data(mtcars) head(mtcars)
mpg cyl disp hp drat wt qsec vs am gear carb Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2 Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
mod <- lm(mpg ~ wt, data = mtcars)
x= mtcars$wt
y = mtcars$mpg
xax <- list(title = "Weight",
titlefont = list(family = "Modern Computer Roman"),
range = c(0, max(x))
)
yax <- list(title = "Miles per Gallon",
titlefont = list(family = "Modern Computer Roman"),
range = c(0, max(y))
)
linPlot <- plot_ly(x = x, y = y, type = "scatter", mode = "markers", name = "data",
height = 630, width = 630)%>%
add_lines(x = x, y = fitted(mod), named = "fitted")%>%
layout(xaxis = xax, yaxis = yax)
config(linPlot, displaylogo = T)
Warning: 'scatter' objects don't have these attributes: 'named' Valid attributes include: 'cliponaxis', 'connectgaps', 'customdata', 'customdatasrc', 'dx', 'dy', 'error_x', 'error_y', 'fill', 'fillcolor', 'fillpattern', 'groupnorm', 'hoverinfo', 'hoverinfosrc', 'hoverlabel', 'hoveron', 'hovertemplate', 'hovertemplatesrc', 'hovertext', 'hovertextsrc', 'ids', 'idssrc', 'legendgroup', 'legendgrouptitle', 'legendrank', 'line', 'marker', 'meta', 'metasrc', 'mode', 'name', 'opacity', 'orientation', 'selected', 'selectedpoints', 'showlegend', 'stackgaps', 'stackgroup', 'stream', 'text', 'textfont', 'textposition', 'textpositionsrc', 'textsrc', 'texttemplate', 'texttemplatesrc', 'transforms', 'type', 'uid', 'uirevision', 'unselected', 'visible', 'x', 'x0', 'xaxis', 'xcalendar', 'xhoverformat', 'xperiod', 'xperiod0', 'xperiodalignment', 'xsrc', 'y', 'y0', 'yaxis', 'ycalendar', 'yhoverformat', 'yperiod', 'yperiod0', 'yperiodalignment', 'ysrc', 'key', 'set', 'frame', 'transforms', '_isNestedKey', '_isSimpleKey', '_isGraticule', '_bbox'
Simple Linear Regression(ggplot) of the flower dataset
flowers <- read.csv("flower.csv", stringsAsFactors = T, header = T, sep = ",")
data(flowers)
Warning in data(flowers): data set 'flowers' not found
head(flowers)
treat nitrogen block height weight leafarea shootarea flowers 1 tip medium 1 7.5 7.62 11.7 31.9 1 2 tip medium 1 10.7 12.14 14.1 46.0 10 3 tip medium 1 11.2 12.76 7.1 66.7 10 4 tip medium 1 10.4 8.78 11.9 20.3 1 5 tip medium 1 10.4 13.58 14.5 26.9 4 6 tip medium 1 9.8 10.08 12.2 72.7 9
x = flowers$weight y = flowers$height flowerData <- lm(height ~ weight, data = flowers) summary(flowerData)
Call:
lm(formula = height ~ weight, data = flowers)
Residuals:
Min 1Q Median 3Q Max
-7.0010 -2.3129 -0.3104 2.2436 8.7842
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 4.12030 1.00744 4.090 9.1e-05 ***
weight 0.22372 0.07879 2.839 0.00554 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.063 on 94 degrees of freedom
Multiple R-squared: 0.07899, Adjusted R-squared: 0.06919
F-statistic: 8.062 on 1 and 94 DF, p-value: 0.005541
ggplot(flowers,aes(x = x, y = y)) +
geom_point(color = "darkgreen") + geom_smooth(method = "lm", color = "gold") +
labs(x = "Flower Weight", y = "Flower Height",
title = "Linear Regression of Flower Weight and Height")
`geom_smooth()` using formula = 'y ~ x'
Simple Linear Regression(ggplot) of the mtcars dataset
data(mtcars) head(mtcars)
mpg cyl disp hp drat wt qsec vs am gear carb Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2 Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
x = mtcars$hp
y = mtcars$qsec
manualCarMod <- lm(y ~ x, data = mtcars)
ggplot(mtcars, aes(x = x, y = y)) +
geom_point() + geom_smooth(method = "lm") +
labs(x = "Horse Power", y = " 1/4 Mile Time",
title = "Relationship between Horse Power and 1/4 Mile Time")
`geom_smooth()` using formula = 'y ~ x'
Simple Linear Regression General
\(\hat{y} = \beta_0 + \beta_1\cdot \text{x}\)
\(\beta_0 = \text{y-intercept}\)
\(\beta_1 = \text{slope of the line}\)
\(\hat{y} = \text{estimated value of y for some value of x}\)
\(\text{This equation represents the Simple Linear Regression derived from}\) \(\text{the slope-intercept form of the linear equation y = mx + b}\) \(\text{where the slope is based on how steep a line is, change in y over change}\) \(\text{in x. If the slope is positive, the line is moving from bottom left to right}\) \(\text{if the slope is negative, the line is moving from top left to bottom right}\)
\(\text{To calculate slope, we would do}\)
\(\beta_1 = \text{r}\cdot \frac{s_{y}} {s_{x}}\)
\(\text{r} = \text{Pearson's correlation coefficient between x and y}\)
\(s_y = \text{standard deviation of y}\)
\(s_x = \text{standard deviation of x}\)
