# Load necessary libraries
library(MASS)
library(ISLR2)
##
## Attaching package: 'ISLR2'
## The following object is masked from 'package:MASS':
##
## Boston
# Load the Boston dataset
data(Boston)
# Explore the dataset
head(Boston)
## crim zn indus chas nox rm age dis rad tax ptratio lstat medv
## 1 0.00632 18 2.31 0 0.538 6.575 65.2 4.0900 1 296 15.3 4.98 24.0
## 2 0.02731 0 7.07 0 0.469 6.421 78.9 4.9671 2 242 17.8 9.14 21.6
## 3 0.02729 0 7.07 0 0.469 7.185 61.1 4.9671 2 242 17.8 4.03 34.7
## 4 0.03237 0 2.18 0 0.458 6.998 45.8 6.0622 3 222 18.7 2.94 33.4
## 5 0.06905 0 2.18 0 0.458 7.147 54.2 6.0622 3 222 18.7 5.33 36.2
## 6 0.02985 0 2.18 0 0.458 6.430 58.7 6.0622 3 222 18.7 5.21 28.7
# Fit a simple linear regression model (medv ~ lstat)
lm.fit <- lm(medv ~ lstat, data = Boston)
# Print the summary of the linear regression model
summary(lm.fit)
##
## Call:
## lm(formula = medv ~ lstat, data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.168 -3.990 -1.318 2.034 24.500
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 34.55384 0.56263 61.41 <2e-16 ***
## lstat -0.95005 0.03873 -24.53 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.216 on 504 degrees of freedom
## Multiple R-squared: 0.5441, Adjusted R-squared: 0.5432
## F-statistic: 601.6 on 1 and 504 DF, p-value: < 2.2e-16
# Access various components of the linear regression model
names(lm.fit)
## [1] "coefficients" "residuals" "effects" "rank"
## [5] "fitted.values" "assign" "qr" "df.residual"
## [9] "xlevels" "call" "terms" "model"
coef(lm.fit)
## (Intercept) lstat
## 34.5538409 -0.9500494
confint(lm.fit)
## 2.5 % 97.5 %
## (Intercept) 33.448457 35.6592247
## lstat -1.026148 -0.8739505
# Make predictions with confidence intervals
predict(lm.fit, data.frame(lstat = c(5, 10, 15)), interval = "confidence")
## fit lwr upr
## 1 29.80359 29.00741 30.59978
## 2 25.05335 24.47413 25.63256
## 3 20.30310 19.73159 20.87461
predict(lm.fit, data.frame(lstat = c(5, 10, 15)), interval = "prediction")
## fit lwr upr
## 1 29.80359 17.565675 42.04151
## 2 25.05335 12.827626 37.27907
## 3 20.30310 8.077742 32.52846
# Diagnostic plots for the linear regression model
par(mfrow = c(2, 2))
plot(lm.fit)
# Fit a multiple linear regression model (medv ~ .)
lm.fit.all <- lm(medv ~ ., data = Boston)
summary(lm.fit.all)
##
## Call:
## lm(formula = medv ~ ., data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.1304 -2.7673 -0.5814 1.9414 26.2526
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 41.617270 4.936039 8.431 3.79e-16 ***
## crim -0.121389 0.033000 -3.678 0.000261 ***
## zn 0.046963 0.013879 3.384 0.000772 ***
## indus 0.013468 0.062145 0.217 0.828520
## chas 2.839993 0.870007 3.264 0.001173 **
## nox -18.758022 3.851355 -4.870 1.50e-06 ***
## rm 3.658119 0.420246 8.705 < 2e-16 ***
## age 0.003611 0.013329 0.271 0.786595
## dis -1.490754 0.201623 -7.394 6.17e-13 ***
## rad 0.289405 0.066908 4.325 1.84e-05 ***
## tax -0.012682 0.003801 -3.337 0.000912 ***
## ptratio -0.937533 0.132206 -7.091 4.63e-12 ***
## lstat -0.552019 0.050659 -10.897 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.798 on 493 degrees of freedom
## Multiple R-squared: 0.7343, Adjusted R-squared: 0.7278
## F-statistic: 113.5 on 12 and 493 DF, p-value: < 2.2e-16
# Check for multicollinearity using VIF
library(car)
## Loading required package: carData
vif(lm.fit.all)
## crim zn indus chas nox rm age dis
## 1.767486 2.298459 3.987181 1.071168 4.369093 1.912532 3.088232 3.954037
## rad tax ptratio lstat
## 7.445301 9.002158 1.797060 2.870777
# Fit a model without the 'age' variable
lm.fit1 <- lm(medv ~ . - age, data = Boston)
