1.96e-06 ***
## num_of_bathrooms 88364.14 11051.65 7.996 2.70e-15 ***
## square_feet 204.16 10.15 20.117 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 295300 on 1384 degrees of freedom
## Multiple R-squared: 0.5516, Adjusted R-squared: 0.5507
## F-statistic: 567.6 on 3 and 1384 DF, p-value: < 2.2e-16
Below is a summary of the models we have created up to this point. We will be validating each of these models in the next section to determine which of our models is the best predictor of our housing sale price.
Model 1: All covariates and original housing data
# Contains all covariates and original housing data (resolved NA values)
summary(housing_model1)
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1910181 -116738 -12530 89325 5835847
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.386e+05 3.716e+04 -3.729 0.0002 ***
## num_of_bedrooms -4.601e+04 1.112e+04 -4.139 3.7e-05 ***
## num_of_bathrooms 1.115e+05 1.135e+04 9.819 < 2e-16 ***
## square_feet 1.793e+02 9.841e+00 18.219 < 2e-16 ***
## lot_size 2.146e-05 3.189e-04 0.067 0.9464
## num_parking_spots -4.712e+03 8.883e+03 -0.531 0.5958
## house_age 1.534e+02 2.294e+02 0.669 0.5037
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 300600 on 1381 degrees of freedom
## Multiple R-squared: 0.5364, Adjusted R-squared: 0.5343
## F-statistic: 266.3 on 6 and 1381 DF, p-value: < 2.2e-16
# Plot model1
plot(housing_model1)
Model 2: All covariates and cleaned housing data (resolved outliers)
This model was also selected as part of our variable selection using our adjusted r-squared.
# Contains all covariates and cleaned housing data (resolved outliers)
summary(housing_model2)
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -643581 -95423 -13986 74081 988217
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.094e+05 2.280e+04 -4.796 1.8e-06 ***
## num_of_bedrooms -1.968e+04 6.787e+03 -2.900 0.00379 **
## num_of_bathrooms 9.000e+04 7.231e+03 12.446 < 2e-16 ***
## square_feet 1.307e+02 6.991e+00 18.694 < 2e-16 ***
## lot_size 6.569e-03 6.388e-03 1.028 0.30395
## num_parking_spots 8.542e+03 5.481e+03 1.558 0.11936
## house_age 1.847e+02 1.394e+02 1.325 0.18537
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179700 on 1359 degrees of freedom
## Multiple R-squared: 0.625, Adjusted R-squared: 0.6234
## F-statistic: 377.5 on 6 and 1359 DF, p-value: < 2.2e-16
# Plot model2
plot(housing_model2)
Model 3: Stepwise variable selection and cleaned housing data
This model selected using both the forward and backward approach of the stepwise variable selection process.
# Adjusted r-squared variable selection
summary(housing_model3)
##
## Call:
## lm(formula = price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
## data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -639756 -95345 -14342 73654 990772
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -85198.344 18285.022 -4.659 3.48e-06 ***
## square_feet 133.825 6.832 19.587 < 2e-16 ***
## num_of_bathrooms 88131.166 6931.618 12.714 < 2e-16 ***
## num_of_bedrooms -18809.275 6747.451 -2.788 0.00538 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179800 on 1362 degrees of freedom
## Multiple R-squared: 0.6237, Adjusted R-squared: 0.6228
## F-statistic: 752.4 on 3 and 1362 DF, p-value: < 2.2e-16
# Plot model3
plot(housing_model3)
The below model validation will be done for each of the models we created in order to see how they perform throughout the validation process.
Adjusted R-Squared: Our adjusted r-squared indicates how much variability we can explain in our model.
Model 1:
We can explain 53.43% of the variability in model 1.
# Adjusted r-squared
summary(housing_model1)$adj.r.squared
## [1] 0.5343469
Model 2:
We can explain 62.32% of the variability in model 2.
# Adjusted r-squared
summary(housing_model2)$adj.r.squared
## [1] 0.623373
Model 3:
We can explain 62.28% of the variability in model 3.
# Adjusted r-squared
summary(housing_model3)$adj.r.squared
## [1] 0.6228366
Hypothesis Testing: Hypothesis testing determines the probability that we will incur a type 1 error. Generally, if greater than 5%, we are likely to incur a type 1 error.
Model 1:
All of our covariates except for lot size, number of parking spots, and house age are less than 5%. Those lower than 5% we can say we are unlikely to incur a type 1 error.
# Hypothesis testing
summary(housing_model1)$coefficients[,4]
## (Intercept) num_of_bedrooms num_of_bathrooms square_feet
## 2.002805e-04 3.700219e-05 4.828470e-22 1.239074e-66
## lot_size num_parking_spots house_age
## 9.463535e-01 5.958491e-01 5.037049e-01
Model 2:
All of our covariates except for lot size, number of parking spots, and house age are less than 5%. Those lower than 5% we can say we are unlikely to incur a type 1 error.
# Hypothesis testing
summary(housing_model2)$coefficients[,4]
## (Intercept) num_of_bedrooms num_of_bathrooms square_feet
## 1.797664e-06 3.791235e-03 9.392577e-34 1.392432e-69
## lot_size num_parking_spots house_age
## 3.039470e-01 1.193601e-01 1.853734e-01
Model 3:
All of our covariates are less than 5% so this model is unlikely to incur a type 1 error.
# Hypothesis testing
summary(housing_model3)$coefficients[,4]
## (Intercept) square_feet num_of_bathrooms num_of_bedrooms
## 3.480713e-06 1.843271e-75 4.446722e-35 5.383603e-03
Confidence Interval: Confidence intervals tell us the range of of values in which we can be 95% confident that our true slope falls within the range.
Model 1:
All of our covariates have a small, all positive or all negative range indicating that we have a strong prediction of the range of our true slope. However, lot size, number of parking spots, and house age all contain zero - a big red flag. This is not unexpected as these 3 covariates also had a high probability of incurring a type 1 error during hypothesis testing.
# confidence interval
confint(housing_model1, level = 0.95)
## 2.5 % 97.5 %
## (Intercept) -2.114540e+05 -6.566134e+04
## num_of_bedrooms -6.781346e+04 -2.420200e+04
## num_of_bathrooms 8.920665e+04 1.337514e+05
## square_feet 1.599833e+02 1.985920e+02
## lot_size -6.041123e-04 6.470350e-04
## num_parking_spots -2.213698e+04 1.271255e+04
## house_age -2.965471e+02 6.033836e+02
Model 2:
All of our covariates have a small, all positive or all negative range indicating that we have a strong prediction of the range of our true slope. However, lot size, number of parking spots, and house age again all contain zero like we saw in model 1.
# confidence interval
confint(housing_model2, level = 0.95)
## 2.5 % 97.5 %
## (Intercept) -1.540905e+05 -6.462690e+04
## num_of_bedrooms -3.299851e+04 -6.368748e+03
## num_of_bathrooms 7.581592e+04 1.041873e+05
## square_feet 1.169733e+02 1.444011e+02
## lot_size -5.961750e-03 1.909992e-02
## num_parking_spots -2.210408e+03 1.929503e+04
## house_age -8.876388e+01 4.582535e+02
Model 3:
All of our covariates have a medium, all positive or all negative range indicating that we have a good prediction of the range of our true slope.
# confidence interval
confint(housing_model3, level = 0.95)
## 2.5 % 97.5 %
## (Intercept) -121068.2051 -49328.4829
## square_feet 120.4216 147.2279
## num_of_bathrooms 74533.3604 101728.9719
## num_of_bedrooms -32045.7990 -5572.7506
Standard Error: Standard error gives us insight into the variability we would expect as we add more data.
Model 1:
In model 1, we should expect to see high variability for all of our covariates except for square feet (5.47%) and number of bathrooms (10.18%) as we add more data. All other covariates have 24% or higher variability which is not terrible, but not ideal.
# Standard error
summary(housing_model1)$coefficients[,1:2]
## Estimate Std. Error
## (Intercept) -1.385577e+05 3.716009e+04
## num_of_bedrooms -4.600773e+04 1.111583e+04
## num_of_bathrooms 1.114790e+05 1.135370e+04
## square_feet 1.792876e+02 9.840704e+00
## lot_size 2.146135e-05 3.188963e-04
## num_parking_spots -4.712217e+03 8.882558e+03
## house_age 1.534182e+02 2.293772e+02
# Intercept
3.719776e+04 / 1.373595e+05
## [1] 0.2708059
# Num of bedrooms
1.111569e+04 / 4.596541e+04
## [1] 0.2418273
# Num of bathrooms
1.135088e+04 / 1.115209e+05
## [1] 0.1017825
# Square feet
9.825128e+00 / 1.794136e+02
## [1] 0.05476245
# Lot size
3.189049e-04 / 2.271410e-05
## [1] 14.03995
# Number of parking spots
8.760708e+03 / 5.483070e+03
## [1] 1.597774
# House age
2.286712e+02 / 1.515446e+02
## [1] 1.508937
Model 2:
In model 2, we should expect to see high variability for all of our covariates except for square feet (5.3%), number of bathrooms (8.05%), and lot size (10.39%) as we add more data. All other covariates have 21% or higher variability which is not terrible, but not ideal.
# Standard error
summary(housing_model2)$coefficients[,1:2]
## Estimate Std. Error
## (Intercept) -1.093587e+05 2.280245e+04
## num_of_bedrooms -1.968363e+04 6.787380e+03
## num_of_bathrooms 9.000160e+04 7.231279e+03
## square_feet 1.306872e+02 6.990775e+00
## lot_size 6.569087e-03 6.387708e-03
## num_parking_spots 8.542312e+03 5.481296e+03
## house_age 1.847448e+02 1.394235e+02
# Intercept
2.282842e+04 / 1.078097e+05
## [1] 0.2117474
# Num of bedrooms
6.789224e+03 / 1.966124e+04
## [1] 0.3453101
# Num of bathrooms
7.232142e+03 / 9.009630e+04
## [1] 0.08027124
# Square feet
6.981615e+00 / 1.310689e+02
## [1] 0.05326676
# Lot size
1.907181e-04 / 1.835479e-05
## [1] 10.39064
# Number of parking spots
5.400466e+03 / 7.196672e+03
## [1] 0.7504116
# House age
1.758936e+02 / 1.390504e+02
## [1] 1.264963
Model 3:
In model 3, we should expect to see low variability for all of our covariates except for number of bedrooms which is high at 53.87%.
# Standard error
summary(housing_model3)$coefficients[,1:2]
## Estimate Std. Error
## (Intercept) -85198.3440 18285.022322
## square_feet 133.8248 6.832392
## num_of_bathrooms 88131.1662 6931.618169
## num_of_bedrooms -18809.2748 6747.451279
# Intercept
18285.022322 / 85198.3440
## [1] 0.2146171
# Square feet
6.832392 / 133.8248
## [1] 0.05105475
# Num of bathrooms
6931.618169 / 88131.1662
## [1] 0.07865116
# Num of bedrooms
6747.451279 / 18809.2748
## [1] 0.35873
Multicollinearity checks for non-linear dependencies among our regression variables and implies near-linear dependencies among the regressors.
Although we do see some trends that could indicate multicollinearity, once we look closed and look at the variance of inflation factor we see that our numbers are still under 5, indicating there is not multicollinear relationship.
# Visualize data sets - housing data
pairs(housing[c(3,5:6,8:10,12)], pch = 20)
# Model summary
summary(housing_model1)
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1910181 -116738 -12530 89325 5835847
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.386e+05 3.716e+04 -3.729 0.0002 ***
## num_of_bedrooms -4.601e+04 1.112e+04 -4.139 3.7e-05 ***
## num_of_bathrooms 1.115e+05 1.135e+04 9.819 < 2e-16 ***
## square_feet 1.793e+02 9.841e+00 18.219 < 2e-16 ***
## lot_size 2.146e-05 3.189e-04 0.067 0.9464
## num_parking_spots -4.712e+03 8.883e+03 -0.531 0.5958
## house_age 1.534e+02 2.294e+02 0.669 0.5037
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 300600 on 1381 degrees of freedom
## Multiple R-squared: 0.5364, Adjusted R-squared: 0.5343
## F-statistic: 266.3 on 6 and 1381 DF, p-value: < 2.2e-16
# Visualize data sets - cleaned housing data
pairs(clean_housing[c(3,5:6,8:10,12)], pch = 20)
# Model summary
summary(housing_model2)
##
## Call:
## lm(formula = price_sold ~ num_of_bedrooms + num_of_bathrooms +
## square_feet + lot_size + num_parking_spots + house_age, data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -643581 -95423 -13986 74081 988217
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.094e+05 2.280e+04 -4.796 1.8e-06 ***
## num_of_bedrooms -1.968e+04 6.787e+03 -2.900 0.00379 **
## num_of_bathrooms 9.000e+04 7.231e+03 12.446 < 2e-16 ***
## square_feet 1.307e+02 6.991e+00 18.694 < 2e-16 ***
## lot_size 6.569e-03 6.388e-03 1.028 0.30395
## num_parking_spots 8.542e+03 5.481e+03 1.558 0.11936
## house_age 1.847e+02 1.394e+02 1.325 0.18537
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179700 on 1359 degrees of freedom
## Multiple R-squared: 0.625, Adjusted R-squared: 0.6234
## F-statistic: 377.5 on 6 and 1359 DF, p-value: < 2.2e-16
summary(housing_model3)
##
## Call:
## lm(formula = price_sold ~ square_feet + num_of_bathrooms + num_of_bedrooms,
## data = clean_housing)
##
## Residuals:
## Min 1Q Median 3Q Max
## -639756 -95345 -14342 73654 990772
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -85198.344 18285.022 -4.659 3.48e-06 ***
## square_feet 133.825 6.832 19.587 < 2e-16 ***
## num_of_bathrooms 88131.166 6931.618 12.714 < 2e-16 ***
## num_of_bedrooms -18809.275 6747.451 -2.788 0.00538 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 179800 on 1362 degrees of freedom
## Multiple R-squared: 0.6237, Adjusted R-squared: 0.6228
## F-statistic: 752.4 on 3 and 1362 DF, p-value: < 2.2e-16
# Correlation of variables
cor(housing[c(3,5:6,8:10,12)])
## price_sold num_of_bedrooms num_of_bathrooms square_feet
## price_sold 1.00000000 0.408165815 0.64818202 0.7267966
## num_of_bedrooms 0.40816581 1.000000000 0.60524973 0.6177780
## num_of_bathrooms 0.64818202 0.605249732 1.00000000 0.7836840
## square_feet 0.72679661 0.617777980 0.78368405 1.0000000
## lot_size -0.01312973 -0.008931345 -0.01292244 -0.0209228
## num_parking_spots 0.28999525 0.274513383 0.37901112 0.4050623
## house_age -0.14466964 -0.061212050 -0.28241176 -0.1546785
## lot_size num_parking_spots house_age
## price_sold -0.0131297286 0.289995253 -0.1446696355
## num_of_bedrooms -0.0089313445 0.274513383 -0.0612120503
## num_of_bathrooms -0.0129224440 0.379011117 -0.2824117625
## square_feet -0.0209227956 0.405062296 -0.1546784652
## lot_size 1.0000000000 0.005288107 -0.0005541334
## num_parking_spots 0.0052881068 1.000000000 -0.2553295961
## house_age -0.0005541334 -0.255329596 1.0000000000
cor(clean_housing[c(3,5:6,8:10,12)])
## price_sold num_of_bedrooms num_of_bathrooms square_feet
## price_sold 1.00000000 0.47045558 0.71733292 0.76090553
## num_of_bedrooms 0.47045558 1.00000000 0.59342185 0.61349195
## num_of_bathrooms 0.71733292 0.59342185 1.00000000 0.76967951
## square_feet 0.76090553 0.61349195 0.76967951 1.00000000
## lot_size 0.07362809 0.02705712 0.04423361 0.07590112
## num_parking_spots 0.33820334 0.25530854 0.35539065 0.39114299
## house_age -0.17146630 -0.07081886 -0.29516802 -0.16803897
## lot_size num_parking_spots house_age
## price_sold 0.07362809 0.3382033 -0.17146630
## num_of_bedrooms 0.02705712 0.2553085 -0.07081886
## num_of_bathrooms 0.04423361 0.3553907 -0.29516802
## square_feet 0.07590112 0.3911430 -0.16803897
## lot_size 1.00000000 0.1733433 -0.09229007
## num_parking_spots 0.17334326 1.0000000 -0.25595055
## house_age -0.09229007 -0.2559506 1.00000000
# Variance inflation factor
vif <- function(mod, ...) {
if (any(is.na(coef(mod))))
stop("there are aliased coefficients in the model")
v <- vcov(mod)
assign <- attr(model.matrix(mod), "assign")
if (names(coefficients(mod)[1]) == "(Intercept)") {
v <- v[-1, -1]
assign <- assign[-1]
}
else warning("No intercept: vifs may not be sensible.")
terms <- labels(terms(mod))
n.terms <- length(terms)
if (n.terms < 2) stop("model contains fewer than 2 terms")
R <- cov2cor(v)
detR <- det(R)
result <- matrix(0, n.terms, 3)
rownames(result) <- terms
colnames(result) <- c("GVIF", "Df", "GVIF^(1/(2*Df))")
for (term in 1:n.terms) {
subs <- which(assign == term)
result[term, 1] <- det(as.matrix(R[subs, subs])) *
det(as.matrix(R[-subs, -subs])) / detR
result[term, 2] <- length(subs)
}
if (all(result[, 2] == 1)) result <- result[, 1]
else result[, 3] <- result[, 1]^(1/(2 * result[, 2]))
result
}
vif(housing_model1)
## num_of_bedrooms num_of_bathrooms square_feet lot_size
## 1.736424 2.812369 2.673052 1.000662
## num_parking_spots house_age
## 1.255516 1.157981
vif(housing_model2)
## num_of_bedrooms num_of_bathrooms square_feet lot_size
## 1.724578 2.838031 2.836030 1.036563
## num_parking_spots house_age
## 1.264158 1.167772
vif(housing_model3)
## square_feet num_of_bathrooms num_of_bedrooms
## 2.705127 2.603983 1.701923
For all of our predictions we will be using a k-fold to pull out a portion of our data to use as testing data to see how well our models can make predictions.
Model 1:
# K-fold
KCV1 = cv.lm(data = housing, housing_model1, m = 10, seed = 0)
##
## fold 1
## Observations in test set: 138
## 4 7 12 34 42 55
## Predicted 200161.89 608111.5 412054.45 66316.93 249824.94 438723.4
## cvpred 198438.47 607800.2 410952.12 68637.77 251980.98 429356.0
## price_sold 178000.00 275000.0 399000.00 230000.00 292000.00 1075000.0
## CV residual -20438.47 -332800.2 -11952.12 161362.23 40019.02 645644.0
## 62 74 80 123 138 153 179
## Predicted 261588.2 253920.89 355453.5 430546.3 510783.3 117584.5 420940.19
## cvpred 265656.7 262248.92 354731.5 430612.1 515436.1 120919.6 432799.12
## price_sold 110000.0 355000.00 550000.0 63497.0 24000.0 225000.0 410000.00
## CV residual -155656.7 92751.08 195268.5 -367115.1 -491436.1 104080.4 -22799.12
## 184 189 197 217 219 264 283
## Predicted 586373.56 567111.68 519223.26 470539.6 444324.2 1173680 358582.06
## cvpred 594682.08 554312.89 530345.01 464887.5 447816.6 1183320 353001.43
## price_sold 525000.00 566000.00 435000.00 297000.0 834900.0 2200000 276000.00
## CV residual -69682.08 11687.11 -95345.01 -167887.5 387083.4 1016680 -77001.43
## 285 289 294 300 305 307 317
## Predicted 223469.9 407050.6 32622.17 1066915.2 991547.0 286156.7 385700.6
## cvpred 220784.2 418880.1 30132.68 1082320.8 1010589.6 290737.8 383960.0
## price_sold 244800.0 630000.0 155000.00 565000.0 600000.0 178000.0 224000.0
## CV residual 24015.8 211119.9 124867.32 -517320.8 -410589.6 -112737.8 -159960.0
## 328 342 348 371 380 381 386
## Predicted 1520476 337619.0 445051.7 367691.4 481955.4 804914.0 1080062
## cvpred 1578159 341566.4 444245.9 373997.0 485846.0 818467.1 1107413
## price_sold 350000 387500.0 331500.0 192500.0 300000.0 700000.0 1425000
## CV residual -1228159 45933.6 -112745.9 -181497.0 -185846.0 -118467.1 317587
## 391 406 410 431 432 452 458
## Predicted 884956.5 290921.88 774855.1 587399.7 192440.7 470666.00 225671.4
## cvpred 899826.5 296601.19 784591.9 608389.2 199995.1 463533.64 238476.4
## price_sold 525000.0 255000.00 999000.0 449500.0 183000.0 414000.00 50000.0
## CV residual -374826.5 -41601.19 214408.1 -158889.2 -16995.1 -49533.64 -188476.4
## 461 478 491 493 503 505
## Predicted 283448.81 302602.1 165346.48 541794.6 333275.6 345141.37
## cvpred 277227.39 298841.6 160522.68 539637.4 329866.3 339057.66
## price_sold 288900.00 135000.0 215000.00 375000.0 500000.0 265000.00
## CV residual 11672.61 -163841.6 54477.32 -164637.4 170133.7 -74057.66
## 520 525 529 558 576 598 601
## Predicted 421654.33 404436.1 334005.35 455473.7 367984.35 620460.6 365411.7
## cvpred 424087.95 405632.1 330604.22 448092.5 366119.17 630853.9 364207.0
## price_sold 410000.00 559000.0 320000.00 595000.0 305000.00 487000.0 200000.0
## CV residual -14087.95 153367.9 -10604.22 146907.5 -61119.17 -143853.9 -164207.0
## 608 614 617 627 632 635
## Predicted 335996.31 471327.9 701019.1 331449.654 396967.19 188683.82
## cvpred 333370.66 477493.5 706452.2 326747.904 396490.53 200602.44
## price_sold 282000.00 289000.0 550000.0 325000.000 300000.00 188000.00
## CV residual -51370.66 -188493.5 -156452.2 -1747.904 -96490.53 -12602.44
## 647 663 671 675 677 684 711
## Predicted 697549.8 339928.1 985485.8 287003.0 214694.8 714546.4 216948.20
## cvpred 707538.2 335898.0 1006482.6 293371.7 213941.2 739082.6 215478.66
## price_sold 246000.0 325000.0 749900.0 262500.0 380000.0 300000.0 184900.00
## CV residual -461538.2 -10898.0 -256582.6 -30871.7 166058.8 -439082.6 -30578.66
## 717 722 733 736 741 756
## Predicted 561894.6 308997.23 713851.9 427777.3 559107.9 129726.606
## cvpred 568704.4 304996.99 728440.7 441591.8 574035.4 133614.975
## price_sold 440000.0 395000.00 155000.0 150000.0 38500.0 126000.000
## CV residual -128704.4 90003.01 -573440.7 -291591.8 -535535.4 -7614.975
## 770 774 805 832 862 866 873
## Predicted 156877.53 366778.8 55729.86 102593.1 155632.72 165452.51 248937.6
## cvpred 155980.77 365557.0 57804.59 105118.0 162223.83 163911.93 252432.1
## price_sold 230000.00 260000.0 282525.00 265000.0 125000.00 140000.00 660000.0
## CV residual 74019.23 -105557.0 224720.41 159882.0 -37223.83 -23911.93 407567.9
## 906 912 913 915 916 948
## Predicted 610273.17 209224.83 324588.35 49548.23 129160.13 190468.47
## cvpred 612329.14 210198.37 321206.19 49722.02 124669.29 190527.11
## price_sold 575000.00 270000.00 283900.00 143000.00 176500.00 230000.00
## CV residual -37329.14 59801.63 -37306.19 93277.98 51830.71 39472.89
## 949 961 972 980 981 986
## Predicted 178218.81 337232.17 38754.23 203155.09 143128.47 135464.76
## cvpred 175603.59 345638.93 45105.81 201049.62 139082.25 130129.29
## price_sold 197000.00 253000.00 85000.00 121500.00 93000.00 199000.00
## CV residual 21396.41 -92638.93 39894.19 -79549.62 -46082.25 68870.71
## 992 994 1010 1017 1028 1042
## Predicted 100774.71 148778.16 231520.67 371821.40 109756.09 125570.4
## cvpred 107611.85 147600.47 235650.67 372070.74 117250.84 130507.9
## price_sold 200000.00 194000.00 276670.00 410000.00 159000.00 457500.0
## CV residual 92388.15 46399.53 41019.33 37929.26 41749.16 326992.1
## 1054 1057 1064 1068 1069 1070
## Predicted 203028.942 463052.568 469208.9 92058.88 371013.37 364709.64
## cvpred 201832.013 465163.436 467236.3 96959.86 365525.75 361324.48
## price_sold 193000.000 460000.000 333500.0 325000.00 319000.00 319900.00
## CV residual -8832.013 -5163.436 -133736.3 228040.14 -46525.75 -41424.48
## 1072 1078 1081 1083 1099 1100 1114
## Predicted 182194.6 356267.41 221513.2 367222.3 169408.307 320276.6 228589.64
## cvpred 186299.3 365390.29 224362.2 371330.8 167122.287 327144.2 228762.94
## price_sold 329000.0 350000.00 506000.0 130500.0 175000.000 461814.0 250000.00
## CV residual 142700.7 -15390.29 281637.8 -240830.8 7877.713 134669.8 21237.06
## 1122 1124 1136 1142 1144 1145 1158
## Predicted 513147.34 387832.5 517312.0 45622.37 513482.45 195776.80 126609.43
## cvpred 517307.36 386364.3 514084.4 49894.31 520546.72 191584.39 131284.63
## price_sold 445500.00 465000.0 485000.0 200000.00 465000.00 255000.00 50000.00
## CV residual -71807.36 78635.7 -29084.4 150105.69 -55546.72 63415.61 -81284.63
## 1159 1188 1195 1206 1209 1233
## Predicted 235836.89 191683.06 139081.28 165870.00 329803.43 228096.4
## cvpred 237740.36 202762.29 147460.01 164024.42 328639.17 232609.2
## price_sold 187000.00 191000.00 110650.00 190000.00 420000.00 86000.0
## CV residual -50740.36 -11762.29 -36810.01 25975.58 91360.83 -146609.2
## 1243 1252 1255 1275 1278 1296
## Predicted 673233.2 472882.92 333041 206921.4 333356.92 59318.89
## cvpred 690362.2 466480.22 326034 206806.4 335974.49 61098.69
## price_sold 110000.0 535000.00 145000 85000.0 350000.00 162000.00
## CV residual -580362.2 68519.78 -181034 -121806.4 14025.51 100901.31
## 1313 1315 1319 1325 1334 1354
## Predicted 227209.825 385888.04 479991.1 298501.26 266846.61 81871.92
## cvpred 226558.956 388016.46 483743.7 301558.75 266654.42 88051.23
## price_sold 220000.000 382500.00 221000.0 225000.00 214000.00 125000.00
## CV residual -6558.956 -5516.46 -262743.7 -76558.75 -52654.42 36948.77
## 1382 1385
## Predicted 443857.0 251977.41
## cvpred 459800.8 244231.71
## price_sold 70000.0 170000.00
## CV residual -389800.8 -74231.71
##
## Sum of squares = 7.621504e+12 Mean square = 55228290830 n = 138
##
## fold 2
## Observations in test set: 139
## 5 8 9 11 21 23
## Predicted 374942.0 628772.07 207039.52 382161.310 287158.1 47871.80
## cvpred 383440.7 616454.18 212191.15 343769.035 279036.9 49970.45
## price_sold 269900.0 680000.00 233000.00 341000.000 403000.0 110000.00
## CV residual -113540.7 63545.82 20808.85 -2769.035 123963.1 60029.55
## 27 70 82 88 89 102 108
## Predicted 99367.54 203741.6 330946.1 519727.9 551079.5 435016.87 2419538
## cvpred 90858.19 214501.4 330629.9 526199.4 568064.1 449903.25 2333556
## price_sold 317500.00 535000.0 425000.0 259900.0 218900.0 525000.00 3500000
## CV residual 226641.81 320498.6 94370.1 -266299.4 -349164.1 75096.75 1166444
## 113 117 120 128 147 151
## Predicted 752330.2 500878.54 304977.4 659373.1 464271.5 808863.9
## cvpred 743416.3 496704.21 317497.6 655874.8 452829.0 797845.7
## price_sold 615000.0 525000.00 205000.0 437000.0 615000.0 555000.0
## CV residual -128416.3 28295.79 -112497.6 -218874.8 162171.0 -242845.7
## 156 157 169 173 175 177 199
## Predicted 337382.36 364997.2 644765.5 904472.0 1880205 215897.8 121119.3
## cvpred 336323.91 351092.2 643986.3 878830.2 1806481 217555.9 132636.7
## price_sold 415000.00 193000.0 415500.0 385000.0 3650000 485000.0 279000.0
## CV residual 78676.09 -158092.2 -228486.3 -493830.2 1843519 267444.1 146363.3
## 203 210 212 235 249 259 263
## Predicted 549922.50 1610350 61486.18 1009391.1 387833.77 1365482.9 881552.8
## cvpred 545319.74 1554525 57414.61 976318.8 395327.71 1315611.2 876738.5
## price_sold 611000.00 2800000 290000.00 1300000.0 465000.00 1937500.0 585000.0
## CV residual 65680.26 1245475 232585.39 323681.2 69672.29 621888.8 -291738.5
## 275 279 288 292 295 302
## Predicted 515661.2 221535.0 587288.89 331408.88 209310.76 910973.9
## cvpred 523182.3 219721.2 592260.01 344534.86 217841.16 906684.4
## price_sold 421500.0 275000.0 515000.00 355000.00 250000.00 490000.0
## CV residual -101682.3 55278.8 -77260.01 10465.14 32158.84 -416684.4
## 311 322 334 387 422 427
## Predicted 862127.3 1399920.3 337619.04 862542.2 926259.8 739147.9
## cvpred 851008.7 1346509.2 343193.05 851624.6 911439.1 733824.4
## price_sold 1125000.0 518535.0 387500.00 940000.0 1305000.0 475000.0
## CV residual 273991.3 -827974.2 44306.95 88375.4 393560.9 -258824.4
## 443 444 457 459 464 479
## Predicted 155605.07 738928.7 304175.64 257264.59 417423.8 1328437.8
## cvpred 163755.52 734695.8 302275.06 257438.02 408206.5 1293645.9
## price_sold 210000.00 499000.0 400000.00 207000.00 297000.0 799900.0
## CV residual 46244.48 -235695.8 97724.94 -50438.02 -111206.5 -493745.9
## 492 500 516 526 545 556
## Predicted 730237.0 505835.3 716602.9 561198.02 75859.65 487821.82
## cvpred 730862.4 509084.7 703807.6 559685.75 76739.80 478465.61
## price_sold 530230.0 427000.0 1500100.0 608000.00 180000.00 555000.00
## CV residual -200632.4 -82084.7 796292.4 48314.25 103260.20 76534.39
## 562 583 611 612 630 633
## Predicted 934947.7 479003.9 236811.00 421697.87 582139.9 133878.36
## cvpred 929085.6 474083.3 240540.83 418213.48 578554.0 128684.37
## price_sold 1058756.0 249900.0 226000.00 467000.00 260000.0 175000.00
## CV residual 129670.4 -224183.3 -14540.83 48786.52 -318554.0 46315.63
## 636 638 643 652 693 695
## Predicted 355447.08 196582.46 81384.00 251982.72 434249.2 502133.51
## cvpred 365195.82 175521.69 72527.66 247845.28 430051.4 492510.28
## price_sold 331000.00 188000.00 146500.00 270000.00 269900.0 577000.00
## CV residual -34195.82 12478.31 73972.34 22154.72 -160151.4 84489.72
## 699 700 707 709 715 716 726
## Predicted 283562.07 67322.25 608928.0 367433.26 444656.2 561894.6 461083.6
## cvpred 302178.46 64249.84 604452.3 380066.91 452787.5 549387.0 451569.1
## price_sold 360000.00 95000.00 415000.0 358000.00 324900.0 440000.0 815000.0
## CV residual 57821.54 30750.16 -189452.3 -22066.91 -127887.5 -109387.0 363430.9
## 728 732 738 746 747 753
## Predicted 227545.650 213658.07 165513.48 271648.4 208947.6 299509.60
## cvpred 231313.753 204703.07 172790.59 265541.2 214596.9 288910.81
## price_sold 235000.000 218000.00 116500.00 286000.0 228000.0 229900.00
## CV residual 3686.247 13296.93 -56290.59 20458.8 13403.1 -59010.81
## 754 758 768 792 801 803 808
## Predicted 432100.0 280806.0 213328.1 327598.62 173326.45 84430.70 20112.19
## cvpred 429586.3 274165.4 212511.1 336421.92 178073.73 83805.11 24542.50
## price_sold 190000.0 655000.0 159900.0 263000.00 223000.00 210000.00 155900.00
## CV residual -239586.3 380834.6 -52611.1 -73421.92 44926.27 126194.89 131357.50
## 812 831 839 848 849 869
## Predicted 619728.34 404177.1 350083.53 442296.9 9783.395 200259.8
## cvpred 611695.19 404569.1 362841.79 424944.1 15704.594 201473.7
## price_sold 710000.00 263500.0 337000.00 276000.0 165000.000 379000.0
## CV residual 98304.81 -141069.1 -25841.79 -148944.1 149295.406 177526.3
## 890 892 926 934 940 941 942
## Predicted 247102.8 316330.77 219240.41 142350.37 333304.1 106434.72 322596.19
## cvpred 248276.0 331009.47 222462.97 133718.78 327792.3 102872.72 313729.84
## price_sold 196000.0 280000.00 169000.00 146000.00 584900.0 185000.00 295000.00
## CV residual -52276.0 -51009.47 -53462.97 12281.22 257107.7 82127.28 -18729.84
## 954 958 987 988 1003 1004 1016
## Predicted 147144.6 365022.6 510178.9 238077.2 353778.8 412052.40 78055.24
## cvpred 150543.5 371048.3 505566.4 237307.1 356836.6 406568.95 77800.37
## price_sold 79000.0 230000.0 232000.0 500000.0 575000.0 315000.00 135000.00
## CV residual -71543.5 -141048.3 -273566.4 262692.9 218163.4 -91568.95 57199.63
## 1018 1020 1032 1035 1055 1060 1061
## Predicted 321560.3 140161.824 116896.9 109234.7 165299.8 263279.52 267210.75
## cvpred 317309.0 131387.054 107597.8 118591.6 172277.9 262383.44 265495.61
## price_sold 164000.0 135800.000 175000.0 320150.0 335000.0 346000.00 