\(\text{To calculate the y-intercept, we would do: }\)
\(\beta_0 = \bar{y} - \beta_1\cdot \bar{x}\)
\(\bar{y} = \text{mean of y}\)
\(\bar{x} = \text{mean of x}\)
\(\beta_1 = \text{slope}\)
General Residual Equation and Sum of Squared Residuals Equation
\(\text{When making predictions such as the predicted y value or}\)
\(\text{line of best fit, we will generally expect to have some error. These}\)
\(\text{errors in regression prediction are called residuals. Residuals are}\)
\(\text{calculated by finding the difference of an individual's observed y value}\)
\(\text{and thir corresponding predicted y value. Hence, we can expect there to}\)
\(\text{be some error for each indivudal, but we need to construct regression}\)
\(\text{lines that minimizes the squared residuals}\)
\(\text{To calculate residuals, we would do}\)
\(e_{i} = y_{i} - \hat{y_{i}}\)
\(y_{i} = \text{actual value of y for ith observation}\)
\(\hat{y_{i}} = \text{prediced value of y for ith observation}\)
\(\text{To calculate the sum of squared residuals, we would do}\)
\(\text{SSE} = \sum{{(y - \hat{y})}^2}\)
\(\text{The sum of squared residual calculates the accuracy of}\)
\(\text{a simple linear regression model. We calculate this sum}\)
\(\text{by finding the sum of the squared differences between the}\)
\(\text{ovserved values of y and the predict values of y}\)
\(\text{By calculating measure of SSE, we would get a better idea}\)
\(\text{of how well the regression model fits the data. A low SSE}\)
\(\text{means we have a good fitting model, wheras a high SSE}\)
\(\text{indicates we have a poor fitting model}\)
Example Code of Creating Simple Linear Regression Models(ggplot)
\(\text{This sample code is the program I created to create a ggplot of}\)
\(\text{a simple linear regression model of the relationship}\)
\(\text{between flower weight and height}\)
flowers <- read.csv("flower.csv", stringsAsFactors = T, header = T, sep = ",")
#data(flowers)
#head(flowers)
#These are the variables that store the data in columns flower$weight and
#flower$height, where x contains the data for each flower weight, and y contains
#the data for each flower height. The scaling of the x-axis is based on the
#range from 0 to the max flower weight.
#The scaling of the y-axis is based on the range from 0 to the max flower height.
x = flowers$weight
y = flowers$height
flowerData <- lm(height ~ weight, data = flowers)
summary(flowerData)
Call:
lm(formula = height ~ weight, data = flowers)
Residuals:
Min 1Q Median 3Q Max
-7.0010 -2.3129 -0.3104 2.2436 8.7842
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 4.12030 1.00744 4.090 9.1e-05 ***
weight 0.22372 0.07879 2.839 0.00554 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.063 on 94 degrees of freedom
Multiple R-squared: 0.07899, Adjusted R-squared: 0.06919
F-statistic: 8.062 on 1 and 94 DF, p-value: 0.005541
#Creates the ggplot # ggplot(flowers,aes(x = x, y = y)) + # geom_point(color = "darkgreen") + geom_smooth(method = "lm", color = "gold") + # labs(x = "Flower Weight", y = "Flower Height", # title = "Linear Regression of Flower Weight and Height")
Example Code of creating Simple Linear Regression Model(plot_ly)
\(\text{This sample code is the program I created to create a plotly plot of}\)
\(\text{a simple linear regression model of the relationship}\)
\(\text{between car weight and miles per gallon}\)
data(mtcars) head(mtcars)
mpg cyl disp hp drat wt qsec vs am gear carb Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2 Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
mod <- lm(mpg ~ wt, data = mtcars)
#These are the variables that store the data in columns mtcars$weight and
#flower$mpg, where x contains the data for the weights of each car, and
#y contains the data for the miles per gallon rates of each cat
x= mtcars$wt
y = mtcars$mpg
#This section of code consists of the title and ranges of the scales
#for the x-axis and y-axis of the simple linear regression model
xax <- list(title = "Weight",
titlefont = list(family = "Modern Computer Roman"),
range = c(0, max(x))
)
yax <- list(title = "Miles per Gallon",
titlefont = list(family = "Modern Computer Roman"),
range = c(0, max(y))
)
#This portion of the code creates the plotly plot
# linPlot <- plot_ly(x = x, y = y, type = "scatter", mode = "markers", name = "data",
# height = 630, width = 630)%>%
# add_lines(x = x, y = fitted(mod), named = "fitted")%>%
# layout(xaxis = xax, yaxis = yax)
#
# config(linPlot, displaylogo = T)