library(forecast)
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(readxl)
library(ggplot2)
df <- read.csv("flinfo2022.csv") #load the data
Avg_age_2021 <- read.csv("Avg_age_2021.csv")
vaC_R <- read.csv("Vax Rate.csv")
Avg_age_2021 <-data.frame(Avg_age_2021)
vaC_R <- data.frame(vaC_R)
df <- df[,-c(1,2,4:6,11:13)] #keep numerical values only
df <- df %>%
rename(County = Admin2) # Name the County Column
Avg_age_2021 <- Avg_age_2021[,-1]
vaC_R <- vaC_R[,-1]
df <- na.omit(df) # delete NA values
Pbed <- read.csv("PatientBed.csv")
Pbed <- Pbed[,-c(2,5,6)]
# rename the column
Pbed <- Pbed %>%
rename(BedInUse = X, InUsePercentage = Inpatient.beds)
# remove "County" in first column
FN <- function(County) {
C_name <- gsub(" County", "", County)
return(C_name)
}
Pbed$County <- FN(Pbed$County)
# Remove extra info after num
FN2 <- function(Bed) {
comma_loc <- regexpr("o", Bed)
Number <- substr(Bed, 1, comma_loc-1)
return(Number)
}
Pbed$BedInUse <- FN2(Pbed$BedInUse)
Pbed$InUsePercentage <- as.numeric(Pbed$InUsePercentage)
## Warning: NAs introduced by coercion
Pbed$BedInUse <- as.numeric(Pbed$BedInUse)
## Warning: NAs introduced by coercion
Pbed <- na.omit(Pbed)
df$Avg_age <- Avg_age_2021
df$Vac_R <- vaC_R
# merge two dataset group by County
merged_df <- merge(df, Pbed, by = "County", all = TRUE)
df <- na.omit(merged_df)
df$AllBed <- df$BedInUse/df$InUsePercentage
Pred.lm <- lm(Deaths ~ population + Confirmed + Vac_R
+ Avg_age + InUsePercentage + AllBed
, data = df)
summary(Pred.lm)
##
## Call:
## lm(formula = Deaths ~ population + Confirmed + Vac_R + Avg_age +
## InUsePercentage + AllBed, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -446.08 -91.53 3.98 76.61 724.30
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.514e+01 2.607e+02 0.365 0.71736
## population 5.004e-03 1.446e-03 3.461 0.00147 **
## Confirmed -9.293e-03 4.881e-03 -1.904 0.06542 .
## Vac_R -4.136e+02 3.631e+02 -1.139 0.26271
## Avg_age 7.685e-01 5.630e+00 0.137 0.89223
## InUsePercentage 3.020e+02 2.097e+02 1.440 0.15893
## AllBed 5.930e-01 1.878e-01 3.158 0.00333 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 215 on 34 degrees of freedom
## Multiple R-squared: 0.8849, Adjusted R-squared: 0.8646
## F-statistic: 43.57 on 6 and 34 DF, p-value: 1.484e-14
#According to the summary above, the model should be
Predl.lm <- lm(Deaths ~ population + Incident_Rate + Vac_R + AllBed
, data = df)
summary(Predl.lm)
##
## Call:
## lm(formula = Deaths ~ population + Incident_Rate + Vac_R + AllBed,
## data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -438.71 -102.98 -6.16 103.49 778.35
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.765e+02 3.899e+02 2.505 0.01692 *
## population 2.557e-03 4.702e-04 5.438 3.92e-06 ***
## Incident_Rate -1.941e-02 9.312e-03 -2.085 0.04425 *
## Vac_R -6.124e+02 3.506e+02 -1.747 0.08924 .
## AllBed 5.743e-01 1.855e-01 3.095 0.00379 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 214.9 on 36 degrees of freedom
## Multiple R-squared: 0.8783, Adjusted R-squared: 0.8648
## F-statistic: 64.94 on 4 and 36 DF, p-value: 5.775e-16
# look at the predicted values
y_hat <- predict(Predl.lm, se.fit = TRUE)
names(y_hat)
## [1] "fit" "se.fit" "df" "residual.scale"
# adding the predictions to the mydata data frame
df$Predictions <- y_hat$fit
# compare the actuals versus the predicted values
ggplot(data = df, aes(Predictions, Deaths)) +
geom_point() +
geom_smooth(method = "lm")
## `geom_smooth()` using formula = 'y ~ x'