351000.00
## CV residual -153309.0 4412.946 67402.2 201558.4 162722.1 83616.56 85504.39
## 1073 1088 1097 1098 1101 1140
## Predicted 315680.892 259062.41 219287.48 419984.74 263895.86 216191.70
## cvpred 304550.931 281226.27 210273.39 413342.33 278779.14 216956.64
## price_sold 310000.000 210000.00 187000.00 475000.00 230000.00 235000.00
## CV residual 5449.069 -71226.27 -23273.39 61657.67 -48779.14 18043.36
## 1184 1192 1199 1226 1236 1242 1283
## Predicted 221382.5 168567.1 253404.9 553965.2 346965.68 201018.43 221150.31
## cvpred 221167.2 171060.8 263029.2 563066.3 345971.16 197683.46 217528.05
## price_sold 339000.0 325000.0 520000.0 197750.0 435000.00 165000.00 275000.00
## CV residual 117832.8 153939.2 256970.8 -365316.3 89028.84 -32683.46 57471.95
## 1306 1317 1329 1343 1345 1347
## Predicted 327883.41 548095.0 348197.9 336116.1 215315.11 119826.48
## cvpred 312724.89 559255.4 334087.7 321962.3 207392.39 109714.72
## price_sold 235000.00 370000.0 229900.0 200000.0 300749.00 131000.00
## CV residual -77724.89 -189255.4 -104187.7 -121962.3 93356.61 21285.28
## 1353 1374 1376 1379
## Predicted 45999.15 478833.652 211674.55 325296.38
## cvpred 44012.81 471372.218 221481.17 308819.84
## price_sold 100000.00 467000.000 190000.00 280000.00
## CV residual 55987.19 -4372.218 -31481.17 -28819.84
##
## Sum of squares = 1.167992e+13 Mean square = 84028190545 n = 139
##
## fold 3
## Observations in test set: 139
## 19 22 28 32 38 45
## Predicted 300491.58 231349.73 362214.2 241402.5 525334.1 173993.190
## cvpred 309569.14 225021.94 366803.6 231849.9 516240.9 171779.108
## price_sold 219000.00 173000.00 120000.0 363000.0 1175000.0 165000.000
## CV residual -90569.14 -52021.94 -246803.6 131150.1 658759.1 -6779.108
## 47 60 84 87 106 116 121
## Predicted 169849.50 211674.81 579043.3 214246.0 536312.40 456528.0 213469.28
## cvpred 162338.23 204304.17 582270.1 214132.2 532022.71 458003.9 208731.92
## price_sold 134000.00 190000.00 700000.0 450000.0 625000.00 67019.0 147000.00
## CV residual -28338.23 -14304.17 117729.9 235867.8 92977.29 -390984.9 -61731.92
## 129 144 148 174 180 190 196
## Predicted 225034.7 755066.3 587567.7 202.060 418695.4 1320940.3 300782.8
## cvpred 216877.7 753975.8 581257.8 -1187.552 415766.3 1323534.7 298120.5
## price_sold 92500.0 915000.0 375000.0 205000.000 565000.0 1609000.0 440000.0
## CV residual -124377.7 161024.2 -206257.8 206187.552 149233.7 285465.3 141879.5
## 206 208 221 224 227 240 241
## Predicted 1184453.5 1779743.9 176792.3 561575.0 639399.1 1052053.6 1418845.4
## cvpred 1184151.7 1799996.9 196386.1 553904.8 642529.7 1053306.9 1432673.9
## price_sold 932000.0 1501960.0 562200.0 750000.0 528000.0 1350000.0 1300000.0
## CV residual -252151.7 -298036.9 365813.9 196095.2 -114529.7 296693.1 -132673.9
## 272 318 327 333 336 337 354
## Predicted 622603.7 197350.4 1336886.3 537560.0 195257 1766499 501820.7
## cvpred 620941.8 189649.6 1354499.8 538853.4 191830 1790465 511579.7
## price_sold 170000.0 260000.0 1842700.0 365000.0 290000 609000 712000.0
## CV residual -450941.8 70350.4 488200.2 -173853.4 98170 -1181465 200420.3
## 367 369 372 378 383 392
## Predicted 856428.943 655671.6 220253.64 486283.359 389901.0 769988.6
## cvpred 861502.357 655404.2 215299.28 486778.501 382893.5 771157.9
## price_sold 858700.000 444500.0 266000.00 485000.000 280000.0 475000.0
## CV residual -2802.357 -210904.2 50700.72 -1778.501 -102893.5 -296157.9
## 393 394 400 408 409 411
## Predicted 199645.26 654769.9 335402.41 768133.3 393393.4 415292.82
## cvpred 196492.24 651114.7 332831.63 775690.7 397076.7 418312.57
## price_sold 255500.00 500000.0 308000.00 1075000.0 245000.0 325000.00
## CV residual 59007.76 -151114.7 -24831.63 299309.3 -152076.7 -93312.57
## 423 433 438 441 446 450 455
## Predicted 926259.8 192440.65 382771.6 364546.4 555167.2 1043565.7 267346.37
## cvpred 945001.6 187159.05 388668.9 366350.9 552628.3 1050408.3 264928.61
## price_sold 1306000.0 183000.00 330000.0 549980.0 900000.0 800000.0 292900.00
## CV residual 360998.4 -4159.05 -58668.9 183629.1 347371.7 -250408.3 27971.39
## 456 473 477 483 494 498
## Predicted 534256.4 468267.62 565120.4 601667.76 115189.80 142141.1
## cvpred 537391.8 467140.84 578631.6 605287.17 98951.69 143181.7
## price_sold 405000.0 499900.00 215000.0 520000.00 290000.00 174528.0
## CV residual -132391.8 32759.16 -363631.6 -85287.17 191048.31 31346.3
## 502 510 521 532 548 551
## Predicted 279721.171 256756.1 584898.6 609776.5 181866.3 606303.8
## cvpred 276753.283 256527.0 585221.8 616646.3 185763.4 605188.5
## price_sold 280000.000 129900.0 177000.0 489900.0 255000.0 405000.0
## CV residual 3246.717 -126627.0 -408221.8 -126746.3 69236.6 -200188.5
## 555 559 575 589 591 600 613
## Predicted 139560.59 662016.8 270239.52 199052.17 712615.4 696888.0 1414508
## cvpred 131204.81 656695.8 260950.21 197861.59 728002.6 693017.9 1404393
## price_sold 159000.00 399000.0 180000.00 219900.00 900000.0 545000.0 3025000
## CV residual 27795.19 -257695.8 -80950.21 22038.41 171997.4 -148017.9 1620607
## 616 645 651 653 655 670
## Predicted 702614.0 373691.92 445646.7 251982.72 616876.5 269678.065
## cvpred 703627.7 370401.38 443794.0 254847.66 615745.5 267284.937
## price_sold 550000.0 320305.00 270000.0 270000.00 320000.0 270000.000
## CV residual -153627.7 -50096.38 -173794.0 15152.34 -295745.5 2715.063
## 673 697 713 718 723 743
## Predicted 570176.2 182594.41 457564.2 263642.6 220504.84 226854.6
## cvpred 584485.4 177200.35 463172.0 265508.6 218808.48 227429.3
## price_sold 310000.0 130000.00 161975.0 98775.0 140000.00 80000.0
## CV residual -274485.4 -47200.35 -301197.0 -166733.6 -78808.48 -147429.3
## 752 779 787 796 800 823
## Predicted 390037.50 351576.5 314990.28 161355.45 29135.11 173517.59
## cvpred 396179.56 350355.5 319948.55 160789.74 30606.36 176044.64
## price_sold 460000.00 385000.0 335000.00 199900.00 104900.00 220000.00
## CV residual 63820.44 34644.5 15051.45 39110.26 74293.64 43955.36
## 824 829 830 883 891 899
## Predicted 228086.21 525527.4 167054.66 194401.4 115821.52 614447.916
## cvpred 230392.56 539576.5 167418.01 197565.9 117690.12 627108.896
## price_sold 300000.00 136429.0 241000.00 89000.0 215000.00 625000.000
## CV residual 69607.44 -403147.5 73581.99 -108565.9 97309.88 -2108.896
## 914 977 1001 1013 1014 1023
## Predicted 49548.23 281032.28 274492.7 72559.31 116401.33 307242.51
## cvpred 44972.73 280344.63 274053.5 68918.13 102377.61 308307.19
## price_sold 143000.00 295000.00 384000.0 105000.00 170000.00 280000.00
## CV residual 98027.27 14655.37 109946.5 36081.87 67622.39 -28307.19
## 1040 1043 1062 1063 1065 1074 1082
## Predicted 342858.1 242639.2 487114.0 339548.2 188606.29 204184.64 269294.8
## cvpred 351146.9 245601.5 481836.9 334914.6 194603.83 198604.52 268938.5
## price_sold 237160.0 467000.0 305000.0 173000.0 276000.00 275000.00 499000.0
## CV residual -113986.9 221398.5 -176836.9 -161914.6 81396.17 76395.48 230061.5
## 1095 1106 1118 1141 1146 1150
## Predicted 228317.00 -714.4482 366557.6 42845.07 161515.47 59601.97
## cvpred 231284.34 -6300.4015 376092.1 36531.70 164406.81 51037.42
## price_sold 190000.00 155000.0000 555000.0 105111.00 256000.00 165000.00
## CV residual -41284.34 161300.4015 178907.9 68579.30 91593.19 113962.58
## 1157 1169 1173 1176 1186 1205
## Predicted 440299.8 431101.2 346238.5 108094.00 162997.22 276870.4
## cvpred 433905.1 432049.9 359802.0 103954.82 166552.33 288862.4
## price_sold 592000.0 290000.0 246000.0 40000.00 187500.00 50013.0
## CV residual 158094.9 -142049.9 -113802.0 -63954.82 20947.67 -238849.4
## 1208 1214 1215 1221 1249 1254
## Predicted 41227.63 136251.78 277137.8 203738.4 157921.80 318838.6
## cvpred 36280.42 135694.32 275322.0 207776.6 156900.79 326137.8
## price_sold 237500.00 111500.00 67000.0 347500.0 197400.00 145000.0
## CV residual 201219.58 -24194.32 -208322.0 139723.4 40499.21 -181137.8
## 1261 1262 1268 1270 1287 1300
## Predicted 437027.115 432999.4 212306.5 103311.70 38375.75 235253.123
## cvpred 431206.814 444390.6 223008.5 102936.44 26875.86 239742.437
## price_sold 435000.000 322000.0 372000.0 27886.00 142000.00 242394.000
## CV residual 3793.186 -122390.6 148991.5 -75050.44 115124.14 2651.563
## 1303 1327 1330 1339 1357 1383
## Predicted 196970.94 196626.44 362400.2 262493.46 338644.34 222195.409
## cvpred 209102.28 204182.43 368682.3 251453.03 336385.54 217327.499
## price_sold 168000.00 150000.00 229000.0 240316.00 425000.00 214000.000
## CV residual -41102.28 -54182.43 -139682.3 -11137.03 88614.46 -3327.499
##
## Sum of squares = 8.434033e+12 Mean square = 60676496241 n = 139
##
## fold 4
## Observations in test set: 139
## 31 48 51 52 58 61
## Predicted 568711.8 314238.9 351916.2 358219.9 546869.4 204209.43
## cvpred 549896.8 333285.9 357147.2 368982.8 563011.1 211112.97
## price_sold 2050000.0 230000.0 200000.0 200000.0 170000.0 150000.00
## CV residual 1500103.2 -103285.9 -157147.2 -168982.8 -393011.1 -61112.97
## 75 91 99 100 107 132 137
## Predicted 350718.0 281188.7 2611430.1 687340.4 322196.4 357926.4 375778.5
## cvpred 349866.8 264348.7 2589834.1 683015.7 320746.6 362429.0 366659.5
## price_sold 185000.0 365000.0 2900000.0 875000.0 450000.0 249900.0 69668.0
## CV residual -164866.8 100651.3 310165.9 191984.3 129253.4 -112529.0 -296991.5
## 150 168 194 205 207 215 218
## Predicted 391096.64 350265.02 1458925 348860.05 510024.1 977095.2 32726.80
## cvpred 389049.72 354458.37 1454605 347267.88 506046.0 975959.3 32752.33
## price_sold 355000.00 420000.00 2495000 349900.00 398000.0 470000.0 179725.00
## CV residual -34049.72 65541.63 1040395 2632.12 -108046.0 -505959.3 146972.67
## 238 242 244 245 254 260 291
## Predicted 54108.43 813785.46 365832.3 460476.8 937320.8 208345.63 564755.5
## cvpred 47781.59 809112.43 361501.4 456167.5 937527.4 220777.31 561124.0
## price_sold 108000.00 792000.00 250000.0 525000.0 792500.0 122000.00 983750.0
## CV residual 60218.41 -17112.43 -111501.4 68832.5 -145027.4 -98777.31 422626.0
## 298 310 321 323 335 340 351
## Predicted 1221660.6 674409.3 262883.7 790538.29 198147.75 271867.1 558824.2
## cvpred 1211130.7 675575.4 177034.9 799506.24 197433.04 271031.5 555072.4
## price_sold 975000.0 325500.0 605000.0 728000.00 289900.00 310000.0 349900.0
## CV residual -236130.7 -350075.4 427965.1 -71506.24 92466.96 38968.5 -205172.4
## 361 363 377 404 416 419
## Predicted 561418.57 768133.4 221848.56 349341.13 684313.9 262109.35
## cvpred 564919.69 768579.3 221818.65 347666.59 671763.1 259686.44
## price_sold 512500.00 1075000.0 269300.00 300000.00 300000.0 200000.00
## CV residual -52419.69 306420.7 47481.35 -47666.59 -371763.1 -59686.44
## 426 434 440 453 460 470
## Predicted 401625.89 716809.1 556598.83 288159.4 257264.59 74365.827
## cvpred 399858.58 724220.7 567177.34 298902.7 256513.58 80028.392
## price_sold 330000.00 550000.0 624900.00 163500.0 207000.00 81500.000
## CV residual -69858.58 -174220.7 57722.66 -135402.7 -49513.58 1471.608
## 490 499 507 512 523 527
## Predicted 395549.61 671359.2 668355.9 378904.8 427913.9 406066.82
## cvpred 393715.04 673407.6 664351.9 377562.6 432478.9 404563.94
## price_sold 312500.00 394500.0 396000.0 257000.0 325000.0 381300.00
## CV residual -81215.04 -278907.6 -268351.9 -120562.6 -107478.9 -23263.94
## 528 549 550 557 560 567
## Predicted 404166.44 328799.6 550486.1 491285.80 399368.26 274818.9
## cvpred 395644.89 332324.2 553444.3 494845.55 403010.79 265642.1
## price_sold 440000.00 218000.0 335000.0 420000.00 390000.00 454500.0
## CV residual 44355.11 -114324.2 -218444.3 -74845.55 -13010.79 188857.9
## 609 620 637 640 644 649
## Predicted 161143.67 520846.2 93259.32 445958.5 251982.72 379757.20
## cvpred 159773.07 524518.3 91124.78 442037.9 244273.19 379037.65
## price_sold 175000.00 300000.0 109500.00 225000.0 270000.00 349900.00
## CV residual 15226.93 -224518.3 18375.22 -217037.9 25726.81 -29137.65
## 658 660 679 683 686 690
## Predicted 425321.61 454467.447 923240.8 463952.5 239023.9 465885.42
## cvpred 421920.37 450150.863 925266.8 462170.9 243847.8 464290.59
## price_sold 383000.00 449000.000 1432500.0 355000.0 378000.0 558650.00
## CV residual -38920.37 -1150.863 507233.2 -107170.9 134152.2 94359.41
## 704 706 712 744 749 762 764
## Predicted 522437.9 237060.79 61151.88 355248.6 33445.44 239869.14 136617.3
## cvpred 525706.9 241878.82 60658.88 360294.0 33721.55 245932.31 141311.8
## price_sold 280000.0 259900.00 84500.00 163600.0 200100.00 275000.00 295000.0
## CV residual -245706.9 18021.18 23841.12 -196694.0 166378.45 29067.69 153688.2
## 785 786 790 809 810 822
## Predicted 132175.32 388282.7 267556.56 133800.54 392147.5 88840.64
## cvpred 135186.99 391444.1 272503.24 128091.78 389908.9 87008.98
## price_sold 205000.00 740000.0 174900.00 219900.00 270000.0 68000.00
## CV residual 69813.01 348555.9 -97603.24 91808.22 -119908.9 -19008.98
## 842 856 864 871 872 875
## Predicted 218113.5 301339.6 177280.0 198853.744 272069.99 216030.016
## cvpred 228923.7 283437.2 181260.8 198492.552 249928.62 220391.017
## price_sold 80000.0 589000.0 360000.0 195000.000 172000.00 230000.000
## CV residual -148923.7 305562.8 178739.2 -3492.552 -77928.62 9608.983
## 904 905 924 925 938 963 965
## Predicted 339163.6 318524.15 607981.4 345054.75 113686.2 195337.3 41496.39
## cvpred 315070.6 316953.32 610716.4 356183.57 108001.2 195124.6 35375.05
## price_sold 430000.0 257500.00 400000.0 380000.00 396300.0 320500.0 140000.00
## CV residual 114929.4 -59453.32 -210716.4 23816.43 288298.8 125375.4 104624.95
## 967 985 996 1000 1005 1012 1024
## Predicted 220339.3 313462.4 185517.2 184853.38 551550.77 311175.35 359315.0
## cvpred 211561.8 311830.7 189147.3 184066.91 562319.13 308779.33 369859.8
## price_sold 79900.0 420000.0 322400.0 90000.00 487600.00 210000.00 262500.0
## CV residual -131661.8 108169.3 133252.7 -94066.91 -74719.13 -98779.33 -107359.8
## 1033 1050 1056 1059 1092 1116
## Predicted 129658.202 234860.00 557688.2 193058.57 59733.78 274818.7
## cvpred 135825.684 239339.22 551977.7 197524.03 63661.77 265641.8
## price_sold 129000.000 190000.00 185000.0 227000.00 88000.00 454500.0
## CV residual -6825.684 -49339.22 -366977.7 29475.97 24338.23 188858.2
## 1123 1125 1127 1149 1154 1166 1174
## Predicted 258669.9 362008.3 262812.5 73828.24 313532.6 683603.0 233335.5
## cvpred 270805.6 372904.1 261489.2 78670.71 322796.0 688167.6 238010.4
## price_sold 105000.0 260000.0 478000.0 158000.00 150000.0 1240000.0 375000.0
## CV residual -165805.6 -112904.1 216510.8 79329.29 -172796.0 551832.4 136989.6
## 1175 1178 1185 1189 1201 1203
## Predicted 370137.73 488381.70 193528.67 234580.5 376002.4 75267.11
## cvpred 380650.02 498630.18 192625.62 225683.6 392615.9 80094.96
## price_sold 325000.00 402000.00 288500.00 385000.0 235000.0 277000.00
## CV residual -55650.02 -96630.18 95874.38 159316.4 -157615.9 196905.04
## 1212 1220 1225 1248 1266 1267
## Predicted 194498.89 399323.4 440572.32 276103.38 427370.0 187975.1
## cvpred 193201.17 389497.4 436603.32 279724.89 433149.9 186096.6
## price_sold 145000.00 74000.0 389000.00 181900.00 295000.0 70000.0
## CV residual -48201.17 -315497.4 -47603.32 -97824.89 -138149.9 -116096.6
## 1273 1280 1285 1288 1298 1302
## Predicted 563821.86 563821.86 399247.05 138853.69 182768.570 182768.570
## cvpred 574310.72 574310.72 403613.14 144024.79 174885.282 174885.282
## price_sold 590000.00 590000.00 374900.00 182500.00 168000.000 168000.000
## CV residual 15689.28 15689.28 -28713.14 38475.21 -6885.282 -6885.282
## 1336 1340 1365 1384 1387
## Predicted 262955.53 88350.44 314693.7 144937.90 829810.2
## cvpred 267872.02 77861.39 331543.3 162781.18 843017.8
## price_sold 239900.00 140000.00 219000.0 92500.00 625000.0
## CV residual -27972.02 62138.61 -112543.3 -70281.18 -218017.8
##
## Sum of squares = 7.442271e+12 Mean square = 53541520832 n = 139
##
## fold 5
## Observations in test set: 139
## 18 26 43 56 57 65 139
## Predicted 626907.2 363258.8 202811.99 352611.8 389080.2 360340.40 675527.0
## cvpred 642630.4 361043.0 212207.49 368928.4 402833.8 379219.73 695187.4
## price_sold 1050000.0 480000.0 185000.00 264900.0 440000.0 439000.00 390000.0
## CV residual 407369.6 118957.0 -27207.49 -104028.4 37166.2 59780.27 -305187.4
## 141 142 143 158 160 183 185
## Predicted 430361.1 481519.9 377161.11 1108937 1743335.2 944923.8 1509177.1
## cvpred 436695.6 493059.1 384334.09 1113660 1785762.6 963853.3 1554815.9
## price_sold 294900.0 212000.0 291500.00 2525000 1600000.0 528400.0 980000.0
## CV residual -141795.6 -281059.1 -92834.09 1411340 -185762.6 -435453.3 -574815.9
## 213 216 233 248 253 257
## Predicted 238198.972 1006449.3 423970.52 453670.6 1640422.12 1495951.6
## cvpred 240998.408 1024106.2 429526.14 456899.0 1686027.07 1538106.5
## price_sold 242000.000 640000.0 465000.00 950000.0 1650000.00 935000.0
## CV residual 1001.592 -384106.2 35473.86 493101.0 -36027.07 -603106.5
## 262 266 270 273 276 280 301
## Predicted 434936.46 450961.8 1042643 225864.8 213964.90 1474044.3 1754816.8
## cvpred 440596.92 454505.1 1054714 228143.5 218367.38 1514248.2 1795090.4
## price_sold 515000.00 275000.0 950000 19330.0 310000.00 1010000.0 2350000.0
## CV residual 74403.08 -179505.1 -104714 -208813.5 91632.62 -504248.2 554909.6
## 312 320 325 330 338 339
## Predicted 1693291.1 1046943.2 387092.04 104412.2 155970.00 1005417.3
## cvpred 1741605.5 1067612.3 390135.78 105607.3 154391.17 1030194.9
## price_sold 1000000.0 650000.0 325000.00 215000.0 202000.00 483100.0
## CV residual -741605.5 -417612.3 -65135.78 109392.7 47608.83 -547094.9
## 341 343 346 376 418 425
## Predicted 739211.1 152325.86 552738.7 602541.11 364230.0 540058.47
## cvpred 755627.3 150903.08 561223.8 611445.15 367621.6 549618.81
## price_sold 585000.0 235000.00 380000.0 581000.00 180000.0 460000.00
## CV residual -170627.3 84096.92 -181223.8 -30445.15 -187621.6 -89618.81
## 447 467 480 485 488 509
## Predicted 576231.7 115932.27 1328437.8 55643.50 324611.8 690805.9
## cvpred 581459.5 110855.92 1362852.6 54377.64 328324.4 702003.8
## price_sold 357500.0 63000.00 799900.0 150000.00 466400.0 350000.0
## CV residual -223959.5 -47855.92 -562952.6 95622.36 138075.6 -352003.8
## 535 547 570 578 587 590 622
## Predicted 77414.89 318267.5 201510.81 337304.02 174041.62 299481.3 223533.08
## cvpred 75348.78 322166.8 201973.97 341064.44 166243.51 295961.4 231346.74
## price_sold 110111.00 272000.0 225000.00 360000.00 115000.00 405000.0 195000.00
## CV residual 34762.22 -50166.8 23026.03 18935.56 -51243.51 109038.6 -36346.74
## 624 626 634 642 648 654
## Predicted 329077.133 192077.6 234070.55 395561.16 177789.5 609870.9
## cvpred 335043.293 194768.7 243619.19 405123.43 185439.5 621829.9
## price_sold 329000.000 237500.0 340000.00 435000.00 287990.0 379000.0
## CV residual -6043.293 42731.3 96380.81 29876.57 102550.5 -242829.9
## 659 662 694 698 725 727 729
## Predicted 545245.67 518501.8 836387.3 227435.26 461083.6 286888.4 149432.4
## cvpred 542897.41 527797.1 848359.7 229053.54 452208.5 290597.9 143561.0
## price_sold 449000.00 350000.0 319000.0 194900.00 815000.0 120000.0 273000.0
## CV residual -93897.41 -177797.1 -529359.7 -34153.54 362791.5 -170597.9 129439.0
## 755 757 759 766 775 780
## Predicted 345095.17 435298.8 245500.938 819183.7 127977.28 236639.8
## cvpred 353708.14 438201.8 238269.695 825975.3 125645.94 232091.8
## price_sold 275000.00 238775.0 235000.000 1025000.0 170000.00 115000.0
## CV residual -78708.14 -199426.8 -3269.695 199024.7 44354.06 -117091.8
## 784 794 807 814 817 825
## Predicted 340502.31 416533.105 165157.4 647904.9 403410.73 39475.97
## cvpred 342523.58 434142.992 163250.2 666256.9 408085.93 37169.46
## price_sold 260000.00 430000.000 55000.0 451000.0 369415.00 162000.00
## CV residual -82523.58 -4142.992 -108250.2 -215256.9 -38670.93 124830.54
## 827 844 847 850 874 878 889
## Predicted 34846.9 435993.2 292704.40 190534.99 227565.93 54373.38 147890.6
## cvpred 32631.9 443354.8 294988.24 191967.22 230724.87 53483.19 145254.4
## price_sold 173900.0 276000.0 255000.00 220000.00 195000.00 193500.00 267500.0
## CV residual 141268.1 -167354.8 -39988.24 28032.78 -35724.87 140016.81 122245.6
## 897 900 902 903 910 922 923
## Predicted 5227.77 373089.89 148470.13 271662.6 651836.31 344383.6 549275.1
## cvpred 3607.38 371831.48 156838.23 263956.9 667118.81 341555.2 567224.3
## price_sold 155100.00 445000.00 100000.00 381000.0 605000.00 299900.0 375000.0
## CV residual 151492.62 73168.52 -56838.23 117043.1 -62118.81 -41655.2 -192224.3
## 928 929 933 944 955 956
## Predicted 144324.443 394068.3 591114.2 163291.20 305096.83 169737.6
## cvpred 141895.851 398468.4 602878.2 158781.78 307305.07 170107.6
## price_sold 135000.000 545000.0 382000.0 180000.00 270000.00 155000.0
## CV residual -6895.851 146531.6 -220878.2 21218.22 -37305.07 -15107.6
## 960 973 991 1009 1011 1027 1037
## Predicted 266855.8 164629.93 510178.9 340785 242430.99 53546.19 91108.02
## cvpred 259393.0 163758.15 519244.2 338104 240073.18 51714.31 94742.41
## price_sold 110000.0 240300.00 232000.0 250000 209500.00 90000.00 119000.00
## CV residual -149393.0 76541.85 -287244.2 -88104 -30573.18 38285.69 24257.59
## 1038 1039 1079 1111 1112 1113
## Predicted 265950.6 46672.15 56923.42 261356.2 287369.35 185516.40
## cvpred 257494.7 47056.84 58398.39 251761.8 288353.62 184583.87
## price_sold 135000.0 149900.00 180000.00 39000.0 221500.00 272000.00
## CV residual -122494.7 102843.16 121601.61 -212761.8 -66853.62 87416.13
## 1119 1120 1128 1129 1164 1168
## Predicted 164675.08 73606.05 326454.1 165420.96 250068.92 187055.4
## cvpred 155047.18 69278.68 324372.4 167524.77 245907.86 182910.3
## price_sold 145000.00 140000.00 190600.0 83000.00 195000.00 315000.0
## CV residual -10047.18 70721.32 -133772.4 -84524.77 -50907.86 132089.7
## 1171 1172 1197 1237 1246 1247
## Predicted 209846.57 204966.4 361800.0 435212.60 363950.8 290430.36
## cvpred 202722.55 200729.5 359093.3 429276.68 366329.4 284233.15
## price_sold 282000.00 388400.0 235000.0 351000.00 151750.0 235000.00
## CV residual 79277.45 187670.5 -124093.3 -78276.68 -214579.4 -49233.15
## 1250 1253 1256 1258 1259 1264
## Predicted 276511.90 527432.5 90748.88 194468.90 173383.15 421787.87
## cvpred 268550.05 540091.1 86711.73 192844.21 171645.14 432327.47
## price_sold 280000.00 750000.0 58500.00 238000.00 235000.00 385000.00
## CV residual 11449.95 209908.9 -28211.73 45155.79 63354.86 -47327.47
## 1274 1286 1311 1314 1318 1321
## Predicted 253323.1 201510.51 277512.1 230558.7 243901.40 60505.28
## cvpred 250227.2 201973.66 267644.9 222340.4 239394.05 60801.73
## price_sold 50000.0 225000.00 165000.0 2900.0 195000.00 131000.00
## CV residual -200227.2 23026.34 -102644.9 -219440.4 -44394.05 70198.27
## 1337 1363 1366 1371 1386
## Predicted 262770.70 261786.5 262678.26 203048.29 208607.02
## cvpred 274785.34 260421.7 274808.37 198606.78 216337.23
## price_sold 230000.00 60000.0 223000.00 135000.00 155000.00
## CV residual -44785.34 -200421.7 -51808.37 -63606.78 -61337.23
##
## Sum of squares = 7.664471e+12 Mean square = 55140077209 n = 139
##
## fold 6
## Observations in test set: 139
## 17 20 33 36 41 53 59
## Predicted 536129.0 300491.6 262770.93 407050.8 269212.3 280014.90 290387.2
## cvpred 495056.5 322343.7 244181.48 364597.7 254766.4 276520.98 268943.6
## price_sold 1050000.0 219000.0 230000.00 1050000.0 551900.0 285000.00 417000.0
## CV residual 554943.5 -103343.7 -14181.48 685402.3 297133.6 8479.02 148056.4
## 69 78 83 86 96 105 115
## Predicted 474540.0 409971.13 280813.629 261835.2 357831.1 1980409 258203.3
## cvpred 451576.2 401913.33 300896.244 243894.4 364177.6 1825549 260464.2
## price_sold 870000.0 310000.00 307000.000 419900.0 600000.0 3500000 133000.0
## CV residual 418423.8 -91913.33 6103.756 176005.6 235822.4 1674451 -127464.2
## 126 162 164 165 167 191 195
## Predicted 382755.4 594732.4 1613427 767566.3 1733647 2405719 136025.97
## cvpred 363278.1 641288.4 1490812 731187.1 1538977 2184920 159909.09
## price_sold 55605.0 425000.0 3850000 580000.0 7500000 3500000 255000.00
## CV residual -307673.1 -216288.4 2359188 -151187.1 5961023 1315080 95090.91
## 201 202 225 232 243 250
## Predicted 540060.50 363330.7 295094.3 592342.19 434566.89 811372.6
## cvpred 528057.79 394229.2 313971.3 561404.17 425407.76 761123.4
## price_sold 570000.00 280000.0 450000.0 572500.00 515000.00 647800.0
## CV residual 41942.21 -114229.2 136028.7 11095.83 89592.24 -113323.4
## 251 252 255 271 314 315
## Predicted 415204.78 1608771.5 713782.61 275804.91 1879501.9 534245.54
## cvpred 403854.32 1466247.6 728556.12 258995.31 1721738.8 514190.47
## price_sold 450500.00 1900000.0 695000.00 195000.00 1025000.0 550000.00
## CV residual 46645.68 433752.4 -33556.12 -63995.31 -696738.8 35809.53
## 326 345 350 358 366 368
## Predicted 1611451.1 1470131.94 323168.22 232884.18 782630.02 754528.7
## cvpred 1522432.7 1366864.01 332535.32 281045.93 742393.18 709616.6
## price_sold 1150000.0 1320000.00 340000.00 335000.00 800000.00 590000.0
## CV residual -372432.7 -46864.01 7464.68 53954.07 57606.82 -119616.6
## 384 397 401 413 414 428
## Predicted 810721.245 233429.97 234456.006 221983.18 140706.8 102593.4
## cvpred 790687.308 237828.55 244748.704 197988.68 149725.3 109061.0
## price_sold 800000.000 268000.00 250000.000 135000.00 292000.0 193900.0
## CV residual 9312.692 30171.45 5251.296 -62988.68 142274.7 84839.0
## 430 439 445 489 504 514 537
## Predicted 496465.3 588066.77 555167.2 405072.1 170022.9 786432.9 503227.1
## cvpred 552424.1 547121.69 525368.5 392290.3 172711.4 729937.5 475985.6
## price_sold 208980.0 587500.00 900000.0 375000.0 215000.0 460000.0 254000.0
## CV residual -343444.1 40378.31 374631.5 -17290.3 42288.6 -269937.5 -221985.6
## 538 539 566 574 579 580 582
## Predicted 389765.6 265972.71 274818.9 783752.74 1479491.5 431101.5 982940.7
## cvpred 383387.3 259509.91 298008.3 733141.07 1351377.8 424526.7 864713.9
## price_sold 545000.0 183000.00 454500.0 799000.00 545000.0 290000.0 600000.0
## CV residual 161612.7 -76509.91 156491.7 65858.93 -806377.8 -134526.7 -264713.9
## 586 588 593 594 605 618 639
## Predicted 384221.0 308332.3 293078.18 220504.9 33776.37 344439.9 186994.26
## cvpred 369860.6 298344.7 287504.29 215404.4 67809.34 325141.1 202014.04
## price_sold 235000.0 375000.0 276000.00 260000.0 119000.00 229000.0 266000.00
## CV residual -134860.6 76655.3 -11504.29 44595.6 51190.66 -96141.1 63985.96
## 650 661 666 667 672 680
## Predicted 550853.20 210146.15 203923.0 81640.81 985485.8 923240.8
## cvpred 556744.99 257826.98 214052.3 107046.47 929650.0 858626.6
## price_sold 640000.00 160100.00 329000.0 208000.00 749900.0 1430000.0
## CV residual 83255.01 -97726.98 114947.7 100953.53 -179750.0 571373.4
## 708 714 719 748 763 765
## Predicted 237060.78 471542.84 198164.5 33445.44 81486.65 238640.196
## cvpred 235438.76 459527.27 213699.3 52527.51 86314.41 243234.873
## price_sold 259900.00 415000.00 318900.0 200100.00 171000.00 250000.000
## CV residual 24461.24 -44527.27 105200.7 147572.49 84685.59 6765.127
## 769 783 793 811 845 852
## Predicted 479065.7 309730.8 285347.8 380125.0 388904.94 298265.35
## cvpred 504372.7 308570.3 289349.9 368553.4 376686.39 297609.17
## price_sold 395000.0 157000.0 172950.0 210000.0 360000.00 265000.00
## CV residual -109372.7 -151570.3 -116399.9 -158553.4 -16686.39 -32609.17
## 858 861 868 885 888 893 908
## Predicted 278837.9 74735.22 233803.8 302421.4 614447.92 329225.81 397718.8
## cvpred 279071.3 76560.07 228703.2 308591.4 605273.75 316619.61 421621.5
## price_sold 187500.0 60000.00 128000.0 330000.0 625000.00 275000.00 125000.0
## CV residual -91571.3 -16560.07 -100703.2 21408.6 19726.25 -41619.61 -296621.5
## 921 927 930 935 946 953
## Predicted 50127.112 293641.5 219937.3 379048.20 169594.924 327854.1
## cvpred 65559.177 279792.2 222456.4 375347.82 184397.241 331888.1
## price_sold 61000.000 130000.0 382000.0 284900.00 180000.000 176000.0
## CV residual -4559.177 -149792.2 159543.6 -90447.82 -4397.241 -155888.1
## 1006 1025 1036 1047 1048 1052 1053
## Predicted 149895.18 138566.9 215888.3 207535.39 144324.4 512918.8 204011.2
## cvpred 157423.37 165576.0 217148.5 230241.95 153214.3 509989.7 202978.3
## price_sold 145000.00 135000.0 355000.0 144900.00 81000.0 333850.0 175000.0
## CV residual -12423.37 -30576.0 137851.5 -85341.95 -72214.3 -176139.7 -27978.3
## 1058 1071 1085 1089 1117 1132
## Predicted 266288.5 227961.252 222028.48 376459.1 333533.5 235370.17
## cvpred 273467.3 260244.467 217637.94 370191.4 335243.0 245840.46
## price_sold 147500.0 253000.000 253000.00 449900.0 158200.0 178800.00
## CV residual -125967.3 -7244.467 35362.06 79708.6 -177043.0 -67040.46
## 1134 1179 1193 1200 1204 1213 1228
## Predicted 7519.369 227747.2 247437.72 577293.3 146072.96 258245.6 473577.9
## cvpred 34567.565 242058.8 261406.24 569782.0 158529.83 275859.5 420723.1
## price_sold 32000.000 60000.0 163500.00 655500.0 245000.00 429000.0 284700.0
## CV residual -2567.565 -182058.8 -97906.24 85718.0 86470.17 153140.5 -136023.1
## 1229 1240 1241 1271 1279 1281 1291
## Predicted 254080.6 221466.8 201018.43 443009.8 563821.86 168656.27 225444.34
## cvpred 268976.1 230113.2 206728.46 434914.9 522858.86 193413.02 231911.73
## price_sold 445000.0 435000.0 165000.00 282200.0 590000.00 140000.00 158000.00
## CV residual 176023.9 204886.8 -41728.46 -152714.9 67141.14 -53413.02 -73911.73
## 1292 1293 1308 1310 1320 1323 1324
## Predicted 506323.5 313842 380670.0 261974.6 343404.7 635761.57 209875.53
## cvpred 478166.7 340545 348554.6 265119.1 328222.2 582936.98 186926.19
## price_sold 42500.0 125000 160000.0 109000.0 1059162.0 549000.00 142500.00
## CV residual -435666.7 -215545 -188554.6 -156119.1 730939.8 -33936.98 -44426.19
## 1344 1350 1355 1364 1369 1372
## Predicted 222610.50 208344.21 143520.79 490546.13 242125.76 325376.40
## cvpred 255107.27 185301.64 158456.85 457187.22 218880.87 306065.97
## price_sold 212000.00 122000.00 90000.00 425500.00 275000.00 290000.00
## CV residual -43107.27 -63301.64 -68456.85 -31687.22 56119.13 -16065.97
## 1377 1380
## Predicted 256742.41 339498.74
## cvpred 227413.38 332283.73
## price_sold 245000.00 280000.00
## CV residual 17586.62 -52283.73
##
## Sum of squares = 5.103922e+13 Mean square = 367188635411 n = 139
##
## fold 7
## Observations in test set: 139
## 24 29 44 54 73 77 81
## Predicted 325376.65 38219.96 223234.1 528880.4 1293174.4 915995.4 1404973.5
## cvpred 322189.48 47130.39 230274.8 517625.3 1339176.8 919736.9 1457654.3
## price_sold 290000.00 90000.00 353000.0 769100.0 695000.0 540000.0 900000.0
## CV residual -32189.48 42869.61 122725.2 251474.7 -644176.8 -379736.9 -557654.3
## 90 103 109 136 154 170 176
## Predicted 227452.6 1681175.5 705287.6 315332.7 237213.12 105083.9 215897.8
## cvpred 227038.3 1725884.1 712271.6 324127.5 241016.52 104846.3 189718.0
## price_sold 365000.0 2400000.0 245000.0 167500.0 325000.00 230000.0 485000.0
## CV residual 137961.7 674115.9 -467271.6 -156627.5 83983.48 125153.7 295282.0
## 182 188 192 193 214 222 228
## Predicted 63053.31 169847.4 280658.2 621362.20 129841.77 544705.2 1788674
## cvpred 65038.37 170015.2 281105.1 622760.02 132142.09 541646.8 1851257
## price_sold 93765.00 320000.0 108500.0 600000.00 120000.00 426500.0 697600
## CV residual 28726.63 149984.8 -172605.1 -22760.02 -12142.09 -115146.8 -1153657
## 236 237 256 265 267 268
## Predicted 208345.78 1342867.5 116229.5 200006.73 1282451.9 283916.18
## cvpred 207931.36 1377288.8 103507.6 195850.26 1320843.9 288842.89
## price_sold 122000.00 1800000.0 178500.0 230000.00 651900.0 319000.00
## CV residual -85931.36 422711.2 74992.4 34149.74 -668943.9 30157.11
## 281 282 290 304 313 352
## Predicted 1445261.0 516082.4 875530.8 288419.89 416756.21 487972.8
## cvpred 1535842.1 521431.0 886830.2 292854.32 418224.99 496928.6
## price_sold 837500.0 407975.0 620000.0 335000.00 385000.00 873500.0
## CV residual -698342.1 -113456.0 -266830.2 42145.68 -33224.99 376571.4
## 355 357 365 373 382 389
## Predicted 612736.4 404462.3 379751.8 217109.85 414893.0 152426.2
## cvpred 629859.8 403698.6 394748.9 219023.06 413911.8 144477.8
## price_sold 512900.0 256000.0 236000.0 238000.00 545000.0 280000.0
## CV residual -116959.8 -147698.6 -158748.9 18976.94 131088.2 135522.2
## 396 403 429 454 463 465
## Predicted 200631.575 438173.6 974146.5 1015954.8 321565.5 561469.47
## cvpred 198698.712 440289.4 994238.7 1032672.3 325625.9 576777.02
## price_sold 200000.000 255000.0 690000.0 565000.0 215000.0 522375.00
## CV residual 1301.288 -185289.4 -304238.7 -467672.3 -110625.9 -54402.02
## 468 474 475 486 511 515
## Predicted 747829.6 1261296.2 299400.57 208127.94 561631.8 716602.9
## cvpred 781101.3 1263378.5 296931.73 204817.14 575179.7 719535.3
## price_sold 669000.0 1550000.0 325000.00 187500.00 431000.0 1500100.0
## CV residual -112101.3 286621.5 28068.27 -17317.14 -144179.7 780564.7
## 518 519 534 542 543 546
## Predicted 645489.5 638652.8 350259.0 572787.2 669385.4 224787.94
## cvpred 646901.5 661171.9 346786.6 561855.9 681363.8 219399.51
## price_sold 415000.0 482725.0 324900.0 398000.0 420000.0 128000.00
## CV residual -231901.5 -178446.9 -21886.6 -163855.9 -261363.8 -91399.51
## 554 563 568 573 577 585
## Predicted 448164.44 454805.86 170944.22 411051.26 382544.6 804199.4
## cvpred 452020.27 458457.08 157188.23 408508.63 380966.1 808037.6
## price_sold 440000.00 407500.00 225000.00 465000.00 279900.0 655000.0
## CV residual -12020.27 -50957.08 67811.77 56491.37 -101066.1 -153037.6
## 606 607 623 625 631 674
## Predicted 259144.7 335996.31 208976.482 339762.6 541847.3 299637.55
## cvpred 261216.1 330515.75 207484.011 341336.3 554074.7 289254.81
## price_sold 425000.0 282000.00 200000.000 185000.0 360000.0 302000.00
## CV residual 163783.9 -48515.75 -7484.011 -156336.3 -194074.7 12745.19
## 696 702 703 731 735 742
## Predicted 400229.9 -19436.64 103786.47 334844.1 249056.49 211150.8
## cvpred 401173.6 -26886.63 107804.57 342813.4 248031.71 205978.2
## price_sold 365000.0 184000.00 140000.00 220000.0 262000.00 97000.0
## CV residual -36173.6 210886.63 32195.43 -122813.4 13968.29 -108978.2
## 745 761 767 781 791 821
## Predicted 295190.10 351364.5 819183.7 410519.1 237752.3 451378.0
## cvpred 295076.23 337732.9 837629.9 410000.1 236921.0 452774.2
## price_sold 196250.00 200000.0 1025000.0 266000.0 510000.0 310000.0
## CV residual -98826.23 -137732.9 187370.1 -144000.1 273079.0 -142774.2
## 828 834 843 854 857 867
## Predicted 826887.7 1032094.12 517300.9 247847.6 246599.26 159392.28
## cvpred 847835.1 1044352.33 508234.3 244604.2 244699.53 150413.05
## price_sold 599950.0 950000.00 617000.0 450000.0 230000.00 220000.00
## CV residual -247885.1 -94352.33 108765.7 205395.8 -14699.53 69586.95
## 870 879 931 962 964 978 983
## Predicted 648415.7 1498121 258729.94 189854.2 260158.51 84736.38 177963.73
## cvpred 645218.2 1609109 257810.13 202258.5 256340.96 82790.72 170030.25
## price_sold 1200000.0 530000 290000.00 310000.0 192000.00 180000.00 120000.00
## CV residual 554781.8 -1079109 32189.87 107741.5 -64340.96 97209.28 -50030.25
## 984 1026 1034 1044 1051 1066
## Predicted 129836.38 146465.55 342972.7 314418.26 224876.06 364709.64
## cvpred 112370.34 150235.99 330897.1 328656.46 221365.49 360221.64
## price_sold 202000.00 135000.00 450000.0 385000.00 205000.00 319900.00
## CV residual 89629.66 -15235.99 119102.9 56343.54 -16365.49 -40321.64
## 1080 1084 1091 1096 1105 1107 1130
## Predicted 225007.34 351425.0 380147.4 373440.5 232485.7 393354.8 123741.1
## cvpred 214192.63 360303.3 365705.3 364383.2 227680.8 385730.5 125496.6
## price_sold 155000.00 130500.0 570000.0 565000.0 415000.0 75000.0 335000.0
## CV residual -59192.63 -229803.3 204294.7 200616.8 187319.2 -310730.5 209503.4
## 1133 1135 1148 1160 1162 1170
## Predicted 45548.43 57317.01 175994.50 182842.9 115145.12 363680.58
## cvpred 41511.65 49334.76 185874.85 173058.7 118406.23 357165.48
## price_sold 260000.00 180000.00 120000.00 370000.0 189900.00 400000.00
## CV residual 218488.35 130665.24 -65874.85 196941.3 71493.77 42834.52
## 1177 1180 1181 1187 1190 1191 1196
## Predicted 349070.80 122138.61 152833.7 221382.5 104843.4 157499.0 349708.852
## cvpred 345259.39 121217.18 159092.3 219193.8 110641.4 146584.5 358662.191
## price_sold 253000.00 96000.00 55000.0 339000.0 285000.0 320000.0 366000.000
## CV residual -92259.39 -25217.18 -104092.3 119806.2 174358.6 173415.5 7337.809
## 1207 1210 1218 1223 1232 1235
## Predicted 134484.26 338298.03 133510.84 514913.56 303945.23 255456.2
## cvpred 134986.02 313488.13 140954.59 517713.41 288605.36 253125.3
## price_sold 152500.00 225000.00 130000.00 560000.00 350000.00 76000.0
## CV residual 17513.98 -88488.13 -10954.59 42286.59 61394.64 -177125.3
## 1269 1276 1290 1297 1304 1307
## Predicted 97007.98 349167.13 323189.4 216145.82 229628.1 423543.7
## cvpred 99033.07 348759.11 322340.5 202948.45 241997.5 435968.2
## price_sold 27886.00 290000.00 170000.0 182000.00 45000.0 235000.0
## CV residual -71147.07 -58759.11 -152340.5 -20948.45 -196997.5 -200968.2
## 1335 1348 1351 1367 1370 1375
## Predicted 269388.69 494226.2 252644.24 262585.85 -49159.51 227713.98
## cvpred 252306.98 496053.9 250317.81 271435.99 -61711.75 225628.07
## price_sold 186500.00 899900.0 214000.00 189000.00 150000.00 245900.00
## CV residual -65806.98 403846.1 -36317.81 -82435.99 211711.75 20271.93
## 1381
## Predicted 150152.61
## cvpred 138184.87
## price_sold 175000.00
## CV residual 36815.13
##
## Sum of squares = 8.855491e+12 Mean square = 63708566545 n = 139
##
## fold 8
## Observations in test set: 139
## 1 10 13 25 35 63 64
## Predicted 343539.1 209988.82 715147.2 155121.4 1040419 698061.8 364229.7
## cvpred 340898.8 213341.71 725390.9 149323.8 1041129 709258.5 344937.9
## price_sold 214300.0 187000.00 1050000.0 309000.0 2275000 535000.0 180000.0
## CV residual -126598.8 -26341.71 324609.1 159676.2 1233871 -174258.5 -164937.9
## 68 76 85 94 95 104 112
## Predicted 760112.6 360985.3 428286.7 700982.12 676020.35 396968.9 916362.6
## cvpred 767212.3 372527.9 385200.4 685585.75 652459.95 364246.6 923619.2
## price_sold 470000.0 500000.0 625000.0 670000.00 705500.00 505000.0 667000.0
## CV residual -297212.3 127472.1 239799.6 -15585.75 53040.05 140753.4 -256619.2
## 118 122 135 146 159 163 166
## Predicted 280536.0 584266.3 316800.4 390149.1 2614746.2 668891.1 655826.1
## cvpred 280653.6 587405.7 318404.7 389190.7 2684404.1 672086.7 669497.9
## price_sold 122000.0 254900.0 490000.0 51314.0 2000000.0 853000.0 425000.0
## CV residual -158653.6 -332505.7 171595.3 -337876.7 -684404.1 180913.3 -244497.9
## 178 200 209 211 220 223 230
## Predicted 225580.9 371483.13 510024.1 248135.9 271055.27 494696.5 1022344.3
## cvpred 221154.1 375821.34 512297.4 242078.4 270990.24 501221.8 1035617.9
## price_sold 353000.0 350000.00 398000.0 515000.0 244900.00 276000.0 740000.0
## CV residual 131845.9 -25821.34 -114297.4 272921.6 -26090.24 -225221.8 -295617.9
## 246 247 261 274 277 284
## Predicted 612440.47 547332.8 1137255.8 212670.77 487437.6 443361.3
## cvpred 616807.72 552655.2 1156978.8 223520.18 481673.0 434005.6
## price_sold 550000.00 837679.0 759000.0 265000.00 315700.0 285000.0
## CV residual -66807.72 285023.8 -397978.8 41479.82 -165973.0 -149005.6
## 299 306 319 324 344 347
## Predicted 91702.54 507861.76 453075.8 342542.63 43579.02 218116.63
## cvpred 85817.75 507940.98 453938.4 335956.08 37376.69 213916.57
## price_sold 476000.00 484000.00 255000.0 305500.00 202500.00 225000.00
## CV residual 390182.25 -23940.98 -198938.4 -30456.08 165123.31 11083.43
## 349 353 362 370 399 405
## Predicted 396473.99 489821.1 699519.4 456785.1 451794.760 341007.5
## cvpred 393749.08 494797.5 711919.6 457218.4 455876.193 336084.8
## price_sold 430000.00 873500.0 380000.0 265000.0 449900.000 364000.0
## CV residual 36250.92 378702.5 -331919.6 -192218.4 -5976.193 27915.2
## 412 421 424 466 482 497
## Predicted 2159366.5 605600.29 747434.4 894768.0 603262.67 613765.35
## cvpred 2216780.1 617398.65 768038.8 910101.9 607505.94 617676.24
## price_sold 2700000.0 524900.00 500000.0 530000.0 520000.00 633000.00
## CV residual 483219.9 -92498.65 -268038.8 -380101.9 -87505.94 15323.76
## 508 517 524 530 531 564
## Predicted 546724.5 382765.4849 465873.821 749623.5 248317.74 312304.16
## cvpred 551349.2 379922.3287 462826.773 758231.3 250104.39 296423.89
## price_sold 685000.0 380000.0000 455000.000 450000.0 200000.00 340000.00
## CV residual 133650.8 77.6713 -7826.773 -308231.3 -50104.39 43576.11
## 572 584 592 599 602 603
## Predicted 201510.81 442697.5 608111.6 511652.3 32170.72 31965.16
## cvpred 202271.72 440496.7 610938.4 522175.3 24746.60 24528.28
## price_sold 225000.00 629900.0 1285000.0 290000.0 110000.00 111000.00
## CV residual 22728.28 189403.3 674061.6 -232175.3 85253.40 86471.72
## 604 629 646 657 668 676 685
## Predicted 310580.78 162016.92 139482.5 425321.61 234081.7 311310.49 411028.7
## cvpred 315621.57 152794.71 132127.7 421529.06 233420.0 305056.87 404589.5
## price_sold 252000.00 229600.00 245900.0 383000.00 215000.0 280000.00 649900.0
## CV residual -63621.57 76805.29 113772.3 -38529.06 -18420.0 -25056.87 245310.5
## 691 720 739 750 760 771
## Predicted 137397.25 213839.54 546512.8 452854.9 198797.00 156877.53
## cvpred 149108.62 208535.94 554715.8 472019.6 199096.18 146089.87
## price_sold 248000.00 225000.00 255000.0 255000.0 292000.00 230000.00
## CV residual 98891.38 16464.06 -299715.8 -217019.6 92903.82 83910.13
## 782 788 798 813 820 835 837
## Predicted 503464.3 568422.96 544255.0 184511.49 562531.5 228584.3 1435363
## cvpred 496495.4 572227.54 542897.3 185121.67 567990.9 228680.7 1519047
## price_sold 282500.0 490000.00 314500.0 249900.00 133000.0 500000.0 215000
## CV residual -213995.4 -82227.54 -228397.3 64778.33 -434990.9 271319.3 -1304047
## 838 851 860 863 884 887 894
## Predicted 309138.48 378434.1 327506.5 170976.2 186921.07 62842.31 329225.81
## cvpred 309563.55 382531.9 316792.8 159011.6 179286.48 70364.52 325037.34
## price_sold 215000.00 276000.0 459900.0 360000.0 202000.00 207500.00 275000.00
## CV residual -94563.55 -106531.9 143107.2 200988.4 22713.52 137135.48 -50037.34
## 907 911 919 939 943 947 970
## Predicted 362496.2 129160.1 476293.4 197130.69 74457.96 99709.46 40678.24
## cvpred 366087.4 125208.9 488958.8 193281.75 76384.36 102250.80 32683.12
## price_sold 495000.0 176500.0 350000.0 256000.00 108000.00 160500.00 234900.00
## CV residual 128912.6 51291.1 -138958.8 62718.25 31615.64 58249.20 202216.88
## 976 982 989 993 997 1007
## Predicted 288930.922 501857.75 176623.6 141913.79 35697.59 389752.4
## cvpred 292627.355 509120.62 172101.1 130360.17 26073.75 385877.1
## price_sold 295000.000 560000.00 333000.0 230000.00 260000.00 260000.0
## CV residual 2372.645 50879.38 160898.9 99639.83 233926.25 -125877.1
## 1041 1045 1067 1087 1103 1108
## Predicted 394603.948 282112.4 437038.7 394600.38 90373.86 184784.32
## cvpred 394341.484 293388.1 441243.2 387392.47 97333.21 189309.62
## price_sold 385000.000 182850.0 565000.0 317000.00 253000.00 149000.00
## CV residual -9341.484 -110538.1 123756.8 -70392.47 155666.79 -40309.62
## 1109 1110 1126 1138 1182 1183
## Predicted 22386.40 231330.91 39626.19 523615.68 324890.79 182174.07
## cvpred 17708.15 225328.94 28487.27 522822.22 334687.93 186205.17
## price_sold 168000.00 147400.00 180000.00 485000.00 270000.00 227000.00
## CV residual 150291.85 -77928.94 151512.73 -37822.22 -64687.93 40794.83
## 1194 1217 1227 1234 1238 1244 1251
## Predicted 72993.01 314120.7 74365.45 122721.5 219351.5 277923.8 273795.9
## cvpred 70284.02 310603.5 76359.36 129783.4 215624.4 277491.9 268508.2
## price_sold 90000.00 415000.0 180000.00 250000.0 339000.0 165000.0 450000.0
## CV residual 19715.98 104396.5 103640.64 120216.6 123375.6 -112491.9 181491.8
## 1294 1301 1309 1322 1328 1331 1332
## Predicted 251724.21 249455.49 262309.5 187067.6 1092632.9 360273.0 308074.9
## cvpred 245506.07 255258.69 256015.6 176981.4 1100544.4 359914.7 306143.4
## price_sold 200000.00 242394.00 280000.0 367700.0 665000.0 516116.0 160000.0
## CV residual -45506.07 -12864.69 23984.4 190718.6 -435544.4 156201.3 -146143.4
## 1333 1338 1341 1346 1349 1358
## Predicted 252644.25 270576.93 171856.5 229517.47 208344.21 338644.34
## cvpred 246189.89 278997.37 164839.2 231957.58 212534.31 337424.47
## price_sold 214000.00 227000.00 10000.0 300749.00 122000.00 425000.00
## CV residual -32189.89 -51997.37 -154839.2 68791.42 -90534.31 87575.53
## 1359 1361 1368
## Predicted 547723.3 324302.164 270576.9
## cvpred 549436.1 325478.448 278997.3
## price_sold 285000.0 335000.000 100000.0
## CV residual -264436.1 9521.552 -178997.3
##
## Sum of squares = 8.274839e+12 Mean square = 59531216654 n = 139
##
## fold 9
## Observations in test set: 139
## 16 37 39 50 71 79 92
## Predicted 143521.02 666946 1040419 323666.83 348467.58 371593.2 1185797.8
## cvpred 134224.36 663668 1031312 324749.34 342546.96 369487.8 1184294.6
## price_sold 90000.00 1650000 2275000 250000.00 392875.00 685000.0 700000.0
## CV residual -44224.36 986332 1243688 -74749.34 50328.04 315512.2 -484294.6
## 93 98 110 111 119 127
## Predicted 313331.0 159457.5 382764.6 238846.087 214752.28 502639.4
## cvpred 307857.9 147209.0 376980.0 234015.343 209178.19 503511.2
## price_sold 530000.0 445000.0 221500.0 225000.000 188500.00 362500.0
## CV residual 222142.1 297791.0 -155480.0 -9015.343 -20678.19 -141011.2
## 130 133 140 155 161 171
## Predicted 343487.9 565245.8 253087.63 332990.7 1143680.2 667618.8
## cvpred 341599.1 565984.7 239844.29 323525.8 1146083.5 663701.7
## price_sold 223000.0 84123.0 290000.00 500000.0 975000.0 430000.0
## CV residual -118599.1 -481861.7 50155.71 176474.2 -171083.5 -233701.7
## 186 187 226 231 234 286
## Predicted 829770.6 277290.42 259546.34 62579.27 396351.9 223469.92
## cvpred 829600.1 272097.91 253965.82 58200.16 393476.9 221501.11
## price_sold 1100000.0 241000.00 350000.00 40000.00 287400.0 244800.00
## CV residual 270399.9 -31097.91 96034.18 -18200.16 -106076.9 23298.89
## 287 293 297 308 316 329
## Predicted 233437.08 943473.6 883310.0 573973.4 360895.4 333528.31
## cvpred 228244.35 943240.1 883182.8 571004.5 358968.2 330995.35
## price_sold 140000.00 1900000.0 1400000.0 710000.0 255500.0 307200.00
## CV residual -88244.35 956759.9 516817.2 138995.5 -103468.2 -23795.35
## 331 364 374 379 385 388 398
## Predicted 608471.78 190163.44 104544.2 118779.8 169191.3 564523.51 1452637.9
## cvpred 616082.44 188382.32 103944.0 114186.3 156168.6 568273.43 1454416.8
## price_sold 630000.00 159000.00 275000.0 266900.0 320000.0 550000.00 1324000.0
## CV residual 13917.56 -29382.32 171056.0 152713.7 163831.4 -18273.43 -130416.8
## 407 417 420 436 437 448
## Predicted 288594.0 1466505.4 693066.0 600166.73 809300.8 945354.0
## cvpred 279232.4 1467507.9 693243.6 600160.84 808974.6 945970.2
## price_sold 225000.0 999000.0 1200000.0 675000.00 560000.0 700000.0
## CV residual -54232.4 -468507.9 506756.4 74839.16 -248974.6 -245970.2
## 451 471 472 481 484 495
## Predicted 82948.79 412425.56 315200.989 214805.695 736207.5 528880.5
## cvpred 75504.87 409508.97 313575.141 201632.558 732891.2 529104.9
## price_sold 55000.00 320000.00 311500.000 199000.000 520000.0 769100.0
## CV residual -20504.87 -89508.97 -2075.141 -2632.558 -212891.2 239995.1
## 501 522 533 544 552 561
## Predicted 279721.171 122637.04 404305.7 458374.3 402840.07 274818.9
## cvpred 274943.488 115195.91 401604.1 455589.4 399907.33 269342.4
## price_sold 280000.000 175000.00 168000.0 211973.0 347000.00 454500.0
## CV residual 5056.512 59804.09 -233604.1 -243616.4 -52907.33 185157.6
## 565 571 581 595 596 610
## Predicted 422095.56 195207.09 723045.9 568787.21 464259.9 427695.3
## cvpred 419618.77 190508.09 724198.2 566142.56 464600.0 422872.0
## price_sold 482500.00 225000.00 1050000.0 532000.00 717000.0 270000.0
## CV residual 62881.23 34491.91 325801.8 -34142.56 252400.0 -152872.0
## 619 628 641 665 669 701
## Predicted 253661.71 162016.92 106689.592 406598.707 507298.1 -5581.092
## cvpred 251860.55 157324.29 102290.759 403829.523 500834.6 -14006.842
## price_sold 229000.00 229600.00 95500.000 405000.000 390000.0 175000.000
## CV residual -22860.55 72275.71 -6790.759 1170.477 -110834.6 189006.842
## 705 710 734 737 751 772
## Predicted 195233.55 287992.98 215350.12 240903.08 199321.257 156877.53
## cvpred 190381.53 289282.81 209828.68 235218.41 197677.311 152423.35
## price_sold 219900.00 255000.00 144500.00 223500.00 199000.000 230000.00
## CV residual 29518.47 -34282.81 -65328.68 -11718.41 1322.689 77576.65
## 777 778 789 795 797 799
## Predicted 205673.26 191470.90 299550.1 310987.7 397609.7 454061.8
## cvpred 207930.57 186885.24 304660.6 309317.9 398733.3 452287.9
## price_sold 230700.00 227500.00 172950.0 565100.0 267000.0 300000.0
## CV residual 22769.43 40614.76 -131710.6 255782.1 -131733.3 -152287.9
## 804 815 818 836 846 855 865
## Predicted 155465.99 338588.4 221665.4 759081.3 388904.94 301339.6 42615.19
## cvpred 153866.01 339944.2 215867.7 753052.7 386766.44 288347.8 34317.41
## price_sold 127000.00 190000.0 404325.0 300000.0 360000.00 589000.0 205000.00
## CV residual -26866.01 -149944.2 188457.3 -453052.7 -26766.44 300652.2 170682.59
## 876 880 882 886 896 917
## Predicted 46683.61 412897.95 343225.0 48639.94 112858.48 206823.16
## cvpred 42399.25 414104.47 340570.6 41099.72 107534.07 205218.73
## price_sold 120000.00 430000.00 445000.0 207500.00 175000.00 189000.00
## CV residual 77600.75 15895.53 104429.4 166400.28 67465.93 -16218.73
## 920 932 936 945 951 957 966
## Predicted 242184.19 219937.3 36755.10 163291.20 37186.94 120950.89 257192.3
## cvpred 229053.62 218335.1 32282.24 158808.58 32703.58 120304.59 255664.1
## price_sold 207000.00 382000.0 175000.00 180000.00 191600.00 179900.00 512500.0
## CV residual -22053.62 163664.9 142717.76 21191.42 158896.42 59595.41 256835.9
## 968 971 975 979 990 995 1008
## Predicted 85595.5 232155.825 388904.91 362823.9 238077.2 281378.33 389752.4
## cvpred 77329.3 230641.376 386766.41 360003.6 236475.5 276754.23 387050.5
## price_sold 200000.0 227000.000 360000.00 510000.0 500000.0 250000.00 260000.0
## CV residual 122670.7 -3641.376 -26766.41 149996.4 263524.5 -26754.23 -127050.5
## 1019 1021 1022 1031 1046 1086
## Predicted 307357.9 110345.687 145572.13 432937.1 267910.02 273264.78
## cvpred 302548.1 105906.461 144956.49 434265.5 263242.37 278103.05
## price_sold 164000.0 115700.000 91000.00 560000.0 182850.00 215000.00
## CV residual -138548.1 9793.539 -53956.49 125734.5 -80392.37 -63103.05
## 1093 1121 1137 1139 1151 1165 1198
## Predicted 59733.78 415159.7 17521.97 458853.3 198324.10 689562.2 243032.41
## cvpred 55580.67 412209.6 10019.28 456281.0 193843.29 689291.7 241160.43
## price_sold 88000.00 280000.0 213000.00 160000.0 180000.00 843475.0 170000.00
## CV residual 32419.33 -132209.6 202980.72 -296281.0 -13843.29 154183.3 -71160.43
## 1211 1222 1224 1230 1239 1257 1263
## Predicted 142555.51 402733.81 78260.32 134250.3 205149.2 474196.1 168573.64
## cvpred 141052.18 399795.46 66493.60 132797.8 203743.2 472505.6 167937.04
## price_sold 111500.00 480000.00 131000.00 165000.0 339000.0 190000.0 157000.00
## CV residual -29552.18 80204.54 64506.40 32202.2 135256.8 -282505.6 -10937.04
## 1265 1277 1282 1284 1289 1299
## Predicted 280241.0 497833.8 168437.53 338091.6 652215.79 -3739.199
## cvpred 277556.3 500110.6 164015.31 336581.6 655920.83 -11030.635
## price_sold 416000.0 313000.0 209900.00 85000.0 560200.00 45000.000
## CV residual 138443.7 -187110.6 45884.69 -251581.6 -95720.83 56030.635
## 1312 1356 1360 1373 1378 1388
## Predicted 213007.46 338644.34 308562.2 224828.8 117244.56 145712.73
## cvpred 208710.26 333264.13 305903.2 219826.4 112922.88 144275.33
## price_sold 220000.00 425000.00 190000.0 353000.0 50000.00 215000.00
## CV residual 11289.74 91735.87 -115903.2 133173.6 -62922.88 70724.67
##
## Sum of squares = 7.306499e+12 Mean square = 52564743314 n = 139
##
## fold 10
## Observations in test set: 138
## 2 3 6 14 15 30 40
## Predicted 342873.736 38219.96 546869.4 131298.67 131298.67 38219.96 214681.9
## cvpred 338486.227 35970.86 545470.2 130580.96 130580.96 35970.86 214633.5
## price_sold 339900.000 90000.00 170000.0 179000.00 200000.00 90000.00 595000.0
## CV residual 1413.773 54029.14 -375470.2 48419.04 69419.04 54029.14 380366.5
## 46 49 66 67 72 97 101
## Predicted 276104.71 164936.9 161880.8 390541.0 391086.4 721477.4 98100.49
## cvpred 273676.87 164882.1 2413027.7 412566.7 406262.6 721826.9 94870.26
## price_sold 235000.00 130000.0 160000.0 289000.0 520000.0 675000.0 315000.00
## CV residual -38676.87 -34882.1 -2253027.7 -123566.7 113737.4 -46826.9 220129.74
## 114 124 125 131 134 145 149
## Predicted 212955.3 833006.92 388411.5 371221.386 758761 882654.5 277034.6
## cvpred 213408.2 834936.53 392228.9 373840.227 762197 889078.4 275937.0
## price_sold 54474.0 849000.00 629000.0 382750.000 110000 680000.0 140000.0
## CV residual -158934.2 14063.47 236771.1 8909.773 -652197 -209078.4 -135937.0
## 152 172 181 198 204 229 239
## Predicted 174690.5 1880205 420940.4 175084.2 527445.4 1271916.4 419713.59
## cvpred 170164.4 1874100 422766.9 175124.4 533751.4 1271301.2 421773.38
## price_sold 335000.0 3600000 445000.0 285000.0 780000.0 700000.0 358000.00
## CV residual 164835.6 1725900 22233.1 109875.6 246248.6 -571301.2 -63773.38
## 258 269 278 296 303 309
## Predicted 371758.0 173994.286 1203949.90 883310.0 547496.0 573973.4
## cvpred 374124.3 173548.367 1208379.86 881782.2 552184.6 573024.6
## price_sold 90201.0 165000.000 1237500.00 1400000.0 675000.0 710000.0
## CV residual -283923.3 -8548.367 29120.14 518217.8 122815.4 136975.4
## 332 356 359 360 375 390
## Predicted 531256.2 937486.5 522776.0 501820.7 533987.4 209622.87
## cvpred 530389.7 941629.2 522415.1 507079.8 532979.8 209633.28
## price_sold 365000.0 1128000.0 314500.0 712000.0 322000.0 244554.00
## CV residual -165389.7 186370.8 -207915.1 204920.2 -210979.8 34920.72
## 395 402 415 435 442 449
## Predicted 274966.48 551340.82 140706.8 210248.21 738928.7 275208.5
## cvpred 272450.04 556298.76 133728.0 214137.02 740953.9 272875.4
## price_sold 208000.00 480000.00 292000.0 235000.00 499000.0 170000.0
## CV residual -64450.04 -76298.76 158272.0 20862.98 -241953.9 -102875.4
## 462 469 476 487 496 506
## Predicted 276977.30 546869.6 935498.37 777963.2 541794.6 546724.5
## cvpred 274915.69 545485.7 932596.06 780591.3 545288.6 545628.3
## price_sold 287500.00 170000.0 980000.00 525000.0 375000.0 685000.0
## CV residual 12584.31 -375485.7 47403.94 -255591.3 -170288.6 139371.7
## 513 536 540 541 553 569 597
## Predicted 441930.1 79009.81 152138.1 340486.7 869879.4 300206.5 464259.9
## cvpred 436985.7 74639.43 151328.4 342456.9 870194.0 296690.4 469317.2
## price_sold 279000.0 110111.00 265000.0 485000.0 410000.0 173000.0 717000.0
## CV residual -157985.7 35471.57 113671.6 142543.1 -460194.0 -123690.4 247682.8
## 615 621 656 664 678 681 682
## Predicted 34237.58 424311.2 225415.28 194777.2 439742.5 251758.97 74365.63
## cvpred 30662.56 426763.8 224595.12 195250.8 440276.7 249619.21 69768.79
## price_sold 154000.00 308500.0 190000.00 315000.0 700000.0 220000.00 173000.00
## CV residual 123337.44 -118263.8 -34595.12 119749.2 259723.3 -29619.21 103231.21
## 687 688 689 692 721 724
## Predicted 209388.15 199936.22 281099.79 40894.2 308997.23 90484.29
## cvpred 208457.34 198027.97 279994.39 37021.6 311227.69 85736.88
## price_sold 235000.00 240000.00 343000.00 120000.0 395000.00 232500.00
## CV residual 26542.66 41972.03 63005.61 82978.4 83772.31 146763.12
## 730 740 773 776 802 806
## Predicted 810881.0 469806.5 514471.0 1540382.0 173326.45 253317.3
## cvpred 811077.1 470260.0 513398.5 1535380.7 173087.62 251545.1
## price_sold 468000.0 275000.0 329900.0 980000.0 223000.00 550000.0
## CV residual -343077.1 -195260.0 -183498.5 -555380.7 49912.38 298454.9
## 816 819 826 833 840 841
## Predicted 1052765.8 251609.23 576457.79 166852.77 494230.6 697046.7
## cvpred 1054674.3 249969.25 575580.55 165714.93 493243.7 697588.6
## price_sold 460000.0 224000.00 637000.00 197500.00 73000.0 385000.0
## CV residual -594674.3 -25969.25 61419.45 31785.07 -420243.7 -312588.6
## 853 859 877 881 895 898 901
## Predicted 298265.3 241869.71 347616.70 396493.5 310667.60 284967.3 238045.3
## cvpred 300928.8 239324.09 348059.42 391234.0 314420.75 281740.0 235256.8
## price_sold 265000.0 259000.00 365000.00 120000.0 285000.00 565000.0 511000.0
## CV residual -35928.8 19675.91 16940.58 -271234.0 -29420.75 283260.0 275743.2
## 909 918 937 950 952 959
## Predicted 319130.73 206823.16 177546.61 280656.89 307827.17 172608.3
## cvpred 321204.11 205055.99 170480.55 277863.56 311327.77 171382.0
## price_sold 235000.00 189000.00 214300.00 265000.00 260000.00 360000.0
## CV residual -86204.11 -16055.99 43819.45 -12863.56 -51327.77 188618.0
## 969 974 998 999 1002 1015
## Predicted 176373.72 409159.44 380187.18 165236.17 158020.95 405990.2
## cvpred 175366.54 411249.38 382989.08 164050.83 156894.47 405679.4
## price_sold 200000.00 380000.00 357000.00 134900.00 90500.00 260000.0
## CV residual 24633.46 -31249.38 -25989.08 -29150.83 -66394.47 -145679.4
## 1029 1030 1049 1075 1076 1077 1090
## Predicted 268472.22 254269.9 144324.41 56923.42 482318.8 452141.5 355365.9
## cvpred 264369.78 251553.5 143723.01 52406.11 481631.8 451910.1 356294.5
## price_sold 222000.00 222000.0 71050.00 180000.00 700000.0 700000.0 690000.0
## CV residual -42369.78 -29553.5 -72673.01 127593.89 218368.2 248089.9 333705.5
## 1094 1102 1104 1115 1131 1143 1147
## Predicted 164242.2 789111.6 234758.1 761756.4 318850.26 235823.8 204252.8
## cvpred 158143.5 791531.5 232515.5 757295.0 320754.31 232663.0 202269.0
## price_sold 357000.0 1070000.0 141000.0 1150000.0 257000.00 495000.0 380000.0
## CV residual 198856.5 278468.5 -91515.5 392705.0 -63754.31 262337.0 177731.0
## 1152 1153 1155 1156 1161 1163
## Predicted 212526.46 198324.1 591656.5 246644.96 210454.24 89909.46
## cvpred 209046.17 196229.9 589161.0 245854.58 207349.26 84736.18
## price_sold 180000.00 180000.0 390000.0 300000.00 284000.00 320000.00
## CV residual -29046.17 -16229.9 -199161.0 54145.42 76650.74 235263.82
## 1167 1202 1216 1219 1231 1245 1260
## Predicted 406196.39 75267.11 328323 174646.74 345124.7 193690.8 443330.839
## cvpred 395249.16 69843.48 322017 172212.49 346316.8 186422.5 443631.327
## price_sold 350000.00 277000.00 13233 230000.00 152000.0 370000.0 435000.000
## CV residual -45249.16 207156.52 -308784 57787.51 -194316.8 183577.5 -8631.327
## 1272 1295 1305 1316 1326 1342
## Predicted 202127.4 265926.58 150443.48 210512.93 126181.652 157388.6
## cvpred 198625.4 262048.53 148629.11 209510.15 118087.997 155474.2
## price_sold 10000.0 200000.00 195000.00 150000.00 120000.000 307000.0
## CV residual -188625.4 -62048.53 46370.89 -59510.15 1912.003 151525.8
## 1352 1362
## Predicted 266846.61 310099.80
## cvpred 262308.33 310344.18
## price_sold 214000.00 335500.00
## CV residual -48308.33 25155.82
##
## Sum of squares = 1.343972e+13 Mean square = 97389257205 n = 138
##
## Overall (Sum over all 138 folds)
## ms
## 94926487556
# MSPE
n1 = dim(housing)[1]
MSPE1 <- sum((housing$price_sold - KCV1$cvpred)^2) / n1
MSPE1
## [1] 94926487556
# Press Statistic
PRESS1 <- sum((housing$price_sold - KCV1$cvpred)^2)
PRESS1
## [1] 1.31758e+14
# Prediction R-Squared
PRS1 <- 1 - sum((housing$price_sold - KCV1$cvpred)^2) / sum((housing$price_sold -
mean(housing$price_sold))^2)
PRS1
## [1] 0.5105264
Model 2:
# K-fold
KCV2 = cv.lm(data = clean_housing, housing_model2, m = 10, seed = 0)
##
## fold 1
## Observations in test set: 136
## 4 7 12 34 42 55
## Predicted 198296.53 561968.7 364795.28 339111.1 246704.845 267081.5
## cvpred 191947.99 566880.3 362780.85 332101.4 241407.522 259558.0
## price_sold 178000.00 275000.0 399000.00 1050000.0 235000.000 417000.0
## CV residual -13947.99 -291880.3 36219.15 717898.6 -6407.522 157442.0
## 62 74 80 115 122 136
## Predicted 463427.5 327096.0 516405.6 544993.9 256541.9 385644.42
## cvpred 454315.0 320445.4 507848.6 549607.7 250031.1 382984.59
## price_sold 289000.0 685000.0 625000.0 254900.0 92500.0 291500.00
## CV residual -165315.0 364554.6 117151.4 -294707.7 -157531.1 -91484.59
## 151 177 182 187 195 214
## Predicted 2040401.21 566454.284 311224.0 530573.04 472864.39 866139.2
## cvpred 2079642.98 571558.115 309219.8 532236.26 477120.59 875751.6
## price_sold 2000000.00 566000.000 440000.0 570000.00 398000.00 740000.0
## CV residual -79642.98 -5558.115 130780.2 37763.74 -79120.59 -135751.6
## 216 261 268 279 281 290 296
## Predicted 520189.30 1002428.6 222021.22 758534.9 128188.8 510493.1 1488848.3
## cvpred 523205.37 1018821.1 215758.98 772822.2 121156.7 514281.3 1521618.8
## price_sold 572500.00 1237500.0 244800.00 1400000.0 476000.0 710000.0 1025000.0
## CV residual 49294.63 218678.9 29041.02 627177.8 354843.3 195718.7 -496618.8
## 301 303 304 313 323 337
## Predicted 432733.5 428137.0 1162115.9 467290.2 198211.18 400538.0
## cvpred 434527.2 407181.5 1188763.5 468869.6 193419.53 401103.2
## price_sold 255000.0 605000.0 518535.0 365000.0 235000.00 256000.0
## CV residual -179527.2 197818.5 -670228.5 -103869.6 41580.47 -145103.2
## 344 348 350 360 371 380
## Predicted 189874.23 656896.83 436192.2 452320.1 761990.1 341834.13
## cvpred 182384.26 664551.12 438569.4 455085.4 769729.2 338862.16
## price_sold 159000.00 590000.00 265000.0 300000.0 525000.0 308000.00
## CV residual -23384.26 -74551.12 -173569.4 -155085.4 -244729.2 -30862.16
## 387 389 390 394 398 406 417
## Predicted 298766.12 412244.8 693537.0 135520.9 407135.8 398207.9 689299.9
## cvpred 294589.12 412428.6 708309.7 128169.6 405535.9 398498.8 696541.3
## price_sold 225000.00 245000.0 999000.0 292000.0 180000.0 330000.0 560000.0
## CV residual -69589.12 -167428.6 290690.3 163830.4 -225535.9 -68498.8 -136541.3
## 419 445 450 459 465 468 476
## Predicted 534615.33 495786.0 88214.905 1077837 89959.40 334533.0 526391.3
## cvpred 536688.39 496263.9 79428.283 1093945 83029.13 332571.2 533525.0
## price_sold 587500.00 522375.0 81500.000 799900 150000.00 466400.0 375000.0
## CV residual 50811.61 26111.1 2071.717 -294045 66970.87 133828.8 -158525.0
## 485 510 512 527 532 542
## Predicted 333290.86 657131.6 563211.39 333036.48 396677.80 787663.4
## cvpred 331255.54 666326.2 569781.82 330851.15 395915.83 796190.3
## price_sold 265000.00 450000.0 489900.00 272000.00 347000.00 1058756.0
## CV residual -66255.54 -216326.2 -79881.82 -58851.15 -48915.83 262565.7
## 558 565 568 582 603 607
## Predicted 318518.75 708708.07 321707.48 73697.24 348131.52 228734.390
## cvpred 317450.66 725645.81 318594.58 64000.49 345634.18 228483.899
## price_sold 360000.00 655000.00 375000.00 110000.00 329000.00 229600.000
## CV residual 42549.34 -70645.81 56405.42 45999.51 -16634.18 1116.101
## 614 619 620 623 626 630
## Predicted 159557.22 434660.8 127801.89 275805.684 644833.1 424508.8
## cvpred 155984.37 439451.7 124092.86 276292.547 647690.9 424603.1
## price_sold 188000.00 225000.0 95500.00 270000.000 246000.0 270000.0
## CV residual 32015.63 -214451.7 -28592.86 -6292.547 -401690.9 -154603.1
## 637 642 652 668 674 676 680
## Predicted 420027.01 358460.9 556832.5 275084.81 456214.1 171644.67 75318.16
## cvpred 423835.61 359287.2 567422.2 269659.55 459400.3 166848.07 66979.88
## price_sold 383000.00 325000.0 310000.0 343000.00 577000.0 130000.00 175000.00
## CV residual -40835.61 -34287.2 -257422.2 73340.45 117599.7 -36848.07 108020.12
## 682 694 696 705 715 719
## Predicted 138758.275 407952.12 479886.23 473463.0 379420.9 444773.7
## cvpred 133311.482 404863.56 484840.08 483544.1 381138.5 447500.2
## price_sold 140000.000 324900.00 440000.00 815000.0 150000.0 275000.0
## CV residual 6688.518 -79963.56 -44840.08 331455.9 -231138.5 -172500.2
## 743 749 771 839 864 867 877
## Predicted 129385.5 202306.52 340453.14 88903.8 97293.89 181730.60 573076.36
## cvpred 122184.7 199747.66 339102.86 80360.3 89675.76 178225.92 582975.23
## price_sold 295000.0 230000.00 263000.00 60000.0 207500.00 267500.00 625000.00
## CV residual 172815.3 30252.34 -76102.86 -20360.3 117824.24 89274.08 42024.77
## 879 900 903 910 916 917 920
## Predicted 242576.2 343225.29 339241.99 228794.1 184837.4 220424.06 309262.83
## cvpred 241912.1 346110.78 340057.29 226824.4 182092.8 213308.39 308062.48
## price_sold 511000.0 299900.00 380000.00 382000.0 396300.0 256000.00 295000.00
## CV residual 269087.9 -46210.78 39942.71 155175.6 214207.2 42691.61 -13062.48
## 934 948 960 965 968 990 992
## Predicted 187429.51 106258.0 457830.8 443463.4 240953.2 348188.7 121549.46
## cvpred 183256.16 100814.9 457530.9 446078.9 239517.4 350863.3 110280.21
## price_sold 155000.00 234900.0 560000.0 232000.0 500000.0 210000.0 170000.00
## CV residual -28256.16 134085.1 102469.1 -214078.9 260482.6 -140863.3 59719.79
## 1008 1064 1070 1071 1074 1084
## Predicted 264716.41 271711.35 88047.709 88047.709 359547.0 66155.75
## cvpred 263667.28 269012.38 83407.001 83407.001 361802.3 58012.01
## price_sold 222000.00 215000.00 88000.000 88000.000 565000.0 155000.00
## CV residual -41667.28 -54012.38 4592.999 4592.999 203197.7 96987.99
## 1090 1092 1094 1124 1139 1140
## Predicted 272789.15 236552.57 292151.8 220617.54 211831.44 118105.07
## cvpred 272234.82 235765.16 292250.3 219473.86 212328.99 111752.76
## price_sold 221500.00 250000.00 454500.0 256000.00 284000.00 189900.00
## CV residual -50734.82 14234.84 162249.7 36526.14 71671.01 78147.24
## 1144 1145 1170 1179 1185 1191 1213
## Predicted 651593.6 338049.1 198383.9 351256.0 184698.21 269717.9 278225.2
## cvpred 659377.0 339878.5 196812.7 356611.1 185016.68 268330.8 278876.8
## price_sold 1240000.0 350000.0 325000.0 235000.0 152500.00 429000.0 76000.0
## CV residual 580623.0 10121.5 128187.3 -121611.1 -32516.68 160669.2 -202876.8
## 1219 1255 1271 1278 1282 1291
## Predicted 208382.61 388434.87 318992.2 256382.45 218628.7 213982.436
## cvpred 206560.07 394148.92 322129.0 256867.26 216344.7 215033.584
## price_sold 165000.00 313000.00 125000.0 242394.00 45000.0 220000.000
## CV residual -41560.07 -81148.92 -197129.0 -14473.26 -171344.7 4966.416
## 1305 1313 1315 1336 1343 1345 1358
## Predicted 259345.9 312604.3 249102.20 308299.5 314149.1 248727.8 299393.07
## cvpred 262068.6 314830.5 241040.42 306396.4 319594.7 240544.9 304189.86
## price_sold 150000.0 186500.0 230000.00 425000.0 219000.0 189000.0 280000.00
## CV residual -112068.6 -128330.5 -11040.42 118603.6 -100594.7 -51544.9 -24189.86
## 1359
## Predicted 202267.08
## cvpred 201640.63
## price_sold 175000.00
## CV residual -26640.63
##
## Sum of squares = 4.580109e+12 Mean square = 33677274428 n = 136
##
## fold 2
## Observations in test set: 137
## 5 8 9 11 21 23 27
## Predicted 365173.62 561620.9 244671.48 311662.22 261795.7 69258.14 135097.7
## cvpred 368806.05 562126.0 247201.83 300579.04 256406.8 61390.14 129529.3
## price_sold 269900.00 680000.0 233000.00 341000.00 403000.0 110000.00 317500.0
## CV residual -98906.05 117874.0 -14201.83 40420.96 146593.2 48609.86 187970.7
## 70 82 88 89 102 108 112
## Predicted 406764.3 262264.6 318088.1 676079.62 624051.1 293610.6 236371.61
## cvpred 413203.6 260179.9 316191.4 684657.14 631995.6 296884.2 236959.33
## price_sold 185000.0 450000.0 530000.0 670000.00 245000.0 133000.0 188500.00
## CV residual -228203.6 189820.1 213808.6 -14657.14 -386995.6 -163884.2 -48459.33
## 127 145 149 154 155 167 173
## Predicted 684210.1 164387.1 325092.56 594884.6 589788.9 350555.13 1194287.6
## cvpred 696337.1 160033.2 326999.52 599062.2 587500.4 349641.52 1206076.4
## price_sold 110000.0 335000.0 415000.00 425000.0 853000.0 410000.00 980000.0
## CV residual -586337.1 174966.8 88000.48 -174062.2 265499.6 60358.48 -226076.4
## 175 197 201 207 209 232 239
## Predicted 287102.04 190454.6 886693.6 508440.7 516392.1 436006.2 709000.9
## cvpred 282975.03 189596.3 903687.3 514816.4 519863.6 440328.4 721004.3
## price_sold 241000.00 290000.0 640000.0 426500.0 750000.0 950000.0 695000.0
## CV residual -41975.03 100403.7 -263687.3 -88316.4 230136.4 509671.6 -26004.3
## 246 256 260 271 275 284
## Predicted 420690.89 244449.6 487322.1 549642.4 352644.031 786310.9
## cvpred 426371.14 244148.3 495371.7 558048.3 359263.861 797782.5
## price_sold 515000.00 19330.0 315700.0 515000.0 355000.000 490000.0
## CV residual 88628.86 -224818.3 -179671.7 -43048.3 -4263.861 -307782.5
## 285 288 291 298 302 307 317
## Predicted 539229.6 479572.37 510493.1 371895.7 886256.4 390774.36 224623.91
## cvpred 549491.0 486889.41 515451.9 377110.2 899969.6 396251.42 224451.17
## price_sold 675000.0 484000.00 710000.0 255500.0 650000.0 325000.00 290000.00
## CV residual 125509.0 -2889.41 194548.1 -121610.2 -249969.6 -71251.42 65548.83
## 318 329 343 374 395 397 408
## Predicted 186208.3 396848.02 670084.7 557904.14 135520.7 1196537.9 118817.46
## cvpred 185587.4 402267.07 676141.6 564329.54 124736.7 1214011.5 115878.58
## price_sold 202000.0 430000.00 1075000.0 500000.00 292000.0 999000.0 193900.00
## CV residual 16412.6 27732.93 398858.4 -64329.54 167263.3 -215011.5 78021.42
## 413 429 442 451 464 466
## Predicted 178204.818 274691.9 274298.85 389010.91 595744.39 247163.71
## cvpred 174290.206 273564.5 273765.86 393788.96 599879.82 248997.37
## price_sold 183000.000 170000.0 287500.00 320000.00 520000.00 187500.00
## CV residual 8709.794 -103564.5 13734.14 -73788.96 -79879.82 -61497.37
## 471 480 507 523 538 552
## Predicted 206523.54 460784.77 399490.93 610731.4 467593.7 214967.42
## cvpred 207912.26 468289.88 406242.75 621286.2 475376.5 214355.52
## price_sold 215000.00 427000.00 381300.00 420000.0 595000.0 225000.00
## CV residual 7087.74 -41289.88 -24942.75 -201286.2 119623.5 10644.48
## 575 589 618 635 638 648
## Predicted 515150.88 203994.31 217686.44 257873.16 531582.10 472937.80
## cvpred 516937.46 203406.59 216987.53 259790.74 536551.81 474091.18
## price_sold 532000.00 175000.00 266000.00 190000.00 449000.00 390000.00
## CV residual 15062.54 -28406.59 49012.47 -69790.74 -87551.81 -84091.18
## 657 700 713 720 727 731
## Predicted 427555.7 345812.5 236680.20 551400.7 73988.30 397963.08
## cvpred 431645.1 349474.8 236738.52 555734.7 68349.62 401303.22
## price_sold 700000.0 395000.0 144500.00 38500.0 200100.00 460000.00
## CV residual 268354.9 45525.2 -92238.52 -517234.7 131750.38 58696.78
## 735 751 775 777 789 790
## Predicted 136011.514 202306.52 189034.69 521742.7 394890.9 340332.8
## cvpred 133048.589 200145.35 188608.65 530338.7 399967.3 339507.7
## price_sold 126000.000 230000.00 199900.00 314500.0 270000.0 210000.0
## CV residual -7048.589 29854.65 11291.35 -215838.7 -129967.3 -129507.7
## 796 802 805 811 830 835
## Predicted 427661.29 211048.276 495771.6 118756.2 320755.24 243983.71
## cvpred 438173.49 212678.337 499407.6 115818.1 325830.57 243182.06
## price_sold 369415.00 220000.000 637000.0 265000.0 265000.00 230000.00
## CV residual -68758.49 7321.663 137592.4 149181.9 -60830.57 -13182.06
## 838 846 847 850 854 865
## Predicted 359116.44 235218.5 230605.9 320745.2 75982.74 81934.16
## cvpred 360985.74 234676.8 229287.6 324917.3 68247.32 77803.37
## price_sold 459900.00 128000.0 379000.0 172000.0 120000.00 207500.00
## CV residual 98914.26 -106676.8 149712.4 -152917.3 51752.68 129696.63
## 872 880 884 894 897 940 958
## Predicted 336696.30 134718.4 573287.027 156673.20 415289.66 191699.3 215980
## cvpred 341302.43 126162.9 578048.699 153265.81 414076.06 187576.5 215367
## price_sold 275000.00 100000.0 575000.000 176500.00 350000.00 310000.0 121500
## CV residual -66302.43 -26162.9 -3048.699 23234.19 -64076.06 122423.5 -93867
## 963 977 996 1001 1002 1003 1005
## Predicted 298698.8 178344.6 278699.3 295930.65 354563.68 160347.64 89076.048
## cvpred 297636.6 175401.0 277146.9 297488.66 355772.21 155774.99 85586.758
## price_sold 420000.0 134900.0 164000.0 280000.00 262500.00 135000.00 90000.000
## CV residual 122363.4 -40501.0 -113146.9 -17488.66 -93272.21 -20774.99 4413.242
## 1012 1014 1016 1028 1030 1097
## Predicted 371679.21 225457.4 278119.0 239282.32 476575.9 210451.04
## cvpred 373622.22 224286.5 276387.3 237398.94 479605.6 210102.87
## price_sold 450000.00 355000.0 135000.0 190000.00 333850.0 145000.00
## CV residual 76377.78 130713.5 -141387.3 -47398.94 -145755.6 -65102.87
## 1114 1115 1117 1127 1134 1154
## Predicted 511431.46 91903.26 428796.3 91838.32 238741.88 114376.97
## cvpred 516190.31 90612.33 429460.6 84624.65 238095.34 106834.14
## price_sold 485000.00 213000.00 160000.0 158000.00 300000.00 40000.00
## CV residual -31190.31 122387.67 -269460.6 73375.35 61904.66 -66834.14
## 1157 1159 1169 1181 1187 1188
## Predicted 236962.8 142442.37 189709.4 92748.13 348759.72 389801.4
## cvpred 231130.7 135007.78 188045.6 85533.20 348747.04 397802.4
## price_sold 60000.0 55000.00 320000.0 277000.00 420000.00 225000.0
## CV residual -171130.7 -80007.78 131954.4 191466.80 71252.96 -172802.4
## 1197 1211 1218 1220 1234 1235
## Predicted 189854.92 237525.9 232389.8 208382.61 118450.86 396846.3
## cvpred 184717.84 232724.8 229873.2 202526.28 109582.02 392609.6
## price_sold 230000.00 86000.0 435000.0 165000.00 58500.00 190000.0
## CV residual 45282.16 -146724.8 205126.8 -37526.28 -51082.02 -202609.6
## 1263 1264 1272 1274 1299 1308 1325
## Predicted 383326.04 214908.6 277483.29 97510.45 93293.83 310433.44 134534.3
## cvpred 387024.47 214297.4 277054.99 92129.04 86786.73 306559.69 126582.7
## price_sold 374900.00 225000.0 200000.00 162000.00 131000.00 229000.00 131000.0
## CV residual -12124.47 10702.6 -77054.99 69870.96 44213.27 -77559.69 4417.3
## 1333 1353
## Predicted 188612.40 219417.68
## cvpred 187749.41 215871.31
## price_sold 90000.00 245900.00
## CV residual -97749.41 30028.69
##
## Sum of squares = 3.115819e+12 Mean square = 22743202595 n = 137
##
## fold 3
## Observations in test set: 137
## 19 22 28 32 38 45
## Predicted 329557.3 206614.54 361168.6 249145.83 254315.35 185970.65
## cvpred 330087.1 209276.64 367429.7 252075.36 257957.49 191257.21
## price_sold 219000.0 173000.00 120000.0 230000.00 292000.00 130000.00
## CV residual -111087.1 -36276.64 -247429.7 -22075.36 34042.51 -61257.21
## 47 60 84 87 106 120
## Predicted 355574.1 407079.3 583361.0 1005838.7 670983.8 493327.0
## cvpred 358439.6 416571.5 601522.5 1001599.9 669816.7 501519.5
## price_sold 200000.0 180000.0 218900.0 700000.0 615000.0 362500.0
## CV residual -158439.6 -236571.5 -382622.5 -301599.9 -54816.7 -139019.5
## 142 146 172 178 188 194
## Predicted 257851.6 129792.54 515645.72 1134854.7 403759.3 1454922.27
## cvpred 260640.6 131190.57 514841.24 1123804.5 404732.8 1433299.99
## price_sold 140000.0 225000.00 525000.00 1609000.0 280000.0 1501960.00
## CV residual -120640.6 93809.43 10158.76 485195.5 -124732.8 68660.01
## 204 218 221 224 237 238
## Predicted 417034.2 379529.56 1102686.8 889062.1 1296148.1 817730.48
## cvpred 415721.8 385099.43 1081912.2 884277.0 1278585.2 815559.86
## price_sold 834900.0 287400.00 1800000.0 1350000.0 1650000.0 792500.00
## CV residual 419178.2 -97699.43 718087.8 465723.0 371414.8 -23059.86
## 314 322 331 332 354 368
## Predicted 460472.78 375053.13 500063.6 449222.0 97901.07 532903.519
## cvpred 460302.77 375562.84 498389.9 453191.8 97896.45 540834.557
## price_sold 365000.00 387500.00 349900.0 873500.0 275000.00 550000.000
## CV residual -95302.77 11937.16 -148489.9 420308.2 177103.55 9165.443
## 376 378 381 399 400 401
## Predicted 228903.74 1127848.3 250281.538 272475.18 638760.3 527133.2130
## cvpred 230689.91 1113367.5 251082.522 271544.97 634743.9 525548.4622
## price_sold 200000.00 1324000.0 250000.000 200000.00 1200000.0 524900.0000
## CV residual -30689.91 210632.5 -1082.522 -71544.97 565256.1 -648.4622
## 407 409 415 418 434 440
## Predicted 658860.5 839328.5 263540.29 393018.70 867122.6 261514.07
## cvpred 658836.2 836899.4 272054.73 393942.62 864530.4 262223.49
## price_sold 475000.0 690000.0 235000.00 330000.00 565000.0 207000.00
## CV residual -183836.2 -146899.4 -37054.73 -63942.62 -299530.4 -55223.49
## 447 448 453 457 462 463
## Predicted 174304.7 631486.42 440055.80 552644.2 555808.30 557533.19
## cvpred 177876.7 623556.48 442615.93 554154.4 560358.63 561797.93
## price_sold 63000.0 669000.00 499900.00 215000.0 520000.00 520000.00
## CV residual -114876.7 45443.52 57284.07 -339154.4 -40358.63 -41797.93
## 490 505 509 517 533 539
## Predicted 268202.0 408281.5 358841.89 451135.4 726021.7 560573.2
## cvpred 266055.6 407624.0 363144.98 450947.4 723071.0 558622.1
## price_sold 129900.0 559000.0 320000.00 254000.0 410000.0 399000.0
## CV residual -136155.6 151376.0 -43144.98 -196947.4 -313071.0 -159622.1
## 555 562 581 588 595 606 615
## Predicted 237327.03 698249.73 363378.8 344928.48 605922.92 352033.5 369179.1
## cvpred 231589.42 677464.69 367576.6 349898.17 606819.71 359461.9 374738.6
## price_sold 180000.00 600000.00 200000.0 282000.00 550000.00 325000.0 331000.0
## CV residual -51589.42 -77464.69 -167576.6 -67898.17 -56819.71 -34461.9 -43738.6
## 622 632 643 650 656 663 673
## Predicted 140730.98 275805.684 218819.72 812229.33 226737 545283.8 714536.8
## cvpred 134661.89 274442.039 224486.17 798131.17 228229 530674.7 706819.7
## price_sold 146500.00 270000.000 315000.00 749900.00 380000 300000.0 319000.0
## CV residual 11838.11 -4442.039 90513.83 -48231.17 151771 -230674.7 -387819.7
## 675 678 702 717 739 744
## Predicted 394242.8 306794.18 226016.26 178913.1 213723.48 250728.581
## cvpred 400407.6 316230.97 229930.24 183497.2 217422.41 252634.763
## price_sold 365000.0 360000.00 140000.00 116500.0 292000.00 250000.000
## CV residual -35407.6 43769.03 -89930.24 -66997.2 74577.59 -2634.763
## 754 757 767 769 776 780 793
## Predicted 182513.17 207623.48 525687.7 256176.71 385682 225751.626 551950.71
## cvpred 186618.91 209247.93 519034.5 258465.89 389641 228148.102 550206.42
## price_sold 170000.00 227500.00 490000.0 174900.00 267000 223000.000 451000.00
## CV residual -16618.91 18252.07 -29034.5 -83565.89 -122641 -5148.102 -99206.42
## 801 829 831 869 881 888
## Predicted 112571.3 382647.7 320755.24 189818.13 310589.41 585474.19
## cvpred 111116.6 383665.2 328866.68 193641.81 312390.57 590455.61
## price_sold 68000.0 276000.0 265000.00 215000.00 381000.00 605000.00
## CV residual -43116.6 -107665.2 -63866.68 21358.19 68609.43 14544.39
## 895 896 901 905 927 933
## Predicted 219953.09 219953.09 475336.2 273007.6 203403.410 335761.05
## cvpred 222727.61 222727.61 476669.7 274328.9 206105.107 343707.82
## price_sold 189000.00 189000.00 375000.0 130000.0 197000.000 270000.00
## CV residual -33727.61 -33727.61 -101669.7 -144328.9 -9105.107 -73707.82
## 950 951 956 975 986 999
## Predicted 109575.34 202942.18 113319.0 92713.26 393737.0 114685.167
## cvpred 107215.14 206306.39 111874.1 91626.29 396574.1 113023.121
## price_sold 85000.00 240300.00 180000.0 260000.00 260000.0 115700.000
## CV residual -22215.14 33993.61 68125.9 168373.71 -136574.1 2676.879
## 1011 1015 1035 1060 1063 1093
## Predicted 169375.02 98926.07 436347.61 276123.2 218730.40 614101.8
## cvpred 175456.77 99951.02 432891.06 273563.3 219228.54 605314.7
## price_sold 129000.00 119000.00 460000.00 499000.0 253000.00 1150000.0
## CV residual -46456.77 19048.98 27108.94 225436.7 33771.46 544685.3
## 1095 1107 1108 1110 1113 1116 1119
## Predicted 313593.6 178706.6 137478.3 250898.0 91555.02 504614.04 86460.99
## cvpred 309728.9 183359.1 135180.5 251558.4 95390.59 506853.39 84578.14
## price_sold 158200.0 83000.0 335000.0 178800.0 180000.00 485000.00 105111.00
## CV residual -151528.9 -100359.1 199819.5 -72758.4 84609.41 -21853.39 20532.86
## 1121 1125 1143 1150 1174 1189 1202
## Predicted 243164.6 219564.5 595916.5 207585.8 326734.65 179451.51 113543.10
## cvpred 242195.8 221669.1 599476.9 210658.7 321950.17 184007.09 105973.25
## price_sold 495000.0 380000.0 843475.0 388400.0 366000.00 111500.00 131000.00
## CV residual 252804.2 158330.9 243998.1 177741.3 44049.83 -72507.09 25026.75
## 1204 1207 1208 1241 1254 1266
## Predicted 486644.0 294475.0 175177.8 139759.32 290766.971 179608.6960
## cvpred 493495.1 299721.2 179397.2 136959.47 286108.295 182787.3103
## price_sold 197750.0 445000.0 165000.0 157000.00 290000.000 182500.0000
## CV residual -295745.1 145278.8 -14397.2 20040.53 3891.705 -287.3103
## 1292 1302 1307 1321 1322 1324
## Predicted 243831.8 202539.54 325793.18 322790.4 249601.33 269929.51
## cvpred 240638.2 208397.31 319747.82 319385.2 245329.56 269276.15
## price_sold 2900.0 142500.00 229900.00 200000.0 212000.00 300749.00
## CV residual -237738.2 -65897.31 -89847.82 -119385.2 -33329.56 31472.85
## 1326 1334 1335 1339 1348 1364
## Predicted 456052.8 308299.5 308299.5 322149.18 43265.50 213807.25
## cvpred 449789.3 302356.3 302356.3 323784.99 42141.68 217629.53
## price_sold 899900.0 425000.0 425000.0 335000.00 150000.00 155000.00
## CV residual 450110.7 122643.7 122643.7 11215.01 107858.32 -62629.53
##
## Sum of squares = 4.385764e+12 Mean square = 32012874353 n = 137
##
## fold 4
## Observations in test set: 137
## 31 48 51 52 58 61 75
## Predicted 236694.3 348756.7 469977.5 302769.34 249434.7 308280.0 385820.6
## cvpred 235467.0 349122.7 469478.0 303768.18 249075.6 309014.1 380949.7
## price_sold 363000.0 200000.0 1075000.0 264900.00 110000.0 439000.0 550000.0
## CV residual 127533.0 -149122.7 605522.0 -38868.18 -139075.6 129985.9 169050.3
## 91 99 100 107 130 135 148
## Predicted 410524.1 454216.39 471759.0 233407.7 352445.9 434430 327010.7
## cvpred 405771.8 450188.47 473712.3 231958.8 355128.3 435676 327376.8
## price_sold 600000.0 505000.00 625000.0 54474.0 69668.0 212000 500000.0
## CV residual 194228.2 54811.53 151287.7 -177484.8 -285460.3 -223676 172623.2
## 166 192 199 203 205 212 215
## Predicted 243296.2 973117.19 131605.0 75115.04 256489.68 581646.71 99026.21
## cvpred 242510.0 981854.64 133195.8 73420.92 255852.46 583669.39 99633.40
## price_sold 353000.0 932000.00 120000.0 179725.00 244900.00 528000.00 40000.00
## CV residual 110490.0 -49854.64 -13195.8 106304.08 -10952.46 -55669.39 -59633.40
## 235 241 242 251 257 306
## Predicted 405629.08 1198467.9 362116.8 278254.42 205267.93 350817.6
## cvpred 406059.97 1213090.5 361269.0 279045.04 206167.04 349667.9
## price_sold 450500.00 935000.0 90201.0 319000.00 265000.00 305500.0
## CV residual 44440.03 -278090.5 -271068.0 39954.96 58832.96 -44167.9
## 316 330 335 347 349 369 372
## Predicted 222556.07 319970.77 522702.43 777154.0 562514.8 180788.4 663696.3
## cvpred 221090.29 322082.76 526929.38 780043.5 568155.9 179529.4 668277.2
## price_sold 289900.00 340000.00 512900.00 858700.0 444500.0 280000.0 475000.0
## CV residual 68809.71 17917.24 -14029.38 78656.5 -123655.9 100470.6 -193277.2
## 386 411 416 423 426 433 436
## Predicted 286934.1 495572.88 557346.2 199122.42 494682.7 256555.63 513294.8
## cvpred 287847.8 501324.56 558723.9 197181.07 497950.1 257631.22 513154.6
## price_sold 255000.0 449500.00 675000.0 210000.00 900000.0 163500.00 405000.0
## CV residual -32847.8 -51824.56 116276.1 12818.93 402049.9 -94131.22 -108154.6
## 460 477 484 497 499 506 514
## Predicted 1077837 564336.86 185717.2 386818.436 574578.86 540233.66 362747.13
## cvpred 1090159 565825.88 184874.9 386843.816 579119.25 541601.27 361792.46
## price_sold 799900 633000.00 215000.0 380000.000 482725.00 608000.00 324900.00
## CV residual -290259 67174.12 30125.1 -6843.816 -96394.25 66398.73 -36892.46
## 519 530 557 566 567 574
## Predicted 256964.13 478910.7 374655.11 374080.2 162736.25 226029.71
## cvpred 258364.31 481503.4 374165.63 373462.8 167288.68 226331.17
## price_sold 183000.00 335000.0 279900.00 235000.0 115000.00 260000.00
## CV residual -75364.31 -146503.4 -94265.63 -138462.8 -52288.68 33668.83
## 585 592 593 597 599 604
## Predicted 90730.89 405550.00 421598.6 336353.0 458039.5 290172.8
## cvpred 89472.27 408120.33 422608.5 336082.9 459847.4 294050.6
## price_sold 119000.00 467000.00 289000.0 229000.0 300000.0 185000.0
## CV residual 29527.73 58879.67 -133608.5 -107082.9 -159847.4 -109050.6
## 634 645 654 665 684 685 688
## Predicted 551251.0 220897.3 288288.38 240061.7 232412.97 238937.89 373516.82
## cvpred 551996.1 221406.0 289521.44 240956.3 231873.37 239806.25 372894.86
## price_sold 320000.0 329000.0 262500.00 378000.0 219900.00 259900.00 358000.00
## CV residual -231996.1 107594.0 -27021.44 137043.7 -11973.37 20093.75 -14894.86
## 690 695 697 703 708 710 718
## Predicted 224512.13 479886.2 271701.3 113333.3 207827.25 302559.87 489384.0
## cvpred 224820.01 484454.0 272777.9 114237.9 206827.25 304300.71 492513.9
## price_sold 184900.00 440000.0 98775.0 232500.0 273000.00 220000.00 255000.0
## CV residual -39920.01 -44454.0 -174002.9 118262.1 66172.75 -84300.71 -237513.9
## 745 752 759 765 766 773 774
## Predicted 747522.2 477450.7 258779.0 386934.3 278187.60 357778.22 288072.4
## cvpred 752889.2 480778.8 259263.6 389106.2 281950.01 360314.33 290620.2
## price_sold 1025000.0 329900.0 115000.0 740000.0 335000.00 430000.00 565100.0
## CV residual 272110.8 -150878.8 -144263.6 350893.8 53049.99 69685.67 274479.8
## 787 791 797 808 809 814 818
## Predicted 68208.17 522022.5 233885.8 461254.6 204293.00 248829.2 493049.6
## cvpred 67680.76 525907.2 232556.5 467235.0 204075.18 250366.7 497916.8
## price_sold 155900.00 710000.0 404325.0 136429.0 241000.00 500000.0 73000.0
## CV residual 88219.24 184092.8 171768.5 -330806.0 36924.82 249633.3 -424916.8
## 841 860 873 898 908 911 913
## Predicted 214793.1 363785.03 339053.67 282370.84 228794.1 547875.5 374921.53
## cvpred 214232.2 363244.49 337469.45 280223.27 229399.9 548724.8 374617.28
## price_sold 360000.0 445000.00 285000.00 207000.00 382000.0 382000.0 284900.00
## CV residual 145767.8 81755.51 -52469.45 -73223.27 152600.1 -166724.8 -89717.28
## 924 971 993 998 1010 1031
## Predicted 199054.79 209456.41 380622.8 158622.75 108221.58 207654.91
## cvpred 198885.99 205360.33 382088.9 159985.37 108840.63 207533.59
## price_sold 180000.00 230000.00 260000.0 135800.00 175000.00 175000.00
## CV residual -18885.99 24639.67 -122088.9 -24185.37 66159.37 -32533.59
## 1034 1047 1056 1059 1066 1067
## Predicted 461707.1 364728.30 329057.65 245619.4 287070.91 364452.35
## cvpred 470135.9 365453.43 331826.28 245458.5 283724.32 367279.21
## price_sold 185000.0 319000.00 350000.00 506000.0 210000.00 449900.00
## CV residual -285135.9 -46453.43 18173.72 260541.5 -73724.32 82620.79
## 1080 1085 1087 1099 1133 1163
## Predicted 686933.1 403455.3 61026.95 389932.0 527761.6 224827.55
## cvpred 690651.2 404682.6 60371.10 389562.7 532749.4 224295.13
## price_sold 1070000.0 75000.0 168000.00 280000.0 390000.0 288500.00
## CV residual 379348.8 -329682.6 107628.90 -109562.7 -142749.4 64204.87
## 1168 1176 1184 1186 1190 1192
## Predicted 122252.1 222876.79 183520.104 70098.76 231381.64 186268.93
## cvpred 122217.8 222586.58 182656.868 69532.39 234355.04 184389.23
## price_sold 285000.0 170000.00 190000.000 237500.00 145000.00 111500.00
## CV residual 162782.2 -52586.58 7343.132 167967.61 -89355.04 -72889.23
## 1195 1196 1198 1206 1222 1225
## Predicted 293889.7 156111.22 372465.5 403122.4 286345.1 321740.64
## cvpred 295673.0 157038.47 377000.6 404586.8 289475.9 320474.03
## price_sold 415000.0 130000.00 74000.0 284700.0 165000.0 235000.00
## CV residual 119327.0 -27038.47 -303000.6 -119886.8 -124475.9 -85474.03
## 1228 1237 1249 1260 1280 1293
## Predicted 270118.55 188165.06 407106.3 168525.16 236036.47 386454.266
## cvpred 274070.77 187439.53 408392.3 171543.12 236401.98 387480.637
## price_sold 280000.00 235000.00 282200.0 209900.00 168000.00 382500.000
## CV residual 5929.23 47560.47 -126192.3 38356.88 -68401.98 -4980.637
## 1310 1314 1317 1319 1340 1365
## Predicted 311300.5 249471.69 248547.964 218900.5 337508.85 728174.5
## cvpred 315603.2 248593.23 247598.159 219929.1 336958.24 731120.3
## price_sold 160000.0 239900.00 240316.000 10000.0 335500.00 625000.0
## CV residual -155603.2 -8693.23 -7282.159 -209929.1 -1458.24 -106120.3
##
## Sum of squares = 3.279989e+12 Mean square = 23941528551 n = 137
##
## fold 5
## Observations in test set: 137
## 18 26 43 56 57 65 81
## Predicted 558124.5 349441.8 189345.94 203096.297 209553.14 283810.9 270457.8
## cvpred 558812.2 349224.0 188306.85 199920.422 208805.25 239828.9 256795.7
## price_sold 1050000.0 480000.0 134000.00 190000.000 150000.00 535000.0 419900.0
## CV residual 491187.8 130776.0 -54306.85 -9920.422 -58805.25 295171.1 163104.3
## 137 139 140 141 156 158 168
## Predicted 669574.9 377596.0 407438.8 546376.5 708800.5 356302.89 423406.3
## cvpred 672579.0 375126.8 406295.5 551930.6 709822.7 354505.63 422331.0
## price_sold 915000.0 51314.0 615000.0 375000.0 580000.0 420000.00 565000.0
## CV residual 242421.0 -323812.8 208704.5 -176930.6 -129822.7 65494.37 142669.0
## 181 183 191 210 213 219 230
## Predicted 188722.4 577033.3 366764.13 335127.4 1029884 836967.3 545981.6786
## cvpred 179263.5 589165.1 361744.85 329742.6 1042290 847953.3 549315.3698
## price_sold 255000.0 435000.0 349900.00 450000.0 700000 1300000.0 550000.0000
## CV residual 75736.5 -154165.1 -11844.85 120257.4 -342290 452046.7 684.6302
## 245 250 254 259 263 267
## Predicted 944462.7 1125671.0 229217.65 234097.88 1170924.4 431319.6
## cvpred 954114.4 1142942.9 227772.56 231568.76 1184469.7 435823.4
## price_sold 759000.0 651900.0 195000.00 310000.00 1010000.0 285000.0
## CV residual -195114.4 -491042.9 -32772.56 78431.24 -174469.7 -150823.4
## 269 272 276 294 297 300
## Predicted 222021.22 362242.7 49468.85 1329145.3 514739.33 192082.52
## cvpred 215377.28 365292.3 43321.92 1347964.7 510892.25 192061.53
## price_sold 244800.00 630000.0 155000.00 1000000.0 550000.00 260000.00
## CV residual 29422.72 264707.7 111678.08 -347964.7 39107.75 67938.47
## 308 311 320 325 328 333
## Predicted 1349118.1 122352.31 317632.144 1183421.7 397996.29 452916.9
## cvpred 1355065.7 124139.08 311219.515 1200465.5 394442.07 450264.9
## price_sold 1150000.0 215000.00 310000.000 1320000.0 331500.00 873500.0
## CV residual -205065.7 90860.92 -1219.515 119534.5 -62942.07 423235.1
## 334 336 338 341 361 363 367
## Predicted 510643.1 813270.0 319753.28 533999.67 704885.41 390776.8 777928.2
## cvpred 503942.4 811698.4 324789.23 531292.17 711147.88 396445.9 777965.9
## price_sold 712000.0 1128000.0 335000.00 512500.00 700000.00 280000.0 940000.0
## CV residual 208057.6 316301.6 10210.77 -18792.17 -11147.88 -116445.9 162034.1
## 385 432 441 454 474 492 495
## Predicted 359425.17 475007.59 307298.83 1082210.0 94209.91 335685.52 652436
## cvpred 353923.35 470056.28 303159.62 1088762.8 93939.75 336041.19 651755
## price_sold 364000.00 414000.00 288900.00 1550000.0 290000.00 257000.00 1500100
## CV residual 10076.65 -56056.28 -14259.62 461237.2 196060.25 -79041.19 848345
## 501 554 556 564 576 584 587
## Predicted 492971.2 664446.2 379680.28 417557.5 475061.1 301232.75 344928.48
## cvpred 500273.8 670326.4 375627.78 419139.2 471109.9 296353.49 342960.57
## price_sold 177000.0 799000.0 305000.00 629900.0 717000.0 252000.00 282000.00
## CV residual -323273.8 128673.6 -70627.78 210760.8 245890.1 -44353.49 -60960.57
## 596 627 639 664 667 689 691
## Predicted 607647.8 205879.24 441580.499 401316.8 216848.73 301968.0 93929.783
## cvpred 610545.3 201351.88 441233.478 403281.1 212485.08 296177.2 88431.628
## price_sold 550000.0 287990.00 449000.000 649900.0 240000.00 255000.0 84500.000
## CV residual -60545.3 86638.12 7766.522 246618.9 27514.92 -41177.2 -3931.628
## 699 709 716 726 729 730
## Predicted 235342.984 693529.4 249650.29 231726.31 369116.7 213931.661
## cvpred 233343.947 696449.3 247450.24 229489.88 368371.2 208883.466
## price_sold 225000.000 468000.0 223500.00 228000.00 255000.0 199000.000
## CV residual -8343.947 -228449.3 -23950.24 -1489.88 -113371.2 -9883.466
## 760 763 784 786 795 804
## Predicted 394684.4 335471.2 79216.84 192711.2 876822.2 80014.59
## cvpred 394954.5 330835.0 77213.26 187074.6 881689.2 74027.48
## price_sold 266000.0 260000.0 282525.00 55000.0 460000.0 162000.00
## CV residual -128954.5 -70835.0 205311.74 -132074.6 -421689.2 87972.52
## 807 816 824 826 837 843
## Predicted 697777.60 308726.27 385175.09 372056.86 243496.61 96328.76
## cvpred 699454.44 305673.88 379605.66 373157.55 240032.73 93726.36
## price_sold 599950.00 215000.00 360000.00 276000.00 259000.00 205000.00
## CV residual -99504.44 -90673.88 -19605.66 -97157.55 18967.27 111273.64
## 844 858 885 902 906 907 922
## Predicted 203058.83 383510.72 330255.6 513668.0 179083.94 421591.6 205872.21
## cvpred 199631.95 380956.47 331639.4 516382.8 172906.04 413799.7 203630.99
## price_sold 140000.00 430000.00 495000.0 400000.0 135000.00 545000.0 180000.00
## CV residual -59631.95 49043.53 163360.6 -116382.8 -37906.04 131200.3 -23630.99
## 923 928 939 954 955 961
## Predicted 205872.21 295275.87 318063.44 274797.59 283339.90 221339.3
## cvpred 203630.99 292871.05 319844.97 272709.28 284197.81 220952.4
## price_sold 180000.00 265000.00 253000.00 295000.00 295000.00 120000.0
## CV residual -23630.99 -27871.05 -66844.97 22290.72 10802.19 -100952.4
## 964 989 1018 1022 1033 1037 1041
## Predicted 173699.76 273361.0 353002.4 280074.1 193255.9 214847.70 289163.8
## cvpred 167403.42 266715.2 346104.0 281701.8 181654.9 210994.94 290002.8
## price_sold 199000.00 209500.0 237160.0 385000.0 335000.0 227000.00 173000.0
## CV residual 31596.58 -57215.2 -108944.0 103298.2 153345.1 16005.06 -117002.8
## 1069 1082 1111 1126 1128 1131 1138
## Predicted 394139.5 237955.05 86252.86 170893.76 91224.98 214857.52 207589.2
## cvpred 386086.1 234078.03 81047.86 175127.44 91464.01 216434.36 203321.8
## price_sold 570000.0 141000.00 260000.00 120000.00 165000.00 180000.00 370000.0
## CV residual 183913.9 -93078.03 178952.14 -55127.44 73535.99 -36434.36 166678.2
## 1142 1148 1164 1165 1171 1173
## Predicted 277419.61 368285.60 218942.70 241276.30 252093.27 159813.26
## cvpred 274698.98 368487.18 213642.48 239875.99 256224.15 159964.51
## price_sold 195000.00 400000.00 187500.00 339000.00 163500.00 110650.00
## CV residual -79698.98 31512.82 -26142.48 99124.01 -92724.15 -49314.51
## 1180 1205 1214 1236 1240 1243
## Predicted 92748.13 88141.42 360638.39 212325.35 443533.3 306281.1
## cvpred 91480.20 85774.32 355189.05 207602.05 442569.4 302317.2
## price_sold 277000.00 180000.00 435000.00 238000.00 322000.0 416000.0
## CV residual 185519.80 94225.68 79810.95 30397.95 -120569.4 113682.8
## 1247 1268 1284 1296 1300 1304
## Predicted 122553.36 312094.3 301495.45 250746.98 210833.5 102424.69
## cvpred 125623.49 308295.9 306986.08 255162.44 213027.4 103312.94
## price_sold 27886.00 170000.0 235000.00 195000.00 367700.0 120000.00
## CV residual -97737.49 -138295.9 -71986.08 -60162.44 154672.6 16687.06
## 1316 1318 1347 1354 1360 1362
## Predicted 240375.14 129730.198 231216.89 203046.336 377233.0 158515.51
## cvpred 238447.21 141494.236 230666.11 199904.337 385737.1 153917.13
## price_sold 227000.00 140000.000 275000.00 190000.000 70000.0 92500.00
## CV residual -11447.21 -1494.236 44333.89 -9904.337 -315737.1 -61417.13
## 1366
## Predicted 197729.70
## cvpred 189765.27
## price_sold 215000.00
## CV residual 25234.73
##
## Sum of squares = 4.204096e+12 Mean square = 30686831164 n = 137
##
## fold 6
## Observations in test set: 137
## 17 20 25 33 36 41 53
## Predicted 468122.9 329557.3 179949.3 84694.03 217186.3 208782.35 360855.2
## cvpred 467996.3 326263.1 180647.6 86182.76 218669.0 207453.75 360772.6
## price_sold 1050000.0 219000.0 309000.0 230000.00 595000.0 165000.00 440000.0
## CV residual 582003.7 -107263.1 128352.4 143817.24 376331.0 -42453.75 79227.4
## 59 69 78 83 86 96
## Predicted 601724.67 328103.76 308802.2998 530889.2 325592.48 120899.5
## cvpred 599794.31 336193.79 307219.7393 526550.7 336426.25 121056.7
## price_sold 535000.00 355000.00 307000.0000 259900.0 365000.00 315000.0
## CV residual -64794.31 18806.21 -219.7393 -266650.7 28573.75 193943.3
## 105 114 125 160 162 163
## Predicted 803189.4 232794.20 359871.4 193494.72 758091.0 69476.71
## cvpred 800596.3 232037.14 357572.5 196029.58 757330.1 66024.19
## price_sold 667000.0 147000.00 249900.0 230000.00 385000.0 205000.00
## CV residual -133596.3 -85037.14 -107672.5 33970.42 -372330.1 138975.81
## 165 189 193 200 208 222
## Predicted 297213.3 479584.5 472864.39 800553.5 428814.3 102043.495
## cvpred 291384.3 479754.1 470620.11 800630.8 430201.6 103104.418
## price_sold 485000.0 611000.0 398000.00 470000.0 276000.0 108000.000
## CV residual 193615.7 131245.9 -72620.11 -330630.8 -154201.6 4895.582
## 225 229 240 247 248 249
## Predicted 1213381.30 394024.4 177324.9 783027.8 201575.11 448475.1
## cvpred 1205527.46 397032.1 175399.4 779961.6 200930.32 447590.6
## price_sold 1300000.00 525000.0 178500.0 585000.0 230000.00 275000.0
## CV residual 94472.54 127967.9 3100.6 -194961.6 29069.68 -172590.6
## 252 310 321 340 345 346
## Predicted 208993.39 345959.93 658465.94 510643.1 391508.9 716834.54
## cvpred 207682.45 343317.06 657349.57 502201.7 396001.9 712315.64
## price_sold 165000.00 307200.00 585000.00 712000.0 236000.0 800000.00
## CV residual -42682.45 -36117.06 -72349.57 209798.3 -160001.9 87684.36
## 352 356 359 370 375 377
## Predicted 238989.94 558752.64 131018.1 241629.749 262096.34 247109.39
## cvpred 238666.84 553633.56 131161.8 238637.674 260395.21 246955.66
## price_sold 266000.00 581000.00 266900.0 244554.000 208000.00 268000.00
## CV residual 27333.16 27366.44 135738.2 5916.326 -52395.21 21044.34
## 392 404 420 421 430 437 446
## Predicted 1716529.3 617307.4 465985.7 365889.6 875024.86 306346.83 754169.3
## cvpred 1714737.5 618043.1 463907.6 363670.6 876291.96 305132.37 755048.7
## price_sold 2700000.0 500000.0 624900.0 549980.0 800000.00 400000.00 530000.0
## CV residual 985262.5 -118043.1 160992.4 186309.4 -76291.96 94867.63 -225048.7
## 452 467 496 500 511 521
## Predicted 292056.09 695192.4 652436.0 421075.215 243819.58 349433.5
## cvpred 291040.45 692510.5 647066.3 419497.658 245960.59 346850.1
## price_sold 311500.00 525000.0 1500100.0 410000.000 200000.00 485000.0
## CV residual 20459.55 -167510.5 853033.7 -9497.658 -45960.59 138149.9
## 526 528 545 546 569 573 580
## Predicted 232919.0 207646.48 435675.2 292195.5 195805.7 314619.40 584876.60
## cvpred 230626.3 204839.59 430354.0 290730.6 190750.9 311241.84 584917.27
## price_sold 128000.0 255000.00 482500.0 454500.0 219900.0 276000.00 545000.00
## CV residual -102626.3 50160.41 52146.0 163769.4 29149.1 -35241.84 -39917.27
## 586 611 624 644 647 649
## Predicted 263562.2 379656.67 403584.32 403335.157 254227.24 295987.16
## cvpred 263406.2 377649.96 399300.59 399550.459 250080.84 291819.68
## price_sold 425000.0 300000.00 320305.00 405000.000 215000.00 270000.00
## CV residual 161593.8 -77649.96 -78995.59 5449.541 -35080.84 -21819.68
## 655 666 671 672 677 683
## Predicted 326958.38 232604.478 81178.79 438671.6 221434.19 460932.5
## cvpred 323851.25 227930.558 80255.62 441794.0 221227.75 460670.5
## price_sold 280000.00 235000.000 120000.00 269900.0 194900.00 280000.0
## CV residual -43851.25 7069.442 39744.38 -171894.0 -26327.75 -180670.5
## 686 722 723 747 753 755 758
## Predicted 512770.69 232823.6 354256.8 200280.80 363852.3 1267345 311484.99
## cvpred 513574.75 230511.6 351722.4 197749.51 361547.7 1278036 310837.86
## price_sold 415000.00 80000.0 163600.0 159900.00 260000.0 980000 385000.00
## CV residual -98574.75 -150511.6 -188122.4 -37849.51 -101547.7 -298036 74162.14
## 764 785 788 794 817 834 848
## Predicted 130881.21 259460.0 196748.77 337528.9 363484.51 325525.8 595302.7
## cvpred 137618.44 259211.2 192836.63 332833.0 358807.05 330909.2 590690.4
## price_sold 205000.00 550000.0 219900.00 190000.0 337000.00 589000.0 1200000.0
## CV residual 67381.56 290788.8 27063.37 -142833.0 -21807.05 258090.8 609309.6
## 851 857 871 874 876 878 890
## Predicted 277977.9 1040082 336696.30 173022.205 286438.0 361099.10 232272.54
## cvpred 276234.8 1059138 333776.57 171318.852 282974.1 356922.83 231805.71
## price_sold 660000.0 530000 275000.00 175000.000 565000.0 445000.00 270000.00
## CV residual 383765.2 -529138 -58776.57 3681.148 282025.9 88077.17 38194.29
## 892 893 925 930 935 944
## Predicted 86415.11 86415.11 106038.22 323340.77 122150.61 255627.5
## cvpred 85599.53 85599.53 107981.42 320139.81 120248.69 253839.9
## price_sold 143000.00 143000.00 160500.00 260000.00 179900.00 512500.0
## CV residual 57400.47 57400.47 52518.58 -60139.81 59651.31 258660.1
## 952 959 978 980 994 1023
## Predicted 402549.78 164416.54 219129.0 174009.34 115735.63 255886.30
## cvpred 398719.78 162958.03 214191.9 172756.12 117056.15 252190.24
## price_sold 380000.00 93000.00 90000.0 90500.00 135000.00 182850.00
## CV residual -18719.78 -69958.03 -124191.9 -82256.12 17943.85 -69340.24
## 1025 1029 1032 1038 1044 1049
## Predicted 236734.34 219660.59 219926.67 255460.51 371545.73 263497.578
## cvpred 236425.29 219413.72 217365.34 253622.91 366674.51 261433.005
## price_sold 144900.00 205000.00 193000.00 346000.00 319900.00 253000.000
## CV residual -91525.29 -14413.72 -24365.34 92377.09 -46774.51 -8433.005
## 1050 1065 1075 1081 1089 1105 1122
## Predicted 235068.25 377606.86 250968.81 103332.0 300773.0 267496.7 479228.46
## cvpred 236624.39 377680.44 246822.11 101036.7 297202.3 267440.8 476796.02
## price_sold 329000.00 317000.00 187000.00 253000.0 39000.0 478000.0 465000.00
## CV residual 92375.61 -60680.44 -59822.11 151963.3 -258202.3 210559.2 -11796.02
## 1136 1166 1178 1199 1215 1217
## Predicted 138164.58 193508.376 549653.0 194534.6 439834.49 280670.03
## cvpred 138479.89 196544.935 544414.7 191883.7 434200.68 273986.95
## price_sold 50000.00 191000.000 655500.0 347500.0 351000.00 339000.00
## CV residual -88479.89 -5544.935 111085.3 155616.3 -83200.68 65013.05
## 1265 1276 1277 1279 1297 1303
## Predicted 60464.76 236036.48 68496.71 241022.71 432641.7 278206.98
## cvpred 61362.43 233051.09 68866.20 237076.96 431761.1 276855.75
## price_sold 142000.00 168000.00 45000.00 242394.00 221000.0 225000.00
## CV residual 80637.57 -65051.09 -23866.20 5317.04 -210761.1 -51855.75
## 1341 1349 1351 1356
## Predicted 259592.1 222877.29 219337.5 179077.5
## cvpred 261765.9 224277.78 220463.8 177187.7
## price_sold 60000.0 135000.00 353000.0 50000.0
## CV residual -201765.9 -89277.78 132536.2 -127187.7
##
## Sum of squares = 5.008166e+12 Mean square = 36555957922 n = 137
##
## fold 7
## Observations in test set: 137
## 24 29 44 54 73 77 79
## Predicted 322622.04 89801.146 303198.96 449624.9 458106.8 343950.03 572605
## cvpred 318571.32 96332.173 300062.11 446167.7 452279.8 347594.57 566286
## price_sold 290000.00 90000.000 230000.00 170000.0 310000.0 425000.00 700000
## CV residual -28571.32 -6332.173 -70062.11 -276167.7 -142279.8 77405.43 133714
## 90 103 134 152 169 174
## Predicted 669860.85 343726.8 415052.9 1390141.5 412529.41 692994.9
## cvpred 663230.65 346361.9 414423.5 1378292.9 411263.01 684446.0
## price_sold 705500.00 221500.0 294900.0 1600000.0 445000.00 1100000.0
## CV residual 42269.35 -124861.9 -119523.5 221707.1 33736.99 415554.0
## 180 190 211 233 234 253
## Predicted 571031.78 506718.8 265075.54 389865.24 702811.10 934768.72
## cvpred 564920.87 500903.2 266980.13 389046.83 699790.72 917664.84
## price_sold 600000.00 780000.0 350000.00 465000.00 647800.00 950000.00
## CV residual 35079.13 279096.8 83019.87 75953.17 -51990.72 32335.16
## 258 262 264 265 277 278
## Predicted 506528.67 245582.57 1120298.7 487517.14 202992.2 758534.9
## cvpred 498791.46 245210.39 1114091.1 487393.74 204461.0 751076.6
## price_sold 421500.00 275000.00 837500.0 407975.00 250000.0 1400000.0
## CV residual -77291.46 29789.61 -276591.1 -79418.74 45539.0 648923.4
## 286 309 312 351 382 391
## Predicted 296790.47 1116294.9 535415.0 321304.6 539847.40 410682.41
## cvpred 300367.67 1089533.1 529136.8 322848.1 535065.42 408318.23
## price_sold 335000.00 1842700.0 630000.0 192500.0 480000.00 325000.00
## CV residual 34632.33 753166.9 100863.2 -130348.1 -55065.42 -83318.23
## 396 403 414 425 461 469
## Predicted 501631.8 804733.8 626633.54 494682.7 262998.13 389712.72
## cvpred 509504.7 791439.6 616621.35 494894.6 265117.72 387685.19
## price_sold 300000.0 1306000.0 550000.00 900000.0 199000.00 375000.00
## CV residual -209504.7 514560.4 -66621.35 405105.4 -66117.72 -12685.19
## 472 475 481 493 516 518
## Predicted 608398.27 529943.2 276412.742 369125.60 118526.01 389880.2
## cvpred 602864.64 523092.7 277668.913 368997.41 124168.37 389530.4
## price_sold 530230.00 769100.0 280000.000 279000.00 110111.00 545000.0
## CV residual -72634.64 246007.3 2331.087 -89997.41 -14057.37 155469.6
## 522 529 535 540 541 544
## Predicted 532900.9 299046.72 146736.32 386991.888 292195.5 357721.28
## cvpred 523529.5 299347.37 150697.41 382988.793 293841.3 355619.14
## price_sold 398000.0 218000.00 159000.00 390000.000 454500.0 340000.00
## CV residual -125529.5 -81347.37 8302.59 7011.207 160658.7 -15619.14
## 549 550 553 561 570 583
## Predicted 281117.1 214967.424 398574.46 589916.6 338014.94 73566.55
## cvpred 281235.3 216408.726 392697.87 581735.8 334918.05 78187.60
## price_sold 173000.0 225000.000 465000.00 1050000.0 405000.00 111000.00
## CV residual -108235.3 8591.274 72302.13 468264.2 70081.95 32812.40
## 591 613 628 629 631 636
## Predicted 249329.04 242166.11 380224.22 483125.1 275805.684 420027.01
## cvpred 251645.38 246953.15 381348.89 484882.7 276986.022 416304.72
## price_sold 226000.00 340000.00 349900.00 640000.0 270000.000 383000.00
## CV residual -25645.38 93046.85 -31448.89 155117.3 -6986.022 -33304.72
## 653 660 662 669 679 701 706
## Predicted 334953.13 247024.86 434757.52 434978.1 88107.12 345812.5 269607.0
## cvpred 333296.96 248527.04 435619.54 436305.6 91452.31 341931.8 271076.7
## price_sold 302000.00 220000.00 355000.00 558650.0 95000.00 395000.0 120000.0
## CV residual -31296.96 -28527.04 -80619.54 122344.4 3547.69 53068.2 -151076.7
## 707 734 736 738 742 750
## Predicted 254969.68 346288.14 410725.2 305187.97 94838.91 202306.52
## cvpred 258512.13 344980.45 405127.8 301273.05 99254.45 201430.74
## price_sold 235000.00 275000.00 238775.0 235000.00 171000.00 230000.00
## CV residual -23512.13 -69980.45 -166352.8 -66273.05 71745.55 28569.26
## 756 762 768 770 781 782
## Predicted 192263.7 297562.5 296248.6 255957.7 225751.626 109352.35
## cvpred 191263.7 299186.6 291982.7 255511.3 228023.094 115780.16
## price_sold 230700.0 157000.0 172950.0 510000.0 223000.000 210000.00
## CV residual 39436.3 -142186.6 -119032.7 254488.7 -5023.094 94219.84
## 803 821 849 856 863 866 870
## Predicted 285074.09 517122.0 225264.50 103300.26 295557.2 573076.36 342528.17
## cvpred 283989.94 512721.9 228993.31 109930.76 295954.4 562512.82 342294.08
## price_sold 300000.00 617000.0 195000.00 193500.00 330000.0 625000.00 280000.00
## CV residual 16010.06 104278.1 -33993.31 83569.24 34045.6 62487.18 -62294.08
## 883 904 915 921 949 976
## Predicted 352648.94 250686.81 171767.96 88346.14 239205.81 382742.61
## cvpred 347169.09 253749.02 174139.68 93666.98 238530.67 382831.72
## price_sold 257500.00 169000.00 214300.00 108000.00 227000.00 357000.00
## CV residual -89669.09 -84749.02 40160.32 14333.02 -11530.67 -25831.72
## 982 984 985 988 991 1004
## Predicted 412105.60 182368.83 393737 237232.31 102424.541 151805.33
## cvpred 406845.96 183573.98 391602 234469.46 108536.539 156996.73
## price_sold 315000.00 145000.00 260000 276670.00 105000.000 135000.00
## CV residual -91845.96 -38573.98 -131602 42200.54 -3536.539 -21996.73
## 1007 1013 1019 1024 1026 1042
## Predicted 249356.68 158531.9 390310.63491 271246.03 179076.79 438837.8
## cvpred 248436.08 158719.6 384918.08069 271380.66 180153.65 434661.5
## price_sold 222000.00 320150.0 385000.00000 182850.00 81000.00 333500.0
## CV residual -26436.08 161430.4 81.91931 -88530.66 -99153.65 -101161.5
## 1054 1057 1061 1077 1079 1091
## Predicted 442082.0 77946.69 311128.7 201195.14 299395.8 189595.49
## cvpred 437180.2 82880.74 310901.4 199508.32 297267.3 193933.81
## price_sold 700000.0 180000.00 130500.0 175000.00 230000.0 272000.00
## CV residual 262819.8 97119.26 -180401.4 -24508.32 -67267.3 78066.19
## 1100 1104 1151 1152 1167 1177 1182
## Predicted 447989.036 110871.59 354978.3 241541.9 267191.9 284356.2 179617.01
## cvpred 443174.517 116238.22 353105.0 241680.0 268455.8 278239.2 178151.08
## price_sold 445500.000 180000.00 246000.0 375000.0 385000.0 520000.0 245000.00
## CV residual 2325.483 63761.78 -107105.0 133320.0 116544.2 241760.8 66848.92
## 1200 1209 1210 1224 1229 1232
## Predicted 381896.50 386559.0 305857.66 338052.6 279632.8 339297.0
## cvpred 381185.77 382407.2 296932.65 337039.6 277650.0 332216.2
## price_sold 480000.00 152000.0 350000.00 151750.0 450000.0 145000.0
## CV residual 98814.23 -230407.2 53067.35 -185289.6 172350.0 -187216.2
## 1239 1244 1269 1275 1285 1286
## Predicted 389823.39 397082.5 240697.83 218711.72 347708.7 308902.6
## cvpred 386488.18 395384.3 242345.86 216458.58 345709.5 305837.9
## price_sold 435000.00 295000.0 158000.00 182000.00 235000.0 160000.0
## CV residual 48511.82 -100384.3 -84345.86 -34458.58 -110709.5 -145837.9
## 1287 1301 1323 1331 1337 1346
## Predicted 285471.72 532179.78 285289.24 88533.594 488584.4 240370.2
## cvpred 285236.94 531038.31 286938.27 93200.953 480314.2 242619.8
## price_sold 280000.00 549000.00 300749.00 100000.000 285000.0 100000.0
## CV residual -5236.94 17961.69 13810.73 6799.047 -195314.2 -142619.8
## 1352
## Predicted 440970.21
## cvpred 435542.23
## price_sold 467000.00
## CV residual 31457.77
##
## Sum of squares = 3.344533e+12 Mean square = 24412648405 n = 137
##
## fold 8
## Observations in test set: 136
## 1 10 13 35 63 64
## Predicted 332027.4 215971.55 598442.4 446599.6 700200.9 494017.3
## cvpred 333227.0 222590.17 588309.1 441979.6 711545.1 519906.2
## price_sold 214300.0 187000.00 1050000.0 1175000.0 470000.0 870000.0
## CV residual -118927.0 -35590.17 461690.9 733020.4 -241545.1 350093.8
## 68 76 85 94 95 104 111
## Predicted 1099912.2 1164989 268434.60 2034560.8 629597.3 249230.88 289506.3
## cvpred 1108159.2 1163630 278947.68 1990745.9 630683.7 252106.33 294204.4
## price_sold 695000.0 900000 365000.00 2900000.0 875000.0 225000.00 122000.0
## CV residual -413159.2 -263630 86052.32 909254.1 244316.3 -27106.33 -172204.4
## 117 121 133 138 144 157
## Predicted 733469.4 651354.8 288164.664 794993.5 717902.6 549353.0
## cvpred 731735.3 643300.3 284164.425 797736.7 716940.2 543325.1
## price_sold 849000.0 437000.0 290000.000 680000.0 555000.0 425000.0
## CV residual 117264.7 -206300.3 5835.575 -117736.7 -161940.2 -118325.1
## 161 164 176 198 206 217 220
## Predicted 614410.0 297213.3 201764.0 252442.45 332923.3 413389.57 201739.73
## cvpred 614488.6 306825.3 206653.4 253906.71 361075.1 418252.28 204349.27
## price_sold 430000.0 485000.0 320000.0 242000.00 562200.0 465000.00 122000.00
## CV residual -184488.6 178174.7 113346.6 -11906.71 201124.9 46747.72 -82349.27
## 227 243 244 273 280 295
## Predicted 419969.08 1112286.7 201711.11 777358.3 968898.96 406372.50
## cvpred 424488.88 1097006.3 204308.33 776264.4 950083.65 411734.42
## price_sold 515000.00 1937500.0 122000.00 620000.0 975000.00 385000.00
## CV residual 90511.12 840493.7 -82308.33 -156264.4 24916.35 -26734.42
## 315 319 339 342 379 388
## Predicted 375053.14 826036.7 463366.3 600001.7 426209.57 670067.7
## cvpred 373209.55 821224.7 461466.7 600134.0 430752.74 668490.8
## price_sold 387500.00 483100.0 314500.0 380000.0 449900.00 1075000.0
## CV residual 14290.45 -338124.7 -146966.7 -220134.0 19147.26 406509.2
## 412 428 431 435 439 449
## Predicted 178204.818 825604.7 93745.89 269060.6 261514.07 449667.1
## cvpred 177938.936 827953.5 87987.62 269843.4 262792.94 446779.7
## price_sold 183000.000 700000.0 55000.00 292900.0 207000.00 170000.0
## CV residual 5061.064 -127953.5 -32987.62 23056.6 -55792.94 -276779.7
## 470 473 482 487 489 494
## Predicted 394952.33 526391.3 276412.742 612605.2 616338.0 674108.4
## cvpred 400661.86 532194.7 276858.359 612552.3 617951.1 673024.8
## price_sold 312500.00 375000.0 280000.000 396000.0 350000.0 460000.0
## CV residual -88161.86 -157194.7 3141.641 -216552.3 -267951.1 -213024.8
## 504 515 525 531 548 571
## Predicted 462336.96 120250.90 103175.41 539938.5 194489.98 668776.5
## cvpred 466840.29 120662.97 106853.38 542399.0 207200.73 674543.8
## price_sold 455000.00 110111.00 180000.00 405000.0 225000.00 900000.0
## CV residual -11840.29 -10551.97 73146.62 -137399.0 17799.27 225456.2
## 578 579 590 594 598 600
## Predicted 538302.07 458710.5 359841.05 91362.54 246351.37 410733.2
## cvpred 536564.58 462929.1 351690.67 99540.29 250302.45 409707.3
## price_sold 487000.00 290000.0 270000.00 154000.00 229000.00 308500.0
## CV residual -49564.58 -172929.1 -81690.67 54459.71 -21302.45 -101207.3
## 605 608 609 610 612 617
## Predicted 206189.00 228734.38 540381.4 485671.9 140968.58 151014.91
## cvpred 212309.01 239624.03 541268.5 486901.2 136455.96 145243.09
## price_sold 237500.00 229600.00 260000.0 360000.0 175000.00 188000.00
## CV residual 25190.99 -10024.03 -281268.5 -126901.2 38544.04 42756.91
## 651 711 724 733 741 761
## Predicted 812229.33 246477.77 278914.97 410637.0 281655.40 488457.3
## cvpred 802901.85 240983.96 280591.92 417090.3 289265.37 492197.8
## price_sold 749900.00 218000.00 196250.00 190000.0 275000.00 282500.0
## CV residual -53001.85 -22983.96 -84341.92 -227090.3 -14265.37 -209697.8
## 772 783 792 812 827 836
## Predicted 311608.3 185668.0 185788.74 194417.889 61009.45 268637.87
## cvpred 317744.9 192576.3 183041.37 200730.013 66861.69 270830.14
## price_sold 172950.0 127000.0 249900.00 197500.000 165000.00 187500.00
## CV residual -144794.9 -65576.3 66858.63 -3230.013 98138.31 -83330.14
## 842 852 859 868 886 899
## Predicted 207975.6 231575.34 375947.6 244428.97 416617.7 77540.35
## cvpred 212928.6 230133.01 373941.1 248253.96 424543.8 78116.10
## price_sold 360000.0 195000.00 120000.0 196000.00 125000.0 61000.00
## CV residual 147071.4 -35133.01 -253941.1 -52253.96 -299543.8 -17116.10
## 919 929 936 938 943 945
## Predicted 124470.11 93592.24 378484.0 277692.2 93378.47 254159.9
## cvpred 126852.58 101607.63 390883.2 283118.7 95712.88 253224.3
## price_sold 185000.00 191600.00 230000.0 110000.0 140000.00 79900.0
## CV residual 58147.42 89992.37 -160883.2 -173118.7 44287.12 -173324.3
## 973 974 981 983 995 1036
## Predicted 224558.87 163235.1 347429.8 509191.6 372370.21 262325.1
## cvpred 217541.74 159420.1 353125.7 512790.6 374813.37 258533.7
## price_sold 250000.00 322400.0 575000.0 487600.0 410000.00 147500.0
## CV residual 32458.26 162979.9 221874.3 -25190.6 35186.63 -111033.7
## 1043 1055 1058 1072 1083 1086
## Predicted 263868.0122 422896.1 221594.65 174810.9 237896.0 191075.44
## cvpred 276442.1867 422607.4 228284.72 172613.8 241789.1 193706.15
## price_sold 276000.0000 700000.0 155000.00 357000.0 415000.0 149000.00
## CV residual -442.1867 277392.6 -73284.72 184386.2 173210.9 -44706.15
## 1101 1103 1109 1120 1123 1132
## Predicted 283679.6 299029.81 337519.60 84857.59 203509.52 231427.06
## cvpred 292974.9 296493.54 341696.99 83395.86 211082.95 226196.37
## price_sold 105000.0 260000.00 257000.00 200000.00 255000.00 150000.00
## CV residual -187974.9 -36493.54 -84696.99 116604.14 43917.05 -76196.37
## 1135 1137 1146 1153 1158 1161 1175
## Predicted 405155.9 283661.6 167691.5 361056.24 109993.22 169651.98 366615.8
## cvpred 406750.1 290761.7 169454.6 371880.45 111006.92 169933.43 369289.9
## price_sold 592000.0 187000.0 315000.0 325000.00 96000.00 227000.00 235000.0
## CV residual 185249.9 -103761.7 145545.4 -46880.45 -15006.92 57066.57 -134289.9
## 1226 1233 1238 1252 1253 1258
## Predicted 267629.30 323937.3 383005.97 265605.6 226287.5 517726.49
## cvpred 269789.24 332671.3 383594.49 265999.8 230328.6 520802.01
## price_sold 181900.00 145000.0 435000.00 50000.0 85000.0 590000.00
## CV residual -87889.24 -187671.3 51405.51 -215999.8 -145328.6 69197.99
## 1259 1270 1283 1290 1294 1306
## Predicted 209004.92 436620.4 217374.66 229342.169 202693.6 960796.9
## cvpred 212584.86 439294.7 223913.26 227328.661 205121.8 962485.2
## price_sold 140000.00 42500.0 195000.00 220000.000 150000.0 665000.0
## CV residual -72584.86 -396794.7 -28913.26 -7328.661 -55121.8 -297485.2
## 1312 1320 1327 1328 1332 1350
## Predicted 250564.91 206371.25 201438.23 201438.23 108261.26 322573.04
## cvpred 255520.18 209653.31 203917.96 203917.96 105545.23 324033.62
## price_sold 214000.00 307000.00 122000.00 122000.00 125000.00 290000.00
## CV residual -41520.18 97346.69 -81917.96 -81917.96 19454.77 -34033.62
## 1361
## Predicted 240224.62
## cvpred 242279.29
## price_sold 214000.00
## CV residual -28279.29
##
## Sum of squares = 5.195817e+12 Mean square = 38204536610 n = 136
##
## fold 9
## Observations in test set: 136
## 16 37 39 50 71 92 93
## Predicted 188658 255849.0 208160.73 529909.6 350846.4 635976.39 174576.3
## cvpred 191699 254455.3 209326.87 521789.0 349475.9 635060.01 179860.6
## price_sold 90000 551900.0 185000.00 769100.0 500000.0 675000.00 445000.0
## CV residual -101699 297444.7 -24326.87 247311.0 150524.1 39939.99 265139.4
## 98 109 110 118 126 128 131
## Predicted 1411783 433589.8 505428.98 401663.7 546387.5 301305.7 468924.8
## cvpred 1390578 428082.6 498457.24 391138.1 535410.1 300470.6 462664.5
## price_sold 2400000 67019.0 525000.00 629000.0 84123.0 490000.0 24000.0
## CV residual 1009422 -361063.6 26542.76 237861.9 -451287.1 189529.4 -438664.5
## 153 159 184 223 228 231
## Predicted 952148.70 614083.1 211301.72 393987.18 342833.17 495176.0
## cvpred 940555.94 608404.5 211346.48 390082.42 348468.38 490919.9
## price_sold 975000.00 415500.0 285000.00 358000.00 250000.00 837679.0
## CV residual 34444.06 -192904.5 73653.52 -32082.42 -98468.38 346759.1
## 282 283 287 289 293 326
## Predicted 897635.0 1426988.7 806249.1 298276.6 764312.7 497711.5
## cvpred 887905.1 1407367.5 798263.9 297611.1 759074.3 493117.4
## price_sold 565000.0 2350000.0 600000.0 178000.0 1125000.0 380000.0
## CV residual -322905.1 942632.5 -198263.9 -119611.1 365925.7 -113117.4
## 353 355 358 362 365 373
## Predicted 235227.329 472882.3 453685.77 409053.7 236296.96 227774.72
## cvpred 234142.747 471731.7 448414.98 404274.6 238812.86 228407.66
## price_sold 238000.000 322000.0 485000.00 545000.0 320000.00 255500.00
## CV residual 3857.253 -149731.7 36585.02 140725.4 81187.14 27092.34
## 383 384 393 405 410 424
## Predicted 421959.3 367118.83 210592.1 530181.02 568897.2 644178.5
## cvpred 416264.1 362356.53 211587.0 522690.92 564541.5 636074.6
## price_sold 255000.0 300000.00 135000.0 460000.00 208980.0 499000.0
## CV residual -161264.1 -62356.53 -76587.0 -62690.92 -355561.5 -137074.6
## 427 443 444 455 458 478
## Predicted 534773.5 292451.59 363809.88 362720.72 326117.7 188998.38
## cvpred 533591.2 292454.47 362906.77 359652.51 325611.6 184915.28
## price_sold 357500.0 215000.00 297000.00 325000.00 135000.0 174528.00
## CV residual -176091.2 -77454.47 -65906.77 -34652.51 -190611.6 -10387.28
## 479 486 488 491 502 508 524
## Predicted 605489.1 495723.6 495723.6 498901.59 149415.62 416092.62 423120.4
## cvpred 599495.2 492019.3 492019.3 492267.36 153897.24 408401.36 421375.3
## price_sold 394500.0 685000.0 685000.0 431000.00 175000.00 440000.00 211973.0
## CV residual -204995.2 192980.7 192980.7 -61267.36 21102.76 31598.64 -209402.3
## 534 537 551 559 563 572
## Predicted 426753.68 441272.79 221784.845 1116622.1 452528.4 561982.3
## cvpred 420348.96 438185.52 222111.284 1109462.4 448904.4 554610.6
## price_sold 440000.00 420000.00 225000.000 545000.0 249900.0 1285000.0
## CV residual 19651.04 -18185.52 2888.716 -564462.4 -199004.4 730389.4
## 601 602 616 625 633 646
## Predicted 266124.12 213909.2 116655.90 183666.58 560449.2 120272.45
## cvpred 266393.34 210953.2 122954.37 181761.59 551856.8 122320.55
## price_sold 195000.00 200000.0 109500.00 245900.00 379000.0 208000.00
## CV residual -71393.34 -10953.2 -13454.37 64138.41 -172856.8 85679.45
## 658 681 704 712 732 737 740
## Predicted 804483.6 67928.00 473463.0 577124.7 271623.75 283458.6 386807.8
## cvpred 790456.5 67438.95 466084.9 576510.0 274072.53 285852.8 382326.5
## price_sold 1432500.0 184000.00 815000.0 155000.0 229900.00 655000.0 200000.0
## CV residual 642043.5 116561.05 348915.1 -421510.0 -44172.53 369147.2 -182326.5
## 778 798 799 800 806 810
## Predicted 452601.6 261238.66 505987.8 433429.6 62121.60 391531.7
## cvpred 448145.9 262010.11 502373.1 429168.6 62211.96 391233.8
## price_sold 300000.0 224000.00 133000.0 310000.0 173900.00 263500.0
## CV residual -148145.9 -38010.11 -369373.1 -119168.6 111688.04 -127733.8
## 813 820 822 853 861 887
## Predicted 887284.31 215119.1 378874.3 228832.0463 225331.3 333460.53
## cvpred 879303.86 219379.5 380576.2 230678.5038 222599.2 332605.33
## price_sold 950000.00 80000.0 276000.0 230000.0000 89000.0 235000.00
## CV residual 70696.14 -139379.5 -104576.2 -678.5038 -133599.2 -97605.33
## 889 891 912 914 926 931
## Predicted 156673.21 336803.77 135794.498 93570.24 238566.749 280224.9
## cvpred 160242.88 335879.67 141956.208 92730.03 238692.935 284473.4
## price_sold 176500.00 283900.00 146000.000 175000.00 230000.000 176000.0
## CV residual 16257.12 -51979.67 4043.792 82269.97 -8692.935 -108473.4
## 932 946 957 967 969 970 1006
## Predicted 195732.4 125917.93 358178.8 205536.4 443463.4 137204.35 125639.23
## cvpred 198248.0 129410.72 354717.1 208275.0 441346.5 141420.87 132339.43
## price_sold 79000.0 200000.00 510000.0 333000.0 232000.0 200000.00 159000.00
## CV residual -119248.0 70589.28 155282.9 124725.0 -209346.5 58579.13 26660.57
## 1017 1021 1039 1045 1046 1051 1052
## Predicted 82059.05 245866.3 271397.93 401494.6 106711.0 294910.99 261604.931
## cvpred 82342.03 247718.5 272255.68 401613.4 114308.9 293983.35 265513.243
## price_sold 149900.00 467000.0 351000.00 565000.0 325000.0 310000.00 275000.000
## CV residual 67557.97 219281.5 78744.32 163386.6 210691.1 16016.65 9486.757
## 1053 1076 1078 1088 1096 1098 1102
## Predicted 77946.70 420260.21 322346.3 266299.3 369829.7 105352.45 389611.95
## cvpred 82657.44 419196.23 322792.5 264802.3 366802.6 108423.77 383914.94
## price_sold 180000.00 475000.00 461814.0 147400.0 555000.0 140000.00 465000.00
## CV residual 97342.56 55803.77 139021.5 -117402.3 188197.4 31576.23 81085.06
## 1118 1141 1147 1160 1162 1183
## Predicted 213503.37 113138.1 418376.5 261396.742 241276.30 342032.9
## cvpred 217595.93 119937.5 413173.1 267201.717 242890.92 337796.0
## price_sold 235000.00 320000.0 290000.0 270000.000 339000.00 50013.0
## CV residual 17404.07 200062.5 -123173.1 2798.283 96109.08 -287783.0
## 1194 1212 1223 1227 1230 1242
## Predicted 278529.9 114517.3 183702.7 189287.450 460921.10 344203.13
## cvpred 285025.0 122188.6 187462.2 195014.803 456246.59 347883.85
## price_sold 13233.0 250000.0 370000.0 197400.000 535000.00 385000.00
## CV residual -271792.0 127811.4 182537.8 2385.197 78753.41 37116.15
## 1245 1248 1251 1256 1257 1267
## Predicted 226327.5 115735.94 517726.49 308649.62 517726.49 561367.33
## cvpred 230910.6 124183.96 512405.48 308849.15 512405.47 555595.83
## price_sold 70000.0 27886.00 590000.00 350000.00 590000.00 560200.00
## CV residual -160910.6 -96297.96 77594.52 41150.85 77594.53 4604.17
## 1273 1281 1288 1298 1309 1330
## Predicted 262123.55 220676.74 249523.1 375823.3 335360.1 250563.62
## cvpred 260777.05 220571.03 256715.9 370134.3 339365.3 252968.12
## price_sold 200000.00 168000.00 109000.0 1059162.0 516116.0 214000.00
## CV residual -60777.05 -52571.03 -147715.9 689027.7 176750.7 -38968.12
## 1342 1355 1357
## Predicted 439724.32 232328.81 314752.80
## cvpred 436184.61 233153.56 319583.54
## price_sold 425500.00 245000.00 280000.00
## CV residual -10684.61 11846.44 -39583.54
##
## Sum of squares = 7.055997e+12 Mean square = 51882327825 n = 136
##
## fold 10
## Observations in test set: 136
## 2 3 6 14 15 30
## Predicted 277102.57 89801.146 449624.9 157035.03 157035.03 89801.146
## cvpred 279135.82 93103.817 450409.7 160255.52 160255.52 93103.817
## price_sold 339900.00 90000.000 170000.0 179000.00 200000.00 90000.000
## CV residual 60764.18 -3103.817 -280409.7 18744.48 39744.48 -3103.817
## 40 46 49 66 67 72 97
## Predicted 221111.6 306081.07 306426.57 370763.35 433000.58 825602.7 470122.3
## cvpred 222149.3 307141.86 306347.44 377084.17 437869.78 828127.2 467072.5
## price_sold 353000.0 250000.00 285000.00 392875.00 520000.00 540000.0 525000.0
## CV residual 130850.7 -57141.86 -21347.44 15790.83 82130.22 -288127.2 57927.5
## 101 113 116 119 123 124
## Predicted 351925.12 323151.0 415479.6 340272.8 347958.7 379240.173
## cvpred 351026.24 323709.8 413537.4 340611.7 348488.5 377894.752
## price_sold 450000.00 205000.0 63497.0 55605.0 223000.0 382750.000
## CV residual 98973.76 -118709.8 -350040.4 -285006.7 -125488.5 4855.248
## 129 132 143 147 150 170
## Predicted 297378.8 600033.5 394715.5 238784.23 336374.3 106909.70
## cvpred 297931.4 597605.2 393390.4 241987.92 338815.3 109007.31
## price_sold 167500.0 390000.0 355000.0 325000.00 193000.0 93765.00
## CV residual -130431.4 -207605.2 -38390.4 83012.08 -145815.3 -15242.31
## 171 179 185 186 196 202
## Predicted 809316.3 297910.4 190518.54 336272.70 279258.6 481758.2
## cvpred 805664.6 298641.1 190153.21 336950.88 280772.6 481437.5
## price_sold 528400.0 108500.0 279000.00 350000.00 515000.0 297000.0
## CV residual -277264.6 -190141.1 88846.79 13049.12 234227.4 -184437.5
## 226 236 255 266 270 274
## Predicted 752610.31 1307304.9 529101.3 341013.72 271827.1 503023.2
## cvpred 747771.96 1301168.3 529207.9 343315.18 273826.0 500738.1
## price_sold 792000.00 1900000.0 170000.0 276000.00 140000.0 983750.0
## CV residual 44228.04 598831.7 -359207.9 -67315.18 -133826.0 483011.9
## 292 299 305 324 327 357
## Predicted 611671.5 351171.7 709457.94 105428.50 236541.68 237265.05
## cvpred 610802.7 353549.4 705921.58 105142.28 237851.54 238117.31
## price_sold 325500.0 224000.0 728000.00 202500.00 225000.00 269300.00
## CV residual -285302.7 -129549.4 22078.42 97357.72 -12851.54 31182.69
## 364 366 402 422 438 456 483
## Predicted 745234.51 879688.0 804733.8 644178.5 197126.3 794386.8 358506.7
## cvpred 742371.16 876847.5 801127.6 640803.5 200706.1 791733.6 357704.0
## price_sold 800000.00 1425000.0 1305000.0 499000.0 50000.0 980000.0 500000.0
## CV residual 57628.84 548152.5 503872.4 -141803.5 -150706.1 188266.4 142296.0
## 498 503 513 520 536 543
## Predicted 568668.6 399224.56 403534.0 200007.34 458803.16 428111.22
## cvpred 564643.7 398330.42 402467.3 200241.96 458745.12 425529.58
## price_sold 415000.0 325000.00 168000.0 265000.00 555000.00 407500.00
## CV residual -149643.7 -73330.42 -234467.3 64758.04 96254.88 -18029.58
## 547 560 577 621 640 641 659
## Predicted 292195.5 418419.6 475061.1 352018.1 257614.23 501098.0 804483.6
## cvpred 292470.4 416684.7 474070.6 352799.1 259871.88 497643.1 797935.3
## price_sold 454500.0 290000.0 717000.0 435000.0 160100.00 350000.0 1430000.0
## CV residual 162029.6 -126684.7 242929.4 82200.9 -99771.88 -147643.1 632064.7
## 661 670 687 692 693 698 714
## Predicted 88177.53 130102.9 238937.61 413682.2 451123.48 227267.4 244419.73
## cvpred 91516.02 131665.1 240304.97 414916.7 446358.05 228889.1 245167.38
## price_sold 173000.00 248000.0 259900.00 161975.0 415000.00 318900.0 262000.00
## CV residual 81483.98 116334.9 19595.03 -252941.7 -31358.05 90010.9 16832.62
## 721 725 728 746 748 779
## Predicted 242577.2 277763.572 73988.30 747522.2 473040.99 73907.41
## cvpred 246069.6 280172.597 77943.22 745769.8 474283.45 73758.85
## price_sold 97000.0 286000.000 200100.00 1025000.0 395000.00 104900.00
## CV residual -149069.6 5827.403 122156.78 279230.2 -79283.45 31141.15
## 815 819 823 825 828 832 833
## Predicted 573497.9 655415.7 385175.1 275060.23 206449.74 278041.2 325525.8
## cvpred 575982.6 652164.6 382528.8 276451.72 207180.22 279218.9 328847.6
## price_sold 300000.0 385000.0 360000.0 255000.00 220000.00 450000.0 589000.0
## CV residual -275982.6 -267164.6 -22528.8 -21451.72 12819.78 170781.1 260152.4
## 840 845 855 862 875 882
## Predicted 158649.82 187909.70 357619.542 219353.47 67677.51 455683.33
## cvpred 161339.43 189082.18 360239.227 220805.21 69390.52 457761.32
## price_sold 125000.00 220000.00 365000.000 202000.00 155100.00 430000.00
## CV residual -36339.43 30917.82 4760.773 -18805.21 85709.48 -27761.32
## 909 918 937 941 942 947 953
## Predicted 268314.23 380734.9 198072.6 269632.47 288635.87 215919.53 385169.70
## cvpred 271119.97 381161.6 199680.1 268961.64 290524.75 218292.86 382522.69
## price_sold 290000.00 584900.0 360000.0 320500.00 192000.00 200000.00 360000.00
## CV residual 18880.03 203738.4 160319.9 51538.36 -98524.75 -18292.86 -22522.69
## 962 966 972 979 987 997
## Predicted 158573.49 240953.2 197743.104 262467.0 298356.32 294059.1
## cvpred 160394.76 242690.8 200034.401 263643.1 301033.91 295306.7
## price_sold 202000.00 500000.0 194000.000 384000.0 250000.00 164000.0
## CV residual 41605.24 257309.2 -6034.401 120356.9 -51033.91 -131306.7
## 1000 1009 1020 1027 1040 1048 1062
## Predicted 124903.01 400022.2 138897.9 179076.8 436816.1 371545.72 328213.4
## cvpred 129109.65 401880.3 141512.5 180501.6 435724.8 369454.28 330294.4
## price_sold 91000.00 560000.0 457500.0 71050.0 305000.0 319900.00 130500.0
## CV residual -38109.65 158119.7 315987.5 -109451.6 -130724.8 -49554.28 -199794.4
## 1068 1073 1106 1112 1129 1130
## Predicted 362879.9 250103.04 344874.3 69591.24 214857.53 199497.79
## cvpred 364877.8 253313.06 347067.6 70733.79 219265.99 203382.79
## price_sold 690000.0 190000.00 190600.0 32000.00 180000.00 180000.00
## CV residual 325122.2 -63313.06 -156467.6 -38733.79 -39265.99 -23382.79
## 1149 1155 1156 1172 1193 1201
## Predicted 238534.86 394246.6 482927.09 95208.81 279460.6 476477.7
## cvpred 239088.85 387899.6 481176.09 100699.21 281369.9 476461.8
## price_sold 282000.00 253000.0 402000.00 90000.00 67000.0 560000.0
## CV residual 42911.15 -134899.6 -79176.09 -10699.21 -214369.9 83538.2
## 1203 1216 1221 1231 1246 1250 1261
## Predicted 431700.45 265310.29 553480.0 483713.9 228917.9 210595.5 230490.6
## cvpred 431909.71 266077.36 557514.6 484957.0 229845.9 215905.3 235131.1
## price_sold 389000.00 339000.00 110000.0 750000.0 372000.0 10000.0 275000.0
## CV residual -42909.71 72922.64 -447514.6 265043.0 142154.1 -205905.3 39868.9
## 1262 1289 1295 1311 1329 1338
## Predicted 367075.9 312032.1 508693.9 265924.64 265923.35 311381.9
## cvpred 368449.2 311734.1 505520.5 269155.63 269154.17 313126.7
## price_sold 85000.0 165000.0 370000.0 214000.00 214000.00 190000.0
## CV residual -283449.2 -146734.1 -135520.5 -55155.63 -55154.17 -123126.7
## 1344 1363
## Predicted 248912.56 287446.8
## cvpred 250568.06 287841.4
## price_sold 223000.00 170000.0
## CV residual -27568.06 -117841.4
##
## Sum of squares = 4.457074e+12 Mean square = 32772601952 n = 136
##
## Overall (Sum over all 136 folds)
## ms
## 32670105154
# MSPE
n2 = dim(clean_housing)[1]
MSPE2 <- sum((clean_housing$price_sold - KCV2$cvpred)^2) / n2
MSPE2
## [1] 32670105154
# Press Statistic
PRESS2 <- sum((clean_housing$price_sold - KCV2$cvpred)^2)
PRESS2
## [1] 4.462736e+13
# Prediction R-Squared
PRS2 <- 1 - sum((clean_housing$price_sold - KCV2$cvpred)^2) / sum((clean_housing$price_sold -
mean(clean_housing$price_sold))^2)
PRS2
## [1] 0.6187243
Model 3:
# K-fold
KCV3 = cv.lm(data = clean_housing, housing_model3, m = 10, seed = 0)
##
## fold 1
## Observations in test set: 136
## 4 7 12 34 42 55
## Predicted 207343.93 567333.9 374565.53 349224.0 256725.27 272248.9
## cvpred 201810.34 573606.5 372682.26 346047.6 252012.12 267793.7
## price_sold 178000.00 275000.0 399000.00 1050000.0 235000.00 417000.0
## CV residual -23810.34 -298606.5 26317.74 703952.4 -17012.12 149206.3
## 62 74 80 115 122 136
## Predicted 371874.59 321095.0 452973.1 551007.3 249023.4 377034.40
## cvpred 371115.17 317451.3 456473.7 557008.7 246222.9 377232.72
## price_sold 289000.00 685000.0 625000.0 254900.0 92500.0 291500.00
## CV residual -82115.17 367548.7 168526.3 -302108.7 -153722.9 -85732.72
## 151 177 182 187 195 214
## Predicted 2044790.25 570753.97 294791.5 529193.82 471976.2 862745.2
## cvpred 2082010.69 577955.45 292751.4 534832.79 475792.5 875966.5
## price_sold 2000000.00 566000.00 440000.0 570000.00 398000.0 740000.0
## CV residual -82010.69 -11955.45 147248.6 35167.21 -77792.5 -135966.5
## 216 261 268 279 281 290
## Predicted 527914.94 1012450.2 240191.015 758094.2 126365.5 514933.9
## cvpred 532660.64 1027862.2 237243.746 769576.8 120655.1 519464.0
## price_sold 572500.00 1237500.0 244800.000 1400000.0 476000.0 710000.0
## CV residual 39839.36 209637.8 7556.254 630423.2 355344.9 190536.0
## 296 301 303 304 313 323
## Predicted 1493684.7 436646.4 330414.7 1158291.0 470577.9 195225.89
## cvpred 1520004.8 439875.8 328966.4 1181375.8 472330.4 191531.55
## price_sold 1025000.0 255000.0 605000.0 518535.0 365000.0 235000.00
## CV residual -495004.8 -184875.8 276033.6 -662840.8 -107330.4 43468.45
## 337 344 348 350 360 371
## Predicted 405599.1 201857.11 661814.17 438520.0 454846.6 769603.1
## cvpred 408312.6 196232.36 669656.56 441780.4 458378.3 781277.0
## price_sold 256000.0 159000.00 590000.00 265000.0 300000.0 525000.0
## CV residual -152312.6 -37232.36 -79656.56 -176780.4 -158378.3 -256277.0
## 380 387 389 390 394 398 406
## Predicted 345853.23 288903.23 412037.1 685561.2 123569.0 398253.2 403993.20
## cvpred 345533.49 286765.29 413689.0 695838.7 113730.9 399676.1 406680.01
## price_sold 308000.00 225000.00 245000.0 999000.0 292000.0 180000.0 330000.00
## CV residual -37533.49 -61765.29 -168689.0 303161.3 178269.1 -219676.1 -76680.01
## 417 419 445 450 459 465
## Predicted 698616.0 539438.31 509982.416 95391.952 1086574.7 98529.94
## cvpred 707069.8 543206.91 514430.184 87126.326 1104386.8 92357.03
## price_sold 560000.0 587500.00 522375.000 81500.000 799900.0 150000.00
## CV residual -147069.8 44293.09 7944.816 -5626.326 -304486.8 57642.97
## 468 476 485 510 512 527
## Predicted 328040.1 521030.5 347592.95 656996.5 565995.64 333675.17
## cvpred 328593.0 526533.9 347302.12 664758.8 572246.05 333153.11
## price_sold 466400.0 375000.0 265000.00 450000.0 489900.00 272000.00
## CV residual 137807.0 -151533.9 -82302.12 -214758.8 -82346.05 -61153.11
## 532 542 558 565 568 582
## Predicted 405866.74 794181.3 314329.94 716534.72 327251.58 71303.49
## cvpred 408584.69 803054.3 312614.45 729367.42 326622.79 62637.65
## price_sold 347000.00 1058756.0 360000.00 655000.00 375000.00 110000.00
## CV residual -61584.69 255701.7 47385.55 -74367.42 48377.21 47362.35
## 603 607 614 619 620 623
## Predicted 358626.60 231210.967 148594.19 428884.6 129175.81 272770.453
## cvpred 360559.67 232195.668 139171.91 431985.0 123512.07 272405.058
## price_sold 329000.00 229600.000 188000.00 225000.0 95500.00 270000.000
## CV residual -31559.67 -2595.668 48828.09 -206985.0 -28012.07 -2405.058
## 626 630 637 642 652 668 674
## Predicted 636387.5 433434.6 416171.3 361704.57 553074.7 281409.04 450370.4
## cvpred 643807.4 436610.6 419060.4 363688.78 561151.0 279146.59 451787.1
## price_sold 246000.0 270000.0 383000.0 325000.00 310000.0 343000.00 577000.0
## CV residual -397807.4 -166610.6 -36060.4 -38688.78 -251151.0 63853.41 125212.9
## 676 680 682 694 696 705
## Predicted 180698.35 80523.61 132789.08 418545.84 484495.69 468482.9
## cvpred 175890.63 76092.13 127185.37 419433.86 486479.43 476322.4
## price_sold 130000.00 175000.00 140000.00 324900.00 440000.00 815000.0
## CV residual -45890.63 98907.87 12814.63 -94533.86 -46479.43 338677.6
## 715 719 743 749 771 839
## Predicted 371606.9 446817.1 135137.9 195225.89 339028.16 95391.95
## cvpred 370843.1 450215.4 127532.6 191531.55 338595.03 87126.33
## price_sold 150000.0 275000.0 295000.0 230000.00 263000.00 60000.00
## CV residual -220843.1 -175215.4 167467.4 38468.45 -75595.03 -27126.33
## 864 867 877 879 900 903 910
## Predicted 97593.17 187196.40 565727.99 244205.8 342106.13 344648.80 233499.8
## cvpred 91404.70 183368.66 571973.95 241325.2 341724.14 344309.06 230441.3
## price_sold 207500.00 267500.00 625000.00 511000.0 299900.00 380000.00 382000.0
## CV residual 116095.30 84131.34 53026.05 269674.8 -41824.14 35690.94 151558.7
## 916 917 920 934 948 960
## Predicted 184178.5 227343.84 304694.555 191999.65 107556.2 471173.23
## cvpred 182341.2 224183.12 302818.978 189420.28 103573.9 474976.21
## price_sold 396300.0 256000.00 295000.000 155000.00 234900.0 560000.00
## CV residual 213958.8 31816.88 -7818.978 -34420.28 131326.1 85023.79
## 965 968 990 992 1008 1064 1070
## Predicted 452511.6 245008.7 341497.0 128848.14 258391.2 296739.5 81474.18
## cvpred 453963.9 242141.5 343145.5 121138.38 255746.3 295603.8 72977.31
## price_sold 232000.0 500000.0 210000.0 170000.00 222000.0 215000.0 88000.00
## CV residual -221963.9 257858.5 -133145.5 48861.62 -33746.3 -80603.8 15022.69
## 1071 1074 1084 1090 1092 1094 1124
## Predicted 81474.18 362046.0 65341.40 276859.00 238049.82 289097.1 215091.98
## cvpred 72977.31 361995.3 58617.08 274520.95 235066.97 289002.9 213768.28
## price_sold 88000.00 565000.0 155000.00 221500.00 250000.00 454500.0 256000.00
## CV residual 15022.69 203004.7 96382.92 -53020.95 14933.03 165497.1 42231.72
## 1139 1140 1144 1145 1170 1179
## Predicted 220920.25 120015.71 662885.4 326299.70 198973.0 356826.9
## cvpred 217652.81 112159.19 673658.2 323911.07 195340.9 356689.4
## price_sold 284000.00 189900.00 1240000.0 350000.00 325000.0 235000.0
## CV residual 66347.19 77740.81 566341.8 26088.93 129659.1 -121689.4
## 1185 1191 1213 1219 1255 1271
## Predicted 181487.51 262138.3 274911.6 203329.18 389077.97 311178.2
## cvpred 180774.07 259555.7 274581.8 197728.89 386563.79 311450.9
## price_sold 152500.00 429000.0 76000.0 165000.00 313000.00 125000.0
## CV residual -28274.07 169444.3 -198581.8 -32728.89 -73563.79 -186450.9
## 1278 1282 1291 1305 1313 1315
## Predicted 244205.758 212414.8 214035.17 251953.8 296739.5 254450.2
## cvpred 241325.192 208134.1 208612.75 253283.1 295603.8 249699.3
## price_sold 242394.000 45000.0 220000.00 150000.0 186500.0 230000.0
## CV residual 1068.808 -163134.1 11387.25 -103283.1 -109103.8 -19699.3
## 1336 1343 1345 1358 1359
## Predicted 298612.4 316010.30 254450.2 302285.71 188802.30
## cvpred 294595.2 315194.74 249699.3 300370.11 185001.24
## price_sold 425000.0 219000.00 189000.0 280000.00 175000.00
## CV residual 130404.8 -96194.74 -60699.3 -20370.11 -10001.24
##
## Sum of squares = 4.58725e+12 Mean square = 33729782160 n = 136
##
## fold 2
## Observations in test set: 137
## 5 8 9 11 21 23 27
## Predicted 370075.5 553757.6 247076.10 294121.74 260070.9 66559.61 127971.4
## cvpred 372306.6 559330.9 247943.38 286824.39 256651.1 57694.27 123210.1
## price_sold 269900.0 680000.0 233000.00 341000.00 403000.0 110000.00 317500.0
## CV residual -102406.6 120669.1 -14943.38 54175.61 146348.9 52305.73 194289.9
## 70 82 88 89 102 108 112
## Predicted 371607.6 233901.3 298672.4 641740.46 628893.3 293527.7 237246.87
## cvpred 375962.5 232673.4 297285.3 649224.97 636409.4 295947.1 236010.77
## price_sold 185000.0 450000.0 530000.0 670000.00 245000.0 133000.0 188500.00
## CV residual -190962.5 217326.6 232714.7 20775.03 -391409.4 -162947.1 -47510.77
## 127 145 149 154 155 167 173
## Predicted 686899.4 166988.2 323430.02 542709.5 568062.4 357361.50 1193574.5
## cvpred 696400.4 160003.5 321982.01 544516.1 571934.2 353702.49 1203495.9
## price_sold 110000.0 335000.0 415000.00 425000.0 853000.0 410000.00 980000.0
## CV residual -586400.4 174996.5 93017.99 -119516.1 281065.8 56297.51 -223495.9
## 175 197 201 207 209 232 239
## Predicted 272308.96 137606.8 892454.9 510665.99 501759.1 435709.7 687643.014
## cvpred 270986.65 132821.8 907371.9 516345.26 503666.4 439907.0 700936.061
## price_sold 241000.00 290000.0 640000.0 426500.00 750000.0 950000.0 695000.000
## CV residual -29986.65 157178.2 -267371.9 -89845.26 246333.6 510093.0 -5936.061
## 246 256 260 271 275 284
## Predicted 425137.5 243402.8 487867.7 553416.11 358760.423 793839.9
## cvpred 429360.8 242151.6 495730.6 561117.81 363146.932 804744.2
## price_sold 515000.0 19330.0 315700.0 515000.00 355000.000 490000.0
## CV residual 85639.2 -222821.6 -180030.6 -46117.81 -8146.932 -314744.2
## 285 288 291 298 302 307
## Predicted 542234.8 486845.178 514933.9 375354.7 897747.9 393688.69
## cvpred 552091.6 492583.027 518936.4 379700.4 910524.3 397989.31
## price_sold 675000.0 484000.000 710000.0 255500.0 650000.0 325000.00
## CV residual 122908.4 -8583.027 191063.6 -124200.4 -260524.3 -72989.31
## 317 318 329 343 374 395 397
## Predicted 223596.74 192817.0 399736.57 668505.4 569400.62 123569.0 1206154.6
## cvpred 222394.21 191690.2 404022.32 675924.1 573269.16 114563.4 1221966.5
## price_sold 290000.00 202000.0 430000.00 1075000.0 500000.00 292000.0 999000.0
## CV residual 67605.79 10309.8 25977.68 399075.9 -73269.16 177436.6 -222966.5
## 408 413 429 442 451 464
## Predicted 129577.3 186988.1145 273647.2 275520.75 396840.46 607213.01
## cvpred 124812.1 182081.7534 272321.6 274190.54 399005.78 608861.02
## price_sold 193900.0 183000.0000 170000.0 287500.00 320000.00 520000.00
## CV residual 69087.9 918.2466 -102321.6 13309.46 -79005.78 -88861.02
## 466 471 480 507 523 538
## Predicted 246942.27 213887.5529 473582.08 407606.46 614172.6 466697.7
## cvpred 247809.89 214836.4509 477686.24 411872.86 621724.9 474612.6
## price_sold 187500.00 215000.0000 427000.00 381300.00 420000.0 595000.0
## CV residual -60309.89 163.5491 -50686.24 -30572.86 -201724.9 120387.4
## 552 575 589 618 635 638
## Predicted 222526.145 507707.39 200846.53 216637.85 258317.38 521833.46
## cvpred 221326.248 511727.65 199699.94 215452.44 259157.02 529612.83
## price_sold 225000.000 532000.00 175000.00 266000.00 190000.00 449000.00
## CV residual 3673.752 20272.35 -24699.94 50547.56 -69157.02 -80612.83
## 648 657 700 713 720 727
## Predicted 458935.16 426341.9 340560.25 236979.22 526235.2 72374.09
## cvpred 460947.79 430562.3 344991.52 235743.78 532337.5 65622.01
## price_sold 390000.00 700000.0 395000.00 144500.00 38500.0 200100.00
## CV residual -70947.79 269437.7 50008.48 -91243.78 -493837.5 134477.99
## 731 735 751 775 777 789
## Predicted 393019.56 147242.16 195225.89 196564.139 525580.6 396499.0
## cvpred 397321.83 142433.53 194093.13 195428.082 533350.7 400792.7
## price_sold 460000.00 126000.00 230000.00 199900.000 314500.0 270000.0
## CV residual 62678.17 -16433.53 35906.87 4471.918 -218850.7 -130792.7
## 790 796 802 805 811 830
## Predicted 342433.1 436051.78 219508.1933 502428.2 129577.3 330657.22
## cvpred 340938.4 444042.08 220443.2703 504333.9 124812.1 335112.84
## price_sold 210000.0 369415.00 220000.0000 637000.0 265000.0 265000.00
## CV residual -130938.4 -74627.08 -443.2703 132666.1 140187.9 -70112.84
## 835 838 846 847 850 854 865
## Predicted 251699.95 349526.5 243670.5 225470.3 316517.4 74782.94 97593.17
## cvpred 250428.31 353935.7 242418.6 224263.2 321469.0 68024.93 92906.63
## price_sold 230000.00 459900.0 128000.0 379000.0 172000.0 120000.00 207500.00
## CV residual -20428.31 105964.3 -114418.6 154736.8 -149469.0 51975.07 114593.37
## 872 880 884 894 897 940
## Predicted 342373.78 131330.80 563988.265 159434.66 421999.52 189664.6
## cvpred 344673.03 122306.19 571663.973 156262.35 424102.97 184751.7
## price_sold 275000.00 100000.00 575000.000 176500.00 350000.00 310000.0
## CV residual -69673.03 -22306.19 3336.027 20237.65 -74102.97 125248.3
## 958 963 977 996 1001 1002
## Predicted 223596.7 298672.4 183523.12 295059.2 306628.12 361169.3
## cvpred 222394.2 297285.3 180291.58 293680.9 307348.97 365549.9
## price_sold 121500.0 420000.0 134900.00 164000.0 280000.00 262500.0
## CV residual -100894.2 122714.7 -45391.58 -129680.9 -27348.97 -103049.9
## 1003 1005 1012 1014 1016 1028 1030
## Predicted 155673.12 96924.042 360633.97 231224.8 275714.6 242733.7 472779.1
## cvpred 150843.76 92239.148 365015.87 230003.5 276511.5 241484.1 476885.3
## price_sold 135000.00 90000.000 450000.00 355000.0 135000.0 190000.0 333850.0
## CV residual -15843.76 -2239.148 84984.13 124996.5 -141511.5 -51484.1 -143035.3
## 1097 1114 1115 1117 1127 1134
## Predicted 211344.88 502428.87 92300.19 422133.3 93116.93 244011.92
## cvpred 212300.03 510255.95 89754.22 424236.5 86313.84 240631.63
## price_sold 145000.00 485000.00 213000.00 160000.0 158000.00 300000.00
## CV residual -67300.03 -25255.95 123245.78 -264236.5 71686.16 59368.37
## 1154 1157 1159 1169 1181 1187 1188
## Predicted 115064.19 224473.5 144371.8 192549.4 94053.70 337154.6 389614.6
## cvpred 108207.14 221141.3 137442.7 191423.2 87248.31 339466.7 397719.1
## price_sold 40000.00 60000.0 55000.0 320000.0 277000.00 420000.0 225000.0
## CV residual -68207.14 -161141.3 -82442.7 128576.8 189751.69 80533.3 -172719.1
## 1197 1211 1218 1220 1234 1235 1263
## Predicted 187002.56 226882.3 233232.1 203329.18 105830.28 395963.1 386937.4
## cvpred 183762.46 223544.2 232005.9 200048.94 98995.94 394336.7 389127.1
## price_sold 230000.00 86000.0 435000.0 165000.00 58500.00 190000.0 374900.0
## CV residual 46237.54 -137544.2 202994.1 -35048.94 -40495.94 -204336.7 -14227.1
## 1264 1272 1274 1299 1308 1325
## Predicted 222526.145 271699.85 98396.11 88968.36 318879.98 125904.00
## cvpred 221326.248 272506.59 93707.60 82175.48 317443.15 119020.29
## price_sold 225000.000 200000.00 162000.00 131000.00 229000.00 131000.00
## CV residual 3673.752 -72506.59 68292.40 48824.52 -88443.15 11979.71
## 1333 1353
## Predicted 181114.27 223536.72
## cvpred 177888.65 220206.79
## price_sold 90000.00 245900.00
## CV residual -87888.65 25693.21
##
## Sum of squares = 3.137126e+12 Mean square = 22898730858 n = 137
##
## fold 3
## Observations in test set: 137
## 19 22 28 32 38 45
## Predicted 316010.3 211298.65 372410.5 254450.25 261469.15 188876.11
## cvpred 322088.4 213433.89 376159.2 254897.96 261979.91 192500.77
## price_sold 219000.0 173000.00 120000.0 230000.00 292000.00 130000.00
## CV residual -103088.4 -40433.89 -256159.2 -24897.96 30020.09 -62500.77
## 47 60 84 87 106 120
## Predicted 352678.3 398253.2 557237.7 992094.4 675524.32 497745.0
## cvpred 356979.9 408556.5 568451.3 982643.1 673200.52 503631.2
## price_sold 200000.0 180000.0 218900.0 700000.0 615000.00 362500.0
## CV residual -156979.9 -228556.5 -349551.3 -282643.1 -58200.52 -141131.2
## 142 146 172 178 188 194
## Predicted 262212.1 139212.67 524569.316 1120105.3 388201.9 1448244.32
## cvpred 262283.7 137436.78 520946.175 1112661.9 391185.5 1433515.95
## price_sold 140000.0 225000.00 525000.000 1609000.0 280000.0 1501960.00
## CV residual -122283.7 87563.22 4053.825 496338.1 -111185.5 68444.05
## 204 218 221 224 237 238
## Predicted 411695.0 386134.5 1098812.7 891130.5 1302849.9 815653.30
## cvpred 413137.3 388815.2 1084594.2 886167.6 1286149.7 814347.16
## price_sold 834900.0 287400.0 1800000.0 1350000.0 1650000.0 792500.00
## CV residual 421762.7 -101415.2 715405.8 463832.4 363850.3 -21847.16
## 314 322 331 332 354 368 376
## Predicted 470577.9 355354.8 505432.4 462073.1 107971.5 549862.857 226674.7
## cvpred 469167.5 359526.7 502736.4 461477.8 107306.1 553627.139 228871.2
## price_sold 365000.0 387500.0 349900.0 873500.0 275000.0 550000.000 200000.0
## CV residual -104167.5 27973.3 -152836.4 412022.2 167693.9 -3627.139 -28871.2
## 378 381 399 400 401 407
## Predicted 1147806 248755.8004 274777.82 633637.2 537148.845 668030.1
## cvpred 1130408 249882.4934 275046.89 633342.7 532916.247 666069.4
## price_sold 1324000 250000.0000 200000.00 1200000.0 524900.000 475000.0
## CV residual 193592 117.5066 -75046.89 566657.3 -8016.247 -191069.4
## 409 415 418 434 440 447
## Predicted 840410.9 261409.79 388469.52 877272.7 262807.40 169531.5
## cvpred 837905.3 270133.18 391440.18 873384.3 263253.32 174496.5
## price_sold 690000.0 235000.00 330000.00 565000.0 207000.00 63000.0
## CV residual -147905.3 -35133.18 -61440.18 -308384.3 -56253.32 -111496.5
## 448 453 457 462 463 490 505
## Predicted 634707.10 447620.07 550264.3 563319.1 563319.1 261469.2 401852.0
## cvpred 625747.98 447724.99 554009.2 566028.4 566028.4 261979.9 404174.3
## price_sold 669000.00 499900.00 215000.0 520000.0 520000.0 129900.0 559000.0
## CV residual 43252.02 52175.01 -339009.2 -46028.4 -46028.4 -132079.9 154825.7
## 509 517 533 539 555 562
## Predicted 358225.12 453849.8 738897.2 575021.3 242283.51 715878.1
## cvpred 362661.07 453249.8 733100.0 568953.8 235514.02 693970.4
## price_sold 320000.00 254000.0 410000.0 399000.0 180000.00 600000.0
## CV residual -42661.07 -199249.8 -323100.0 -169953.8 -55514.02 -93970.4
## 581 588 595 606 615 622
## Predicted 364187.2 344916.45 612372.81 359028.07 373748.80 122083.10
## cvpred 367931.2 349594.09 612302.41 363425.12 377432.65 121137.11
## price_sold 200000.0 282000.00 550000.00 325000.00 331000.00 146500.00
## CV residual -167931.2 -67594.09 -62302.41 -38425.12 -46432.65 25362.89
## 632 643 650 656 663 673
## Predicted 272770.453 225871.76 808084.65 229485.0 554545.4 712399.9
## cvpred 273136.772 228107.15 798935.44 231545.4 540857.1 707886.5
## price_sold 270000.000 315000.00 749900.00 380000.0 300000.0 319000.0
## CV residual -3136.772 86892.85 -49035.44 148454.6 -240857.1 -388886.5
## 675 678 702 717 739 744
## Predicted 404528.50 313066.16 235373.32 183523.12 220518.8 252502.894
## cvpred 406721.12 319286.88 237148.37 187407.13 223013.5 253448.047
## price_sold 365000.00 360000.00 140000.00 116500.00 292000.0 250000.000
## CV residual -41721.12 40713.12 -97148.37 -70907.13 68986.5 -3448.047
## 754 757 767 769 776 780
## Predicted 179434.57 203864.48 521819.01 265885.37 394491.6 223924.411
## cvpred 183919.75 206762.99 518732.21 266182.17 397170.5 226657.235
## price_sold 170000.00 227500.00 490000.00 174900.00 267000.0 223000.000
## CV residual -13919.75 20737.01 -28732.21 -91282.17 -130170.5 -3657.235
## 793 801 829 831 869 881
## Predicted 565653.5 109175.90 387860.4 330657.22 186185.82 297542.5
## cvpred 560039.9 108452.15 391263.7 336428.78 190747.02 304515.3
## price_sold 451000.0 68000.00 276000.0 265000.00 215000.00 381000.0
## CV residual -109039.9 -40452.15 -115263.7 -71428.78 24252.98 76484.7
## 888 895 896 901 905 927
## Predicted 597845.933 225202.64 225202.64 486235.4 282747.3 205798.05
## cvpred 598882.424 227470.44 227470.44 484066.4 282227.2 209005.97
## price_sold 605000.000 189000.00 189000.00 375000.0 130000.0 197000.00
## CV residual 6117.576 -38470.44 -38470.44 -109066.4 -152227.2 -12005.97
## 933 950 951 956 975 986
## Predicted 341630.85 96254.92 202318.6 115124.21 87422.48 394759.3
## cvpred 346870.76 96560.26 205695.1 114515.37 88155.74 397425.2
## price_sold 270000.00 85000.00 240300.0 180000.00 260000.00 260000.0
## CV residual -76870.76 -11560.26 34604.9 65484.63 171844.26 -137425.2
## 999 1011 1015 1035 1060 1063
## Predicted 117071.5649 175687.5 106231.76 432765.52 269632.5 218451.38
## cvpred 115965.2789 180354.2 105650.64 433590.12 269747.7 220643.18
## price_sold 115700.0000 129000.0 119000.00 460000.00 499000.0 253000.00
## CV residual -265.2789 -51354.2 13349.36 26409.88 229252.3 32356.82
## 1093 1095 1107 1108 1110 1113
## Predicted 620461.7 310716.7 183523.1 140818.6 249291.10 109563.59
## cvpred 611789.6 308841.5 187407.1 138964.9 250391.86 109627.24
## price_sold 1150000.0 158200.0 83000.0 335000.0 178800.00 180000.00
## CV residual 538210.4 -150641.5 -104407.1 196035.1 -71591.86 70372.76
## 1116 1119 1121 1125 1143 1150 1174
## Predicted 502428.87 77727.08 241796.9 222927.6 607019.8 217708.5 322225.60
## cvpred 508088.15 78526.97 243260.8 225305.6 607208.8 220339.3 319792.81
## price_sold 485000.00 105111.00 495000.0 380000.0 843475.0 388400.0 366000.00
## CV residual -23088.15 26584.03 251739.2 154694.4 236266.2 168060.7 46207.19
## 1189 1202 1204 1207 1208 1241
## Predicted 183181.66 88373.05 496286.7 288442.4 177293.4 149055.69
## cvpred 187485.31 88254.06 501437.4 295856.1 181882.3 146399.82
## price_sold 111500.00 131000.00 197750.0 445000.0 165000.0 157000.00
## CV residual -75985.31 42745.94 -303687.4 149143.9 -16882.3 10600.18
## 1254 1266 1292 1302 1307 1321
## Predicted 293794.731 179568.393 236443.9 214570.47 318879.98 331579.5
## cvpred 292336.272 184047.096 238167.1 216950.28 316609.28 329499.8
## price_sold 290000.000 182500.000 2900.0 142500.00 229900.00 200000.0
## CV residual -2336.272 -1547.096 -235267.1 -74450.28 -86709.28 -129499.8
## 1322 1324 1326 1334 1335 1339 1348
## Predicted 235373.32 276905.23 442876.2 298612.4 298612.4 321363.293 30011.66
## cvpred 237148.37 277877.42 442807.8 296920.6 296920.6 327182.037 33526.37
## price_sold 212000.00 300749.00 899900.0 425000.0 425000.0 335000.000 150000.00
## CV residual -25148.37 22871.58 457092.2 128079.4 128079.4 7817.963 116473.63
## 1364
## Predicted 217246.96
## cvpred 219497.11
## price_sold 155000.00
## CV residual -64497.11
##
## Sum of squares = 4.383583e+12 Mean square = 31996959125 n = 137
##
## fold 4
## Observations in test set: 137
## 31 48 51 52 58 61 75
## Predicted 239997.2 352678.3 469058.5 312262.55 250837.0 319355.3 353213.6
## cvpred 239821.9 351926.1 468102.0 314172.06 250974.5 321469.4 352476.8
## price_sold 363000.0 200000.0 1075000.0 264900.00 110000.0 439000.0 550000.0
## CV residual 123178.1 -151926.1 606898.0 -49272.06 -140974.5 117530.6 197523.2
## 91 99 100 107 130 135 148
## Predicted 404067.7 420319.82 476466.2 236979.2 357347.7 439396.7 318344.7
## cvpred 400970.3 421784.99 479285.1 236983.0 361089.9 441146.2 320695.7
## price_sold 600000.0 505000.00 625000.0 54474.0 69668.0 212000.0 500000.0
## CV residual 199029.7 83215.01 145714.9 -182509.0 -291421.9 -229146.2 179304.3
## 166 192 199 203 205 212
## Predicted 243938.1 977447.45 127777.547 71303.49 259000.29 587942.90
## cvpred 244142.6 986797.43 128458.666 70355.43 259373.27 590150.02
## price_sold 353000.0 932000.00 120000.000 179725.00 244900.00 528000.00
## CV residual 108857.4 -54797.43 -8458.666 109369.57 -14473.27 -62150.02
## 215 235 241 242 251 257
## Predicted 100938.8 413494.75 1200593.4 368603.4 280338.45 226273.24
## cvpred 101111.7 414763.04 1216646.8 368310.6 281593.04 225968.14
## price_sold 40000.0 450500.00 935000.0 90201.0 319000.00 265000.00
## CV residual -61111.7 35736.96 -281646.8 -278109.6 37406.96 39031.86
## 306 316 330 335 347 349
## Predicted 348395.90 227343.84 322017.97 524241.65 779580.63 568062.4
## cvpred 347520.14 227069.63 324740.99 528438.74 783488.53 573789.7
## price_sold 305500.00 289900.00 340000.00 512900.00 858700.00 444500.0
## CV residual -42020.14 62830.37 15259.01 -15538.74 75211.47 -129289.7
## 369 372 386 411 416 423 426
## Predicted 192014.10 673323.1 285156.14 502012.29 561980.9 197902.39 504495.6
## cvpred 190720.68 677993.3 286549.72 509927.84 563439.1 196778.84 508389.1
## price_sold 280000.00 475000.0 255000.00 449500.00 675000.0 210000.00 900000.0
## CV residual 89279.32 -202993.3 -31549.72 -60427.84 111560.9 13221.16 391610.9
## 433 436 460 477 484 497
## Predicted 263550.3 520093.7 1086574.7 571616.3 184593.72 391413.67
## cvpred 264054.6 520343.5 1099338.8 573352.4 182820.19 392044.95
## price_sold 163500.0 405000.0 799900.0 633000.0 215000.00 380000.00
## CV residual -100554.6 -115343.5 -299438.8 59647.6 32179.81 -12044.95
## 499 506 514 519 530 557
## Predicted 579497.5 532940.92 371875.25 264011.82 485700.1 375160.85
## cvpred 585820.7 533561.33 371942.88 264795.42 488785.4 375057.22
## price_sold 482725.0 608000.00 324900.00 183000.00 335000.0 279900.00
## CV residual -103095.7 74438.67 -47042.88 -81795.42 -153785.4 -95157.22
## 566 567 574 585 592 593
## Predicted 377034.4 165174.68 235373.32 88894.56 408007.94 415649.7
## cvpred 376984.8 167200.68 235330.75 88720.01 409117.94 416448.1
## price_sold 235000.0 115000.00 260000.00 119000.00 467000.00 289000.0
## CV residual -141984.8 -52200.68 24669.25 30279.99 57882.06 -127448.1
## 597 599 604 634 645 654 665
## Predicted 345451.8 467366.1 306969.6 558976.7 221990.8 280739.9 246347
## cvpred 344491.1 469922.5 308992.4 560082.2 221562.2 282006.1 246621
## price_sold 229000.0 300000.0 185000.0 320000.0 329000.0 262500.0 378000
## CV residual -115491.1 -169922.5 -123992.4 -240082.2 107437.8 -19506.1 131379
## 684 685 688 690 695 697 703
## Predicted 239314.26 245008.7 383116.53 232696.83 484495.69 264011.8 120611.0
## cvpred 239651.42 245244.1 383508.45 232577.04 487546.18 264795.4 121351.4
## price_sold 219900.00 259900.0 358000.00 184900.00 440000.00 98775.0 232500.0
## CV residual -19751.42 14655.9 -25508.45 -47677.04 -47546.18 -166020.4 111148.6
## 708 710 718 745 752 759 765
## Predicted 207330.14 295400.6 498741.1 725307.1 473849.7 246748.4 384990.1
## cvpred 206744.61 296823.7 502468.6 731743.0 476859.1 247034.0 385436.0
## price_sold 273000.00 220000.0 255000.0 1025000.0 329900.0 115000.0 740000.0
## CV residual 66255.39 -76823.7 -247468.6 293257.0 -146959.1 -132034.0 354564.0
## 766 773 774 787 791 797 808
## Predicted 289037.06 371205.47 292115.0 74976.78 531200.5 244339.6 468898.2
## cvpred 290542.59 375081.42 293709.4 74400.73 535598.4 244555.7 471764.8
## price_sold 335000.00 430000.00 565100.0 155900.00 710000.0 404325.0 136429.0
## CV residual 44457.41 54918.58 271390.6 81499.27 174401.6 159769.3 -335335.8
## 809 814 818 841 860 873 898
## Predicted 216564.05 254035.0 488422.8 202720.1 364648.71 345377.95 264011.82
## cvpred 216244.91 254796.8 492384.8 201735.5 364507.87 344681.17 264795.42
## price_sold 241000.00 500000.0 73000.0 360000.0 445000.00 285000.00 207000.00
## CV residual 24755.09 245203.2 -419384.8 158264.5 80492.13 -59681.17 -57795.42
## 908 911 913 924 971 993 998
## Predicted 233499.8 557832.3 371681.4 199642.11 212697.58 383056.5 155673.12
## cvpred 233403.2 559170.8 371477.4 198568.75 207907.15 383180.7 157425.02
## price_sold 382000.0 382000.0 284900.0 180000.00 230000.00 260000.0 135800.00
## CV residual 148596.8 -177170.8 -86577.4 -18568.75 22092.85 -123180.7 -21625.02
## 1010 1031 1034 1047 1056 1059 1066
## Predicted 104565.8 206541.0 466548.7 379101.79 325035.92 238585.1 296739.53
## cvpred 104311.3 205400.6 473441.2 379377.89 327579.96 238635.2 294373.58
## price_sold 175000.0 175000.0 185000.0 319000.00 350000.00 506000.0 210000.00
## CV residual 70688.7 -30400.6 -288441.2 -60377.89 22420.04 267364.8 -84373.58
## 1067 1080 1085 1087 1099 1133
## Predicted 372812.02 692058.6 393554.9 58723.96 398981.7 523498.7
## cvpred 372906.68 697269.3 394247.9 57413.00 399565.2 527940.4
## price_sold 449900.00 1070000.0 75000.0 168000.00 280000.0 390000.0
## CV residual 76993.32 372730.7 -319247.9 110587.00 -119565.2 -137940.4
## 1163 1168 1176 1184 1186 1190
## Predicted 219448.18 117473.0 236517.73 181649.57 72374.09 240043.40
## cvpred 218946.19 117856.9 236242.12 179791.11 71456.91 240667.64
## price_sold 288500.00 285000.0 170000.00 190000.00 237500.00 145000.00
## CV residual 69553.81 167143.1 -66242.12 10208.89 166043.09 -95667.64
## 1192 1195 1196 1198 1206 1222
## Predicted 183181.66 279743.1 152862.80 367250.7 414980.6 283208.8
## cvpred 181633.45 280714.5 154533.63 371278.7 415759.7 284812.2
## price_sold 111500.00 415000.0 130000.00 74000.0 284700.0 165000.0
## CV residual -70133.45 134285.5 -24533.63 -297278.7 -131059.7 -119812.2
## 1225 1228 1237 1249 1260 1280
## Predicted 310122.01 277989.6191 186601.09 393167.2 168654.12 225664.13
## cvpred 308142.12 279442.4998 184885.47 393317.0 170780.51 225607.51
## price_sold 235000.00 280000.0000 235000.00 282200.0 209900.00 168000.00
## CV residual -73142.12 557.5002 50114.53 -111117.0 39119.49 -57607.51
## 1293 1310 1314 1317 1319 1340
## Predicted 370343.16 300070.7 254450.25 254450.25 214155.2 321363.29
## cvpred 370100.54 302160.6 254691.97 254691.97 213766.6 319707.69
## price_sold 382500.00 160000.0 239900.00 240316.00 10000.0 335500.00
## CV residual 12399.46 -142160.6 -14791.97 -14375.97 -203766.6 15792.31
## 1365
## Predicted 722183.59
## cvpred 723903.59
## price_sold 625000.00
## CV residual -98903.59
##
## Sum of squares = 3.313509e+12 Mean square = 24186194576 n = 137
##
## fold 5
## Observations in test set: 137
## 18 26 43 56 57 65 81
## Predicted 565266.5 343831.4 191954.1 216042.54 215105.76 231626.2 253647.3
## cvpred 566260.9 341894.8 190398.8 215373.36 214402.13 228546.2 254361.4
## price_sold 1050000.0 480000.0 134000.0 190000.00 150000.00 535000.0 419900.0
## CV residual 483739.1 138105.2 -56398.8 -25373.36 -64402.13 306453.8 165538.6
## 137 139 140 141 156 158 168
## Predicted 668505.4 379309.4 415561.5 534606.2 705917.0 353481.24 420186.0
## cvpred 670313.4 377562.6 416263.5 535588.0 705001.8 350784.37 416958.8
## price_sold 915000.0 51314.0 615000.0 375000.0 580000.0 420000.00 565000.0
## CV residual 244686.6 -326248.6 198736.5 -160588.0 -125001.8 69215.63 148041.2
## 181 183 191 210 213 219
## Predicted 194616.8 533610.04 368797.28 332530.8 1033787.7 830834.9
## cvpred 187191.3 530455.85 363679.74 326079.1 1044933.4 838614.2
## price_sold 255000.0 435000.00 349900.00 450000.0 700000.0 1300000.0
## CV residual 67808.7 -95455.85 -13779.74 123920.9 -344933.4 461385.8
## 230 245 250 254 259 263
## Predicted 546382.754 945998.6 1099228.7 242283.5 236979.22 1181188.8
## cvpred 547797.762 953915.0 1105698.2 243694.9 234096.13 1194772.6
## price_sold 550000.000 759000.0 651900.0 195000.0 310000.00 1010000.0
## CV residual 2202.238 -194915.0 -453798.2 -48694.9 75903.87 -184772.6
## 267 269 272 276 294 297
## Predicted 417851.0 240191.015 360098.0 62471.06 1337510.6 519424.6
## cvpred 417521.9 237426.073 361743.9 60252.05 1355729.4 515748.6
## price_sold 285000.0 244800.000 630000.0 155000.00 1000000.0 550000.0
## CV residual -132521.9 7373.927 268256.1 94747.95 -355729.4 34251.4
## 300 308 311 320 325 328 333
## Predicted 194348.48 1348203.4 117071.56 318612.991 1183062 412096.5 462073.1
## cvpred 193996.55 1353764.1 116861.06 311649.401 1196715 411555.8 460386.8
## price_sold 260000.00 1150000.0 215000.00 310000.000 1320000 331500.0 873500.0
## CV residual 66003.45 -203764.1 98138.94 -1649.401 123285 -80055.8 413113.2
## 334 336 338 341 361 363
## Predicted 512258.1 825750.2 293393.92 536152.71 698615.987 375146.40
## cvpred 505334.4 826259.0 288486.71 533092.05 701531.599 374361.77
## price_sold 712000.0 1128000.0 335000.00 512500.00 700000.000 280000.00
## CV residual 206665.6 301741.0 46513.29 -20592.05 -1531.599 -94361.77
## 367 385 432 441 454 474 492
## Predicted 773424.7 364648.713 477671.29 310389.66 1075823.8 109651.2 343503.7
## cvpred 772008.7 359378.564 472459.36 306107.65 1080317.1 112151.8 344539.2
## price_sold 940000.0 364000.000 414000.00 288900.00 1550000.0 290000.0 257000.0
## CV residual 167991.3 4621.436 -58459.36 -17207.65 469682.9 177848.2 -87539.2
## 495 501 554 556 564 576 584
## Predicted 649562.3 487647.5 661888.0 380707.69 412096.5 471515.3 307297.24
## cvpred 647689.4 492870.0 666436.6 376028.27 411555.8 466077.0 304016.75
## price_sold 1500100.0 177000.0 799000.0 305000.00 629900.0 717000.0 252000.00
## CV residual 852410.6 -315870.0 132563.4 -71028.27 218344.2 250923.0 -52016.75
## 587 596 627 639 664 667
## Predicted 344916.45 612372.81 215834.91 433702.30 389613.9 220117.30
## cvpred 341904.52 615100.02 212174.02 430972.31 388246.2 216613.94
## price_sold 282000.00 550000.00 287990.00 449000.00 649900.0 240000.00
## CV residual -59904.52 -65100.02 75815.98 18027.69 261653.8 23386.06
## 689 691 699 709 716 726
## Predicted 307980.82 101875.56 236176.272 698080.7 255179.4 233232.1
## cvpred 303610.19 98121.98 233263.646 700976.6 252965.8 230211.2
## price_sold 255000.00 84500.00 225000.000 468000.0 223500.0 228000.0
## CV residual -48610.19 -13621.98 -8263.646 -232976.6 -29465.8 -2211.2
## 729 730 760 763 784 786
## Predicted 377227.6 220920.25 392290.4 342106.13 81875.65 198437.7
## cvpred 379503.6 217446.42 391021.2 338990.82 80370.45 194136.8
## price_sold 255000.0 199000.00 266000.0 260000.00 282525.00 55000.0
## CV residual -124503.6 -18446.42 -125021.2 -78990.82 202154.55 -139136.8
## 795 804 807 816 824 826
## Predicted 885911.3 87823.96 711329.3 311605.40 395696.1 377361.4
## cvpred 891617.3 83553.49 714712.6 308483.39 391568.0 379642.3
## price_sold 460000.0 162000.00 599950.0 215000.00 360000.0 276000.0
## CV residual -431617.3 78446.51 -114762.6 -93483.39 -31568.0 -103642.3
## 837 843 844 858 885 902
## Predicted 247417.55 94649.02 205396.57 388275.68 330414.7 523974.0
## cvpred 244918.44 90629.62 201351.71 386858.73 330968.6 527548.8
## price_sold 259000.00 205000.00 140000.00 430000.00 495000.0 400000.0
## CV residual 14081.56 114370.38 -61351.71 43141.27 164031.4 -127548.8
## 906 907 922 923 928 939 954
## Predicted 185055.21 430029.7 199642.11 199642.11 290836.8 314463.76 277394.3
## cvpred 180262.07 423065.2 195385.56 195385.56 286950.8 314430.97 275997.9
## price_sold 135000.00 545000.0 180000.00 180000.00 265000.0 253000.00 295000.0
## CV residual -45262.07 121934.8 -15385.56 -15385.56 -21950.8 -61430.97 19002.1
## 955 961 964 989 1018 1022 1033
## Predicted 277394.3 208608.37 179166.92 278137.89 357823.6 288977.04 208534.6
## cvpred 275997.9 204681.65 174157.18 272669.49 352302.4 290990.79 201621.0
## price_sold 295000.0 120000.00 199000.00 209500.00 237160.0 385000.00 335000.0
## CV residual 19002.1 -84681.65 24842.82 -63169.49 -115142.4 94009.21 133379.0
## 1037 1041 1069 1082 1111 1126
## Predicted 214496.66 297006.5 395622.3 243268.98 90634.28 162170.51
## cvpred 210786.54 299315.6 388507.4 240617.27 86467.19 163618.99
## price_sold 227000.00 173000.0 570000.0 141000.00 260000.00 120000.00
## CV residual 16213.46 -126315.6 181492.6 -99617.27 173532.81 -43618.99
## 1128 1131 1138 1142 1148 1164 1165
## Predicted 89102.19 206942.45 208206.9 272502.80 360172.48 214958.15 238183.6
## cvpred 87862.82 205938.53 204265.4 267942.39 357721.75 208280.93 235344.9
## price_sold 165000.00 180000.00 370000.0 195000.00 400000.00 187500.00 339000.0
## CV residual 77137.18 -25938.53 165734.6 -72942.39 42278.25 -20780.93 103655.1
## 1171 1173 1180 1205 1214 1236
## Predicted 238391.27 154067.22 94053.70 95391.95 358091.30 217039.33
## cvpred 238544.21 152233.54 92996.48 94383.95 352579.93 213422.74
## price_sold 163500.00 110650.00 277000.00 180000.00 435000.00 238000.00
## CV residual -75044.21 -41583.54 184003.52 85616.05 82420.07 24577.26
## 1240 1243 1247 1268 1284 1296 1300
## Predicted 432512.3 310122.0 109845.03 314122.3 289244.69 233305.9 198110.0
## cvpred 428623.3 305830.2 109368.69 311092.9 291268.28 233271.8 196781.2
## price_sold 322000.0 416000.0 27886.00 170000.0 235000.00 195000.0 367700.0
## CV residual -106623.3 110169.8 -81482.69 -141092.9 -56268.28 -38271.8 170918.8
## 1304 1316 1318 1347 1354 1360
## Predicted 104565.84 254450.25 101889.35 240933.95 216042.54 363785.1
## cvpred 106879.39 255193.91 104104.43 241180.41 215373.36 368550.7
## price_sold 120000.00 227000.00 140000.00 275000.00 190000.00 70000.0
## CV residual 13120.61 -28193.91 35895.57 33819.59 -25373.36 -298550.7
## 1362 1366
## Predicted 161977.33 199300.65
## cvpred 159319.34 192047.47
## price_sold 92500.00 215000.00
## CV residual -66819.34 22952.53
##
## Sum of squares = 4.159404e+12 Mean square = 30360614079 n = 137
##
## fold 6
## Observations in test set: 137
## 17 20 25 33 36 41 53
## Predicted 477135.3 316010.30 184727.5 89369.84 223804.4 208474.5 366134.57
## cvpred 477298.8 311870.08 184526.9 91669.21 224647.5 206509.0 365732.43
## price_sold 1050000.0 219000.00 309000.0 230000.00 595000.0 165000.0 440000.00
## CV residual 572701.2 -92870.08 124473.1 138330.79 370352.5 -41509.0 74267.57
## 59 69 78 83 86 96
## Predicted 612372.81 274450.16 285617.63 507915.7 280412.25 126097.8
## cvpred 611101.55 274246.85 283313.38 501455.1 282767.44 126979.0
## price_sold 535000.00 355000.00 307000.00 259900.0 365000.00 315000.0
## CV residual -76101.55 80753.15 23686.62 -241555.1 82232.56 188021.0
## 105 114 125 160 162 163
## Predicted 803207.6 235373.32 359369.5 175955.12 756963.6 77579.47
## cvpred 799587.4 234126.26 356387.4 173120.98 757155.2 74765.44
## price_sold 667000.0 147000.00 249900.0 230000.00 385000.0 205000.00
## CV residual -132587.4 -87126.26 -106487.4 56879.02 -372155.2 130234.56
## 165 189 193 200 208 222
## Predicted 275253.8 485031.0 471976.18 805809.6 434652.9 100671.14
## cvpred 267625.7 485405.4 469602.63 807305.9 436080.9 100873.13
## price_sold 485000.0 611000.0 398000.00 470000.0 276000.0 108000.00
## CV residual 217374.3 125594.6 -71602.63 -337305.9 -160080.9 7126.87
## 225 229 240 247 248 249
## Predicted 1219002.49 395963.1 168460.94 778985.3 205738.03 438787.6
## cvpred 1211595.81 399005.4 165426.62 774718.1 206098.64 435527.6
## price_sold 1300000.00 525000.0 178500.00 585000.0 230000.00 275000.0
## CV residual 88404.19 125994.6 13073.38 -189718.1 23901.36 -160527.6
## 252 310 321 340 345 346 352
## Predicted 208474.5 342106.13 658067.08 512258.1 365109.5 716087.67 240592.49
## cvpred 206509.0 338662.94 655617.09 503514.2 364928.6 710140.43 239484.83
## price_sold 165000.0 307200.00 585000.00 712000.0 236000.0 800000.00 266000.00
## CV residual -41509.0 -31462.94 -70617.09 208485.8 -128928.6 89859.57 26515.17
## 356 359 370 375 377 392
## Predicted 563586.79 139212.7 248681.9938 270167.76 249291.10 1730019.9
## cvpred 558613.19 140444.1 245391.1732 269850.08 248415.79 1731215.7
## price_sold 581000.00 266900.0 244554.0000 208000.00 268000.00 2700000.0
## CV residual 22386.81 126455.9 -837.1732 -61850.08 19584.21 968784.3
## 404 420 421 430 437 446 452
## Predicted 629487.9 486101.6 362179.8 867027.57 310375.21 760844.5 294256.22
## cvpred 631321.6 486504.6 359272.8 867759.75 308732.24 761139.7 294581.95
## price_sold 500000.0 624900.0 549980.0 800000.00 400000.00 530000.0 311500.00
## CV residual -131321.6 138395.4 190707.2 -67759.75 91267.76 -231139.7 16918.05
## 467 496 500 511 521 526
## Predicted 699345.1 649562.3 423799.26 242451.59 347057.6 236176.3
## cvpred 695598.4 644485.9 420138.89 244041.36 343746.7 234950.7
## price_sold 525000.0 1500100.0 410000.00 200000.00 485000.0 128000.0
## CV residual -170598.4 855614.1 -10138.89 -44041.36 141253.3 -106950.7
## 528 545 546 569 573 580
## Predicted 207270.12 427472.55 289097.1 217708.453 318419.15 596700.87
## cvpred 205272.41 421511.05 286885.8 215989.556 314343.27 597658.76
## price_sold 255000.00 482500.00 454500.0 219900.000 276000.00 545000.00
## CV residual 49727.59 60988.95 167614.2 3910.444 -38343.27 -52658.76
## 586 611 624 644 647 649
## Predicted 263610.4 386536.0 408201.78 406268.217 256711.48 302627.82
## cvpred 263117.5 384279.5 401725.55 402139.581 253635.13 298130.15
## price_sold 425000.0 300000.0 320305.00 405000.000 215000.00 270000.00
## CV residual 161882.5 -84279.5 -81420.55 2860.419 -38635.13 -28130.15
## 655 666 671 672 677 683
## Predicted 329928.08 243462.828 88626.91 417181.8 222332.30 467499.9
## cvpred 326159.61 240032.601 88507.19 415743.9 223136.15 467406.1
## price_sold 280000.00 235000.000 120000.00 269900.0 194900.00 280000.0
## CV residual -46159.61 -5032.601 31492.81 -145843.9 -28236.15 -187406.1
## 686 722 723 747 753 755
## Predicted 525312.2 238183.6 358834.2 207343.93 365257.8 1233246.6
## cvpred 526762.6 237011.6 355837.9 207747.43 362433.0 1238713.6
## price_sold 415000.0 80000.0 163600.0 159900.00 260000.0 980000.0
## CV residual -111762.6 -157011.6 -192237.9 -47847.43 -102433.0 -258713.6
## 758 764 785 788 794 817 834
## Predicted 319682.93 119955.69 259997.1 197694.76 339295.8 371339.95 299876.9
## cvpred 320687.81 125471.26 259407.7 193042.05 335777.6 366278.37 300352.7
## price_sold 385000.00 205000.00 550000.0 219900.00 190000.0 337000.00 589000.0
## CV residual 64312.19 79528.74 290592.3 26857.95 -145777.6 -29278.37 288647.3
## 848 851 857 871 874 876
## Predicted 587541.4 271164.6 1056060.6 342373.78 169531.535 289900.0
## cvpred 583207.7 268474.3 1079133.7 338937.74 166525.813 287710.2
## price_sold 1200000.0 660000.0 530000.0 275000.00 175000.000 565000.0
## CV residual 616792.3 391525.7 -549133.7 -63937.74 8474.187 277289.8
## 878 890 892 893 925 930
## Predicted 360975.43 233232.13 94381.37 94381.37 111049.45 328322.18
## cvpred 358036.24 231927.87 94415.36 94415.36 113927.89 324510.82
## price_sold 445000.00 270000.00 143000.00 143000.00 160500.00 260000.00
## CV residual 86963.76 38072.13 48584.64 48584.64 46572.11 -64510.82
## 935 944 952 959 978 980
## Predicted 133859.68 256250.0 409078.54 169070.04 226467.1 178705.43
## cvpred 134948.15 255560.5 405024.97 168451.23 222582.9 178343.98
## price_sold 179900.00 512500.0 380000.00 93000.00 90000.0 90500.00
## CV residual 44951.85 256939.5 -25024.97 -75451.23 -132582.9 -87843.98
## 994 1023 1025 1029 1032 1038
## Predicted 116863.93 268294.22 229485.03 220726.40 221589.37 262138.28
## cvpred 117498.44 267926.49 228080.69 221487.36 219974.13 261606.12
## price_sold 135000.00 182850.00 144900.00 205000.00 193000.00 346000.00
## CV residual 17501.56 -85076.49 -83180.69 -16487.36 -26974.13 84393.88
## 1044 1049 1050 1065 1075 1081 1089
## Predicted 379101.79 258049.728 217708.5 361049.23 244132.0 113652.1 293974.8
## cvpred 374247.53 255009.123 215989.6 360511.26 240719.6 114200.9 289494.5
## price_sold 319900.00 253000.000 329000.0 317000.00 187000.0 253000.0 39000.0
## CV residual -54347.53 -2009.123 113010.4 -43511.26 -53719.6 138799.1 -250494.5
## 1105 1122 1136 1166 1178 1199
## Predicted 265216.2 469701.159 143227.4 188192.5375 543780.7 200920.3
## cvpred 264766.3 467266.842 144566.1 190732.2625 538278.1 201152.3
## price_sold 478000.0 465000.000 50000.0 191000.0000 655500.0 347500.0
## CV residual 213233.7 -2266.842 -94566.1 267.7375 117221.9 146347.7
## 1215 1217 1265 1276 1277 1279
## Predicted 435635.86 270168.42 74247.64 225664.1 61326.65 244205.7581
## cvpred 429892.41 262404.51 76143.09 221758.5 60477.74 243194.6139
## price_sold 351000.00 339000.00 142000.00 168000.0 45000.00 242394.0000
## CV residual -78892.41 76595.49 65856.91 -53758.5 -15477.74 -800.6139
## 1297 1303 1341 1349 1351 1356
## Predicted 440467.3 284888.5 246153.1 207611.58 230094.1 168460.9
## cvpred 439651.4 284964.0 247593.2 208022.23 231105.3 165426.6
## price_sold 221000.0 225000.0 60000.0 135000.00 353000.0 50000.0
## CV residual -218651.4 -59964.0 -187593.2 -73022.23 121894.7 -115426.6
##
## Sum of squares = 4.974171e+12 Mean square = 36307815266 n = 137
##
## fold 7
## Observations in test set: 137
## 24 29 44 54 73 77 79
## Predicted 323578.30 83347.722 320827.99 462756.1 439397.4 319281.5 523632.5
## cvpred 318672.56 87501.905 317054.65 457998.7 432227.8 320164.5 521210.7
## price_sold 290000.00 90000.000 230000.00 170000.0 310000.0 425000.0 700000.0
## CV residual -28672.56 2498.095 -87054.65 -287998.7 -122227.8 104835.5 178789.3
## 90 103 134 152 169 174
## Predicted 631302.13 346447.9 421658.1 1400260.6 415903.60 694808.9
## cvpred 624337.08 347359.9 419127.5 1387069.9 413366.93 686776.2
## price_sold 705500.00 221500.0 294900.0 1600000.0 445000.00 1100000.0
## CV residual 81162.92 -125859.9 -124227.5 212930.1 31633.07 413223.8
## 180 190 211 233 234 253
## Predicted 575898.67 506677.0 265751.55 394893.11 716073.23 926594.70
## cvpred 568874.56 498443.8 266577.49 392334.04 710333.87 911763.76
## price_sold 600000.00 780000.0 350000.00 465000.00 647800.00 950000.00
## CV residual 31125.44 281556.2 83422.51 72665.96 -62533.87 38236.24
## 258 262 264 265 277 278
## Predicted 505640.66 238718.94 1090380.5 492511.39 213901.34 758094.2
## cvpred 498541.65 239516.07 1088562.8 491191.71 213536.69 752399.6
## price_sold 421500.00 275000.00 837500.0 407975.00 250000.00 1400000.0
## CV residual -77041.65 35483.93 -251062.8 -83216.71 36463.31 647600.4
## 286 309 312 351 382 391
## Predicted 299936.88 1109889.1 557163.20 330414.7 545580.46 411085.9
## cvpred 301934.59 1088324.9 550119.12 331309.6 539659.35 408544.1
## price_sold 335000.00 1842700.0 630000.00 192500.0 480000.00 325000.0
## CV residual 33065.41 754375.1 79880.88 -138809.6 -59659.35 -83544.1
## 396 403 414 425 461 469 472
## Predicted 511379.4 809825.0 628625.63 504495.6 247149.90 399710.80 628298.0
## cvpred 517125.2 799527.6 621657.73 502053.4 247956.02 397156.87 620194.4
## price_sold 300000.0 1306000.0 550000.00 900000.0 199000.00 375000.00 530230.0
## CV residual -217125.2 506472.4 -71657.73 397946.6 -48956.02 -22156.87 -89964.4
## 475 481 493 516 518 522
## Predicted 528852.4 277126.652 368201.30 116462.46 396632.8 535885.1
## cvpred 522913.4 277964.728 368001.15 121787.26 394075.6 528818.3
## price_sold 769100.0 280000.000 279000.00 110111.00 545000.0 398000.0
## CV residual 246186.6 2035.272 -89001.15 -11676.26 150924.4 -130818.3
## 529 535 540 541 544 549
## Predicted 303891.61 141293.85 385331.534 289097.1 349660.338 285156.1
## cvpred 304758.22 145509.81 381626.955 291083.2 347053.048 286002.8
## price_sold 218000.00 159000.00 390000.000 454500.0 340000.000 173000.0
## CV residual -86758.22 13490.19 8373.045 163416.8 -7053.048 -113002.8
## 550 553 561 570 583 591
## Predicted 222526.145 390952.17 585801.0 335207.26 71169.67 251432.30
## cvpred 223306.011 387253.59 582310.2 332584.56 75310.87 252242.98
## price_sold 225000.000 465000.00 1050000.0 405000.00 111000.00 226000.00
## CV residual 1693.989 77746.41 467689.8 72415.44 35689.13 -26242.98
## 613 628 629 631 636 653 660
## Predicted 252235.24 391681.32 480928 272770.453 416171.25 336813.16 255179.39
## cvpred 253046.78 389118.82 484254 274739.202 413634.87 334192.17 255994.07
## price_sold 340000.00 349900.00 640000 270000.000 383000.00 302000.00 220000.00
## CV residual 86953.22 -39218.82 155746 -4739.202 -30634.87 -32192.17 -35994.07
## 662 669 679 701 706 707
## Predicted 446014.17 447753.9 88700.713 340560.25 277929.6 259387.98
## cvpred 443509.61 445251.2 92860.602 337943.26 278768.5 261342.46
## price_sold 355000.00 558650.0 95000.000 395000.00 120000.0 235000.00
## CV residual -88509.61 113398.8 2139.398 57056.74 -158768.5 -26342.46
## 734 736 738 742 750 756
## Predicted 352945.94 405940.5 299342.22 99005.22 195225.89 203864.48
## cvpred 349206.83 402257.9 296681.29 103176.10 195976.65 203489.14
## price_sold 275000.00 238775.0 235000.00 171000.00 230000.00 230700.00
## CV residual -74206.83 -163482.9 -61681.29 67823.90 34023.35 27210.86
## 762 768 770 781 782 803
## Predicted 298003.3 310122.0 249157.3 223924.411 116730.1 289974.49
## cvpred 298863.6 306337.3 249965.5 225841.086 122055.2 287303.57
## price_sold 157000.0 172950.0 510000.0 223000.000 210000.0 300000.00
## CV residual -141863.6 -133387.3 260034.5 -2841.086 87944.8 12696.43
## 821 849 856 863 866 870
## Predicted 523900.85 236905.41 102544.68 291981.20 565727.99 349125.04
## cvpred 517956.62 238835.93 107854.65 292835.11 558693.03 346517.18
## price_sold 617000.00 195000.00 193500.00 330000.00 625000.00 280000.00
## CV residual 99043.38 -43835.93 85645.35 37164.89 66306.97 -66517.18
## 883 904 915 921 949 976
## Predicted 344039.70 253499.69 163241.11 95391.952 240191.01 390878.37
## cvpred 341426.42 255447.89 167480.47 99558.974 240989.71 388315.02
## price_sold 257500.00 169000.00 214300.00 108000.000 227000.00 357000.00
## CV residual -83926.42 -86447.89 46819.53 8441.026 -13989.71 -31315.02
## 982 984 985 988 991 1004
## Predicted 404930.0 188802.30 394759.3 227952.94 108700.622 155673.12
## cvpred 402381.6 189546.22 392200.1 227603.28 114017.152 161039.72
## price_sold 315000.0 145000.00 260000.0 276670.00 105000.000 135000.00
## CV residual -87381.6 -44546.22 -132200.1 49066.72 -9017.152 -26039.72
## 1007 1013 1019 1024 1026 1042
## Predicted 258391.18 161368.2 389406.296 268294.22 185055.2 447680.1
## cvpred 259209.29 162082.9 386841.378 269122.88 185795.1 446312.6
## price_sold 222000.00 320150.0 385000.000 182850.00 81000.0 333500.0
## CV residual -37209.29 158067.1 -1841.378 -86272.88 -104795.1 -112812.6
## 1054 1057 1061 1077 1079 1091
## Predicted 438192.3 83615.37 323162.4 198437.69 308040.83 184177.79
## cvpred 434544.1 87769.84 324049.5 199191.87 305389.17 189574.79
## price_sold 700000.0 180000.00 130500.0 175000.00 230000.00 272000.00
## CV residual 265455.9 92230.16 -193549.5 -24191.87 -75389.17 82425.21
## 1100 1104 1151 1152 1167 1177 1182
## Predicted 453180.694 104344.42 370329.4 250421.7 262599.8 283357.1 173887.73
## cvpred 449548.448 110791.63 368879.4 252366.6 264557.7 279543.8 173480.43
## price_sold 445500.000 180000.00 246000.0 375000.0 385000.0 520000.0 245000.00
## CV residual -4048.448 69208.37 -122879.4 122633.4 120442.3 240456.2 71519.57
## 1200 1209 1210 1224 1229 1232
## Predicted 390952.17 377422.1 299489.84 330414.7 269900.1 328857.5
## cvpred 387253.59 375979.7 294558.42 331309.6 270730.5 325092.7
## price_sold 480000.00 152000.0 350000.00 151750.0 450000.0 145000.0
## CV residual 92746.41 -223979.7 55441.58 -179559.6 179269.5 -180092.7
## 1239 1244 1269 1275 1285 1286
## Predicted 395709.85 404870.0 242332.21 223061.44 349224.0 315206.7
## cvpred 390881.01 401186.2 243133.19 223841.88 349003.6 314950.0
## price_sold 435000.00 295000.0 158000.00 182000.00 235000.0 160000.0
## CV residual 44118.99 -106186.2 -85133.19 -41841.88 -114003.6 -154950.0
## 1287 1301 1323 1331 1337 1346
## Predicted 277989.61906 541638.87 276905.23 89965.15 476064.7 254450.2
## cvpred 279963.93263 538100.93 281149.03 95261.71 472456.9 254128.8
## price_sold 280000.00000 549000.00 300749.00 100000.00 285000.0 100000.0
## CV residual 36.06737 10899.07 19599.97 4738.29 -187456.9 -154128.8
## 1352
## Predicted 435382.00
## cvpred 431730.78
## price_sold 467000.00
## CV residual 35269.22
##
## Sum of squares = 3.370195e+12 Mean square = 24599961696 n = 137
##
## fold 8
## Observations in test set: 136
## 1 10 13 35 63 64
## Predicted 336425.5 218511.40 585801.0 455261.9 632372.1 434846.7
## cvpred 337836.5 222861.49 576942.3 449887.2 620854.0 434607.7
## price_sold 214300.0 187000.00 1050000.0 1175000.0 470000.0 870000.0
## CV residual -123536.5 -35861.49 473057.7 725112.8 -150854.0 435392.3
## 68 76 85 94 95 104 111
## Predicted 1063824.5 1151406 243402.8 2024775.9 624343.2 251833.77 294182.4
## cvpred 1051137.7 1137688 246331.6 1980509.3 625017.6 254281.09 298181.5
## price_sold 695000.0 900000 365000.0 2900000.0 875000.0 225000.00 122000.0
## CV residual -356137.7 -237688 118668.4 919490.7 249982.4 -29281.09 -176181.5
## 117 121 133 138 144 157
## Predicted 734273.4 620730.0 272308.96 796710.2 718615.9 553014.0
## cvpred 732640.5 621610.7 273587.12 799276.1 717877.1 546027.4
## price_sold 849000.0 437000.0 290000.00 680000.0 555000.0 425000.0
## CV residual 116359.5 -184610.7 16412.88 -119276.1 -162877.1 -121027.4
## 161 164 176 198 206 217 220
## Predicted 611094.6 275253.8 210481.9 251432.30 330644.1 418178.62 213633.69
## cvpred 612525.5 288097.7 215290.5 253902.54 359999.0 422861.34 214292.36
## price_sold 430000.0 485000.0 320000.0 242000.00 562200.0 465000.00 122000.00
## CV residual -182525.5 196902.3 104709.5 -11902.54 202201.0 42138.66 -92292.36
## 227 243 244 273 280 295
## Predicted 425137.51 1105577.8 213633.69 775907.3 970414.10 414565.35
## cvpred 429422.86 1090506.9 214292.36 775691.2 951327.29 419454.39
## price_sold 515000.00 1937500.0 122000.00 620000.0 975000.00 385000.00
## CV residual 85577.14 846993.1 -92292.36 -155691.2 23672.71 -34454.39
## 315 319 339 342 379 388
## Predicted 355354.8 842403.8 466697.0 603005.1 438519.987 668505.4
## cvpred 359654.9 834596.5 464639.3 600928.0 442041.178 666658.1
## price_sold 387500.0 483100.0 314500.0 380000.0 449900.000 1075000.0
## CV residual 27845.1 -351496.5 -150139.3 -220928.0 7858.822 408341.9
## 412 428 431 435 439 449
## Predicted 186988.115 826598.7 88373.05 268829.52 262807.40 462756.1
## cvpred 185374.216 827633.8 84450.35 270306.35 264628.11 456953.5
## price_sold 183000.000 700000.0 55000.00 292900.00 207000.00 170000.0
## CV residual -2374.216 -127633.8 -29450.35 22593.65 -57628.11 -286953.5
## 470 473 482 487 489 494
## Predicted 399736.57 521030.5 277126.65 612299.0 620328.5 684029.1
## cvpred 405472.35 527604.2 278129.71 613661.1 621232.1 681295.3
## price_sold 312500.00 375000.0 280000.00 396000.0 350000.0 460000.0
## CV residual -92972.35 -152604.2 1870.29 -217661.1 -271232.1 -221295.3
## 504 515 525 531 548 571
## Predicted 468155.28 116462.46 111510.94 553535.5 213352.254 660550.4
## cvpred 473954.19 118875.69 114206.91 554459.0 221966.873 666921.3
## price_sold 455000.00 110111.00 180000.00 405000.0 225000.000 900000.0
## CV residual -18954.19 -8764.69 65793.09 -149459.0 3033.127 233078.7
## 578 579 590 594 598 600
## Predicted 545981.28 468496.7 356692.37 99259.08 257320.6 409420.0
## cvpred 543366.26 470306.2 349182.16 106624.59 259454.6 410632.9
## price_sold 487000.00 290000.0 270000.00 154000.00 229000.0 308500.0
## CV residual -56366.26 -180306.2 -79182.16 47375.41 -30454.6 -102132.9
## 605 608 609 610 612 617
## Predicted 217708.45 231210.97 531007.4 496064.6 138617.35 148594.19
## cvpred 222104.39 242775.76 533041.4 496299.9 135795.56 141232.77
## price_sold 237500.00 229600.00 260000.0 360000.0 175000.00 188000.00
## CV residual 15395.61 -13175.76 -273041.4 -136299.9 39204.44 46767.23
## 651 711 724 733 741 761
## Predicted 808084.65 220458.755 281409.04 415502.1 283357.06 480689.2
## cvpred 798267.11 220727.702 282167.57 420337.7 291768.36 485596.6
## price_sold 749900.00 218000.000 196250.00 190000.0 275000.00 282500.0
## CV residual -48367.11 -2727.702 -85917.57 -230337.7 -16768.36 -203096.6
## 772 783 792 812 827 836 842
## Predicted 310122 192549.40 187389.59 199240.63 68553.19 270703.06 202720.1
## cvpred 317005 198381.95 185752.77 204691.11 73702.12 272072.92 207971.9
## price_sold 172950 127000.00 249900.00 197500.00 165000.00 187500.00 360000.0
## CV residual -144055 -71381.95 64147.23 -7191.11 91297.88 -84572.92 152028.1
## 852 859 868 886 899 919
## Predicted 226882.34 365243.4 251967.59 413287.1 77325.61 130514.06
## cvpred 226784.49 365184.8 254407.28 422219.1 78003.68 132124.92
## price_sold 195000.00 120000.0 196000.00 125000.0 61000.00 185000.00
## CV residual -31784.49 -245184.8 -58407.28 -297219.1 -17003.68 52875.08
## 929 936 938 943 945 973
## Predicted 100998.80 388663.4 276785.2 92641.65 245008.7 227878.48
## cvpred 108264.97 399001.4 281777.7 96415.09 247845.8 219959.73
## price_sold 191600.00 230000.0 110000.0 140000.00 79900.0 250000.00
## CV residual 83335.03 -169001.4 -171777.7 43584.91 -167945.8 30040.27
## 974 981 983 995 1036 1043
## Predicted 165650.0 349065.0 516688.10 363651.92 251506.1 262406.58627
## cvpred 161284.6 353724.3 519539.84 367478.26 250002.2 275984.13669
## price_sold 322400.0 575000.0 487600.00 410000.00 147500.0 276000.00000
## CV residual 161115.4 221275.7 -31939.84 42521.74 -102502.2 15.86331
## 1055 1058 1072 1083 1086 1101 1103
## Predicted 418545.8 230154.16 170929.1 241127.8 195345.3 288710.0 313734.62
## cvpred 419237.6 233839.42 170232.2 244186.4 197224.1 296815.7 308677.37
## price_sold 700000.0 155000.00 357000.0 415000.0 149000.0 105000.0 260000.00
## CV residual 280762.4 -78839.42 186767.8 170813.6 -48224.1 -191815.7 -48677.37
## 1109 1120 1123 1132 1135 1137 1146
## Predicted 332069.27 78797.68 210883.39 243669.80 415709.8 277781.99 175211.5
## cvpred 337699.03 79391.69 215669.05 234849.35 416563.5 286687.51 174270.1
## price_sold 257000.00 200000.00 255000.00 150000.00 592000.0 187000.00 315000.0
## CV residual -80699.03 120608.31 39330.95 -84849.35 175436.5 -99687.51 140729.9
## 1153 1158 1161 1175 1226 1233 1238
## Predicted 368395.8 118945.11 181991.0 356826.9 268561.87 328857.5 395709.85
## cvpred 375921.2 117246.64 180486.6 361042.9 270053.99 334670.6 393735.69
## price_sold 325000.0 96000.00 227000.0 235000.0 181900.00 145000.0 435000.00
## CV residual -50921.2 -21246.64 46513.4 -126042.9 -88153.99 -189670.6 41264.31
## 1252 1253 1258 1259 1270 1283
## Predicted 257052.9 222258.5 524316.11 203255.38 440467.3 203716.87
## cvpred 259202.2 226394.6 526732.28 208476.61 439907.4 212881.69
## price_sold 50000.0 85000.0 590000.00 140000.00 42500.0 195000.00
## CV residual -209202.2 -141394.6 63267.72 -68476.61 -397407.4 -17881.69
## 1290 1294 1306 1312 1320 1327
## Predicted 214035.17 215105.76 950147.9 256249.99 193753.8 213633.69
## cvpred 214670.91 215680.38 951716.2 258445.14 199517.6 214292.36
## price_sold 220000.00 150000.00 665000.0 214000.00 307000.0 122000.00
## CV residual 5329.09 -65680.38 -286716.2 -44445.14 107482.4 -92292.36
## 1328 1332 1350 1361
## Predicted 213633.69 102217.02 323578.30 241796.91
## cvpred 214292.36 101473.74 325722.96 244817.36
## price_sold 122000.00 125000.00 290000.00 214000.00
## CV residual -92292.36 23526.26 -35722.96 -30817.36
##
## Sum of squares = 5.225747e+12 Mean square = 38424612020 n = 136
##
## fold 9
## Observations in test set: 136
## 16 37 39 50 71 92 93
## Predicted 181114.3 267625.1 214436.64 528852.4 315668.2 611227.8 160698.4
## cvpred 184518.9 268367.1 217822.46 520162.3 316383.1 609747.3 166143.2
## price_sold 90000.0 551900.0 185000.00 769100.0 500000.0 675000.0 445000.0
## CV residual -94518.9 283532.9 -32822.46 248937.7 183616.9 65252.7 278856.8
## 98 109 110 118 126 128 131
## Predicted 1409228 437850.9 493314.34 412216.5 554011.4 303624.0 475054.2
## cvpred 1388727 433854.5 486672.87 405620.8 545307.1 304345.7 471036.8
## price_sold 2400000 67019.0 525000.00 629000.0 84123.0 490000.0 24000.0
## CV residual 1011273 -366835.5 38327.13 223379.2 -461184.1 185654.3 -447036.8
## 153 159 184 223 228 231
## Predicted 959039.65 601057.7 210883.39 401524.33 327712.42 496867.6
## cvpred 948078.21 594940.7 211657.44 400162.22 328420.54 492837.9
## price_sold 975000.00 415500.0 285000.00 358000.00 250000.00 837679.0
## CV residual 26921.79 -179440.7 73342.56 -42162.22 -78420.54 344841.1
## 282 283 287 289 293 326
## Predicted 901167.3 1437672.2 816783.3 294717.7 757707.2 500748.5
## cvpred 892852.3 1419769.7 810544.5 292830.7 749473.1 496716.6
## price_sold 565000.0 2350000.0 600000.0 178000.0 1125000.0 380000.0
## CV residual -327852.3 930230.3 -210544.5 -114830.7 375526.9 -116716.6
## 353 355 358 362 365 373 383
## Predicted 239388.066 472852.9 458326.05 411487.4 216370.2 226273.2 427546.4
## cvpred 240146.028 471450.6 454318.11 407505.9 217141.2 227038.6 423555.8
## price_sold 238000.000 322000.0 485000.00 545000.0 320000.0 255500.0 255000.0
## CV residual -2146.028 -149450.6 30681.89 137494.1 102858.8 28461.4 -168555.8
## 384 393 405 410 424 427 443
## Predicted 368931.1 222332.30 529193.8 527186.5 652981.7 528063.2 300144.51
## cvpred 364973.6 225713.67 523117.3 521111.1 646835.4 524601.1 300868.19
## price_sold 300000.0 135000.00 460000.0 208980.0 499000.0 357500.0 215000.00
## CV residual -64973.6 -90713.67 -63117.3 -312131.1 -147835.4 -167101.1 -85868.19
## 444 455 458 478 479 486 488
## Predicted 369198.10 346582.37 322032.4 200103.60 606946.0 495930.8 495930.8
## cvpred 369882.81 342637.48 320715.2 198269.95 600825.6 491901.6 491901.6
## price_sold 297000.00 325000.00 135000.0 174528.00 394500.0 685000.0 685000.0
## CV residual -72882.81 -17637.48 -185715.2 -23741.95 -206325.6 193098.4 193098.4
## 491 502 508 524 534 537
## Predicted 508644.17 143361.24 419710.71 424408.4 434772.894 447158.58
## cvpred 504607.83 146201.97 413110.77 423033.3 430778.237 445770.71
## price_sold 431000.00 175000.00 440000.00 211973.0 440000.000 420000.00
## CV residual -73607.83 28798.03 26889.23 -211060.3 9221.763 -25770.71
## 551 559 563 572 601 602
## Predicted 222526.145 1132937.4 451902.5 567333.9 253975.0 230154.16
## cvpred 223293.621 1123906.4 447898.1 561235.8 254724.7 230917.33
## price_sold 225000.000 545000.0 249900.0 1285000.0 195000.0 200000.00
## CV residual 1706.379 -578906.4 -197998.1 723764.2 -59724.7 -30917.33
## 616 625 633 646 658 681
## Predicted 111450.924 189872.9 569742.7 120477.20 818657.5 68479.38
## cvpred 116923.444 190658.8 563643.3 123330.85 807775.2 68748.59
## price_sold 109500.000 245900.0 379000.0 208000.00 1432500.0 184000.00
## CV residual -7423.444 55241.2 -184643.3 84669.15 624724.8 115251.41
## 704 712 732 737 740 778 798
## Predicted 468482.9 583124.5 277394.30 277126.7 380927.3 447546.3 259863.26
## cvpred 459241.7 581660.0 278130.82 277863.3 374349.2 440930.6 260609.66
## price_sold 815000.0 155000.0 229900.00 655000.0 200000.0 300000.0 224000.00
## CV residual 355758.3 -426660.0 -48230.82 377136.7 -174349.2 -140930.6 -36609.66
## 799 800 806 810 813 820
## Predicted 506101.5 434639.1 80329.77 387740.4 883027.18 216444.0
## cvpred 502066.6 430644.5 83206.07 386386.0 872108.63 219828.7
## price_sold 133000.0 310000.0 173900.00 263500.0 950000.00 80000.0
## CV residual -369066.6 -120644.5 90693.93 -122886.0 77891.37 -139828.7
## 822 853 861 887 889 891
## Predicted 377361.4 229752.683 232623 331935.4 159434.66 335548.72
## cvpred 378041.5 230516.081 230771 330612.6 162851.52 334223.83
## price_sold 276000.0 230000.000 89000 235000.0 176500.00 283900.00
## CV residual -102041.5 -516.081 -141771 -95612.6 13648.48 -50323.83
## 912 914 926 931 932 946
## Predicted 137546.755 100597.33 231820.07243 276784.5 189070.0 121547.80
## cvpred 143004.549 100848.41 229968.52418 279550.0 189856.3 124400.84
## price_sold 146000.000 175000.00 230000.00000 176000.0 79000.0 200000.00
## CV residual 2995.451 74151.59 31.47582 -103550.0 -110856.3 75599.16
## 957 967 969 970 1006 1017 1021
## Predicted 364187.2 203255.4 452511.6 130647.89 120551.01 93712.25 247016.1
## cvpred 362846.2 204033.7 451120.7 133495.79 126018.39 96581.00 247769.7
## price_sold 510000.0 333000.0 232000.0 200000.00 159000.00 149900.00 467000.0
## CV residual 147153.8 128966.3 -219120.7 66504.21 32981.61 53319.00 219230.3
## 1039 1045 1046 1051 1052 1053
## Predicted 269900.11 402728.8 103421.4 303550.151 237648.34 83615.37
## cvpred 270640.86 401366.0 108898.5 301658.126 238407.29 89103.60
## price_sold 351000.00 565000.0 325000.0 310000.000 275000.00 180000.00
## CV residual 80359.14 163634.0 216101.5 8341.874 36592.71 90896.40
## 1076 1078 1088 1096 1098 1102 1118
## Predicted 410952.08 315728.2 270911.4 372410.5 108299.15 394893.11 215373.41
## cvpred 406970.87 313829.3 269622.9 368451.1 111159.67 390920.96 218758.71
## price_sold 475000.00 461814.0 147400.0 555000.0 140000.00 465000.00 235000.00
## CV residual 68029.13 147984.7 -122222.9 186548.9 28840.33 74079.04 16241.29
## 1141 1147 1160 1162 1183 1194 1212
## Predicted 107570.0 422461.0 261092.786 238183.6 333527.6 279743.1 117339.2
## cvpred 113044.7 418473.3 266480.864 238942.3 326976.3 283092.1 122808.4
## price_sold 320000.0 290000.0 270000.000 339000.0 50013.0 13233.0 250000.0
## CV residual 206955.3 -128473.3 3519.136 100057.7 -276963.3 -269859.1 127191.6
## 1223 1227 1230 1242 1245 1248 1251
## Predicted 185516 180579.0 464630.27 349223.95 213426.1 109845.03 524316.11
## cvpred 188333 183983.9 461203.96 352533.71 214198.7 115318.45 520856.12
## price_sold 370000 197400.0 535000.00 385000.00 70000.0 27886.00 590000.00
## CV residual 181667 13416.1 73796.04 32466.29 -144198.7 -87432.45 69143.88
## 1256 1257 1267 1273 1281 1288
## Predicted 313854.66 524316.11 576240.13 271699.9 225664.13 241870.7
## cvpred 311956.82 520856.12 572750.84 269825.8 223816.06 245241.1
## price_sold 350000.00 590000.00 560200.00 200000.0 168000.00 109000.0
## CV residual 38043.18 69143.88 -12550.84 -69825.8 -55816.06 -136241.1
## 1298 1309 1330 1342 1355 1357
## Predicted 381658.9 325838.9 256249.99 447158.58 245082.513 302285.71
## cvpred 378279.4 326548.0 256998.43 445770.71 248451.041 303008.18
## price_sold 1059162.0 516116.0 214000.00 425500.00 245000.000 280000.00
## CV residual 680882.6 189568.0 -42998.43 -20270.71 -3451.041 -23008.18
##
## Sum of squares = 7.027044e+12 Mean square = 51669442529 n = 136
##
## fold 10
## Observations in test set: 136
## 2 3 6 14 15 30
## Predicted 294330.03 83347.722 462756.1 161308.21 161308.21 83347.722
## cvpred 297522.36 87693.857 464942.8 164963.84 164963.84 87693.857
## price_sold 339900.00 90000.000 170000.0 179000.00 200000.00 90000.000
## CV residual 42377.64 2306.143 -294942.8 14036.16 35036.16 2306.143
## 40 46 49 66 67 72 97
## Predicted 230094.1 318225.30 309854.4 326641.82 377689.1 791431 469058.46
## cvpred 233510.2 320915.44 310869.6 328017.56 377183.0 788227 465692.11
## price_sold 353000.0 250000.00 285000.0 392875.00 520000.0 540000 525000.00
## CV residual 119489.8 -70915.44 -25869.6 64857.44 142817.0 -248227 59307.89
## 101 113 116 119 123 124
## Predicted 351132.41 324039.8 421658.1 345644.9 348931.2 382313.583
## cvpred 350299.82 325005.6 420579.8 346954.5 349810.3 381372.391
## price_sold 450000.00 205000.0 63497.0 55605.0 223000.0 382750.000
## CV residual 99700.18 -120005.6 -357082.8 -291349.5 -126810.3 1377.609
## 129 132 143 147 150 170
## Predicted 301750.4 592953.8 396231.36 235580.95 330414.7 107094.73
## cvpred 303212.8 591278.9 395241.69 238977.91 331777.3 109654.09
## price_sold 167500.0 390000.0 355000.00 325000.00 193000.0 93765.00
## CV residual -135712.8 -201278.9 -40241.69 86022.09 -138777.3 -15889.09
## 171 179 185 186 196 202
## Predicted 815519.5 292175.0 191137.34 338686.048 280948.2 474459.5
## cvpred 812231.5 291966.8 191280.97 340019.837 282064.1 472778.4
## price_sold 528400.0 108500.0 279000.00 350000.000 515000.0 297000.0
## CV residual -283831.5 -183466.8 87719.03 9980.163 232935.9 -175778.4
## 226 236 255 266 270 274
## Predicted 750674.48 1311756.8 530665.2 345184.10 259388.0 509714.8
## cvpred 745908.33 1305902.6 530911.4 346076.29 259293.9 508329.9
## price_sold 792000.00 1900000.0 170000.0 276000.00 140000.0 983750.0
## CV residual 46091.67 594097.4 -360911.4 -70076.29 -119293.9 475420.1
## 292 299 305 324 327 357
## Predicted 606946.0 355963.9 715552.4 110768.01 237380.69 240592.49
## cvpred 604803.5 358522.6 712612.6 111610.53 239067.32 242267.93
## price_sold 325500.0 224000.0 728000.0 202500.00 225000.00 269300.00
## CV residual -279303.5 -134522.6 15387.4 90889.47 -14067.32 27032.07
## 364 366 402 422 438 456 483
## Predicted 739567.03 877807.4 809825.0 652981.7 197098.8 790747.4 357689.8
## cvpred 734839.56 874721.4 804852.9 650678.9 201048.7 786260.7 356834.4
## price_sold 800000.00 1425000.0 1305000.0 499000.0 50000.0 980000.0 500000.0
## CV residual 65160.44 550278.6 500147.1 -151678.9 -151048.7 193739.3 143165.6
## 498 503 513 520 536 543 547
## Predicted 588210.5 406743.50 403993.2 204385.99 454980.4 438118.51 289097.1
## cvpred 586133.3 407421.28 402976.5 204483.48 453786.2 436982.96 288899.5
## price_sold 415000.0 325000.00 168000.0 265000.00 555000.0 407500.00 454500.0
## CV residual -171133.3 -82421.28 -234976.5 60516.52 101213.8 -29482.96 165600.5
## 560 577 621 640 641 659 661
## Predicted 422461 471515.3 353942.07 243864.30 510859.8 818657.5 95391.95
## cvpred 421380 469844.5 355222.73 243824.29 509052.0 813654.5 99696.14
## price_sold 290000 717000.0 435000.00 160100.00 350000.0 1430000.0 173000.00
## CV residual -131380 247155.5 79777.27 -83724.29 -159052.0 616345.5 73303.86
## 670 687 692 693 698 714
## Predicted 145770.08 245008.71 416512.7 464943.49 225068.82 253841.142
## cvpred 148194.75 246668.76 417156.5 462010.45 226798.32 255470.436
## price_sold 248000.00 259900.00 161975.0 415000.00 318900.00 262000.000
## CV residual 99805.25 13231.24 -255181.5 -47010.45 92101.68 6529.564
## 721 725 728 746 748 779
## Predicted 230154.2 271104.54 72374.09 725307.1 453776.01 91095.77
## cvpred 231866.0 272673.71 76758.44 721048.3 452585.92 92006.80
## price_sold 97000.0 286000.00 200100.00 1025000.0 395000.00 104900.00
## CV residual -134866.0 13326.29 123341.56 303951.7 -57585.92 12893.20
## 815 819 823 825 828 832
## Predicted 573354.7 648953.2 395696.06 280873.75 216102.556 270094.0
## cvpred 575575.2 643256.3 394708.26 282408.89 217863.289 269962.6
## price_sold 300000.0 385000.0 360000.00 255000.00 220000.000 450000.0
## CV residual -275575.2 -258256.3 -34708.26 -27408.89 2136.711 180037.4
## 833 840 845 855 862 875 882
## Predicted 299876.9 161159.9 195225.89 347592.95 218109.93 70292.91 407814.76
## cvpred 301345.8 163531.0 197059.34 348476.74 219863.67 72980.46 406365.77
## price_sold 589000.0 125000.0 220000.00 365000.00 202000.00 155100.00 430000.00
## CV residual 287654.2 -38531.0 22940.66 16523.26 -17863.67 82119.54 23634.23
## 909 918 937 941 942 947 953
## Predicted 260933.85 366582.3 202987.7 268428.70 276785.20 209678.97 395696.06
## cvpred 262538.45 363991.8 204794.1 267884.16 276630.52 211462.07 394708.26
## price_sold 290000.00 584900.0 360000.0 320500.00 192000.00 200000.00 360000.00
## CV residual 27461.55 220908.2 155205.9 52615.84 -84630.52 -11462.07 -34708.26
## 962 966 972 979 987 997
## Predicted 169397.71 245008.7 192014.0967 269498.6 304025.43 295059.2
## cvpred 171321.11 246668.8 193858.7271 271073.4 305479.94 296544.9
## price_sold 202000.00 500000.0 194000.0000 384000.0 250000.00 164000.0
## CV residual 30678.89 253331.2 141.2729 112926.6 -55479.94 -132544.9
## 1000 1009 1020 1027 1040 1048 1062
## Predicted 134201.14 399517.0 141889.2 185055.2 445285.0 379101.79 323162.4
## cvpred 138370.15 400219.9 144327.3 186924.1 445828.6 378171.78 324550.2
## price_sold 91000.00 560000.0 457500.0 71050.0 305000.0 319900.00 130500.0
## CV residual -47370.15 159780.1 313172.7 -115874.1 -140828.6 -58271.78 -194050.2
## 1068 1073 1106 1112 1129 1130
## Predicted 354819.5 240592.49 335816.4 73906.18 206942.45 206942.45
## cvpred 355678.1 242267.93 336741.2 76581.14 210439.15 210439.15
## price_sold 690000.0 190000.00 190600.0 32000.00 180000.00 180000.00
## CV residual 334321.9 -52267.93 -146141.2 -44581.14 -30439.15 -30439.15
## 1149 1155 1156 1172 1193 1201
## Predicted 241053.98 396263.1 489374.06 90708.085 275520.8 472377.65
## cvpred 241023.75 388876.1 485936.96 95028.584 277074.5 471122.78
## price_sold 282000.00 253000.0 402000.00 90000.000 67000.0 560000.00
## CV residual 40976.25 -135876.1 -83936.96 -5028.584 -210074.5 88877.22
## 1203 1216 1221 1231 1246 1250 1261
## Predicted 425137.51 270168.42 543050.9 483974.8 236370.1 203329.2 221261.70
## cvpred 424047.17 269617.82 544958.0 485668.7 236356.2 206838.5 224708.53
## price_sold 389000.00 339000.00 110000.0 750000.0 372000.0 10000.0 275000.00
## CV residual -35047.17 69382.18 -434958.0 264331.3 135643.8 -196838.5 50291.47
## 1262 1289 1295 1311 1329 1338
## Predicted 355816.3 304011.6 523840.8 256249.99 256249.99 312872.3
## cvpred 354967.4 302058.1 521987.7 257870.89 257870.89 315581.1
## price_sold 85000.0 165000.0 370000.0 214000.00 214000.00 190000.0
## CV residual -269967.4 -137058.1 -151987.7 -43870.89 -43870.89 -125581.1
## 1344 1363
## Predicted 254450.25 289780.6
## cvpred 257781.48 290865.8
## price_sold 223000.00 170000.0
## CV residual -34781.48 -120865.8
##
## Sum of squares = 4.442851e+12 Mean square = 32668019244 n = 136
##
## Overall (Sum over all 136 folds)
## ms
## 32665358834
# MSPE
n3 = dim(clean_housing)[1]
MSPE3 <- sum((clean_housing$price_sold - KCV3$cvpred)^2) / n3
MSPE3
## [1] 32665358834
# Press Statistic
PRESS3 <- sum((clean_housing$price_sold - KCV3$cvpred)^2)
PRESS3
## [1] 4.462088e+13
# Prediction R-Squared
PRS3 <- 1 - sum((clean_housing$price_sold - KCV3$cvpred)^2) / sum((clean_housing$price_sold -
mean(clean_housing$price_sold))^2)
PRS3
## [1] 0.6187797
Comparing predicted R-Squared for each model
When comparing each of the models below, we see that model 3 has the highest predicted r-squared. This isn’t surprising considering model 3 was selected using the adjusted r-squared during variable selection and is utilizing our cleaned data that contains no outliers.
Our models ability to make predictions shows similar results to our models traditional r-squared that we utilized to predict the goodness of fit of each model excluding model 2 which has a much lower predicted r-squared value.
# Model 1
PRS1
## [1] 0.5105264
summary(housing_model1)$adj.r.squared
## [1] 0.5343469
# Model 2
PRS2
## [1] 0.6187243
summary(housing_model2)$adj.r.squared
## [1] 0.623373
# Model 3
PRS3
## [1] 0.6187797
summary(housing_model3)$adj.r.squared
## [1] 0.6228366
Despite finding that housing_model3 was the strongest, the overall results are not ideal. Having a higher ability to predict new observations and explain the variability in our model would make it more reliable and a stronger predictor of future observations. However, from housing_model3, square footage of a house is the number one predictor of price with number of bedrooms and number of bathrooms following as number two and three, respectively. It was also found that lot size, house age, and number of parking spaces have little influence on house prices. One recommendation from these findings to drive the best value for buyers would be to search for houses that have a larger lot size and smaller square footage. Taking this approach will keep housing prices lower but will provide the property space needed to expand on the existing home. This expansion would not only drive up the value of the home by increasing the square footage but would allow for a reduction in the amount spent on purchasing the house.
For future analysis, there are a few key changes that would help improve the model creation and predictability of the housing market. The first would be to narrow the scope of the dataset. If a specific buyer type or price range is chosen, the ability to predict costs may increase. For example, houses sold for $7 million are outside of the “typical” buyer and create noise in a model. If the typical buyer is the focus, the data collection process may yield better results. Second, increasing the sample size provides more information to work with that will in turn produce better, more accurate models. The last recommendation, which is the most important, is data quality. During the cleaning process many mistakes and duplicate values were found in the data. While corrected, it is not guaranteed that all mistakes will be caught. Finding ways to source better data, perhaps through established organizations who store that data, may help drive better quality data and in turn better models.