summary(lm.fit1)
##
## Call:
## lm(formula = medv ~ . - age, data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.1851 -2.7330 -0.6116 1.8555 26.3838
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 41.525128 4.919684 8.441 3.52e-16 ***
## crim -0.121426 0.032969 -3.683 0.000256 ***
## zn 0.046512 0.013766 3.379 0.000785 ***
## indus 0.013451 0.062086 0.217 0.828577
## chas 2.852773 0.867912 3.287 0.001085 **
## nox -18.485070 3.713714 -4.978 8.91e-07 ***
## rm 3.681070 0.411230 8.951 < 2e-16 ***
## dis -1.506777 0.192570 -7.825 3.12e-14 ***
## rad 0.287940 0.066627 4.322 1.87e-05 ***
## tax -0.012653 0.003796 -3.333 0.000923 ***
## ptratio -0.934649 0.131653 -7.099 4.39e-12 ***
## lstat -0.547409 0.047669 -11.483 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.794 on 494 degrees of freedom
## Multiple R-squared: 0.7343, Adjusted R-squared: 0.7284
## F-statistic: 124.1 on 11 and 494 DF, p-value: < 2.2e-16
# Interaction terms in regression
summary(lm(medv ~ lstat * age, data = Boston))
##
## Call:
## lm(formula = medv ~ lstat * age, data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.806 -4.045 -1.333 2.085 27.552
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 36.0885359 1.4698355 24.553 < 2e-16 ***
## lstat -1.3921168 0.1674555 -8.313 8.78e-16 ***
## age -0.0007209 0.0198792 -0.036 0.9711
## lstat:age 0.0041560 0.0018518 2.244 0.0252 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.149 on 502 degrees of freedom
## Multiple R-squared: 0.5557, Adjusted R-squared: 0.5531
## F-statistic: 209.3 on 3 and 502 DF, p-value: < 2.2e-16
# Log transformation
summary(lm(medv ~ log(rm), data = Boston))
##
## Call:
## lm(formula = medv ~ log(rm), data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -19.487 -2.875 -0.104 2.837 39.816
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -76.488 5.028 -15.21 <2e-16 ***
## log(rm) 54.055 2.739 19.73 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.915 on 504 degrees of freedom
## Multiple R-squared: 0.4358, Adjusted R-squared: 0.4347
## F-statistic: 389.3 on 1 and 504 DF, p-value: < 2.2e-16
# Load the Carseats dataset
data(Carseats)
# Fit a multiple linear regression model with interactions
lm.fit.carseats <- lm(Sales ~ . + Income:Advertising + Price:Age, data = Carseats)
summary(lm.fit.carseats)
##
## Call:
## lm(formula = Sales ~ . + Income:Advertising + Price:Age, data = Carseats)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.9208 -0.7503 0.0177 0.6754 3.3413
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.5755654 1.0087470 6.519 2.22e-10 ***
## CompPrice 0.0929371 0.0041183 22.567 < 2e-16 ***
## Income 0.0108940 0.0026044 4.183 3.57e-05 ***
## Advertising 0.0702462 0.0226091 3.107 0.002030 **
## Population 0.0001592 0.0003679 0.433 0.665330
## Price -0.1008064 0.0074399 -13.549 < 2e-16 ***
## ShelveLocGood 4.8486762 0.1528378 31.724 < 2e-16 ***
## ShelveLocMedium 1.9532620 0.1257682 15.531 < 2e-16 ***
## Age -0.0579466 0.0159506 -3.633 0.000318 ***
## Education -0.0208525 0.0196131 -1.063 0.288361
## UrbanYes 0.1401597 0.1124019 1.247 0.213171
## USYes -0.1575571 0.1489234 -1.058 0.290729
## Income:Advertising 0.0007510 0.0002784 2.698 0.007290 **
## Price:Age 0.0001068 0.0001333 0.801 0.423812
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.011 on 386 degrees of freedom
## Multiple R-squared: 0.8761, Adjusted R-squared: 0.8719
## F-statistic: 210 on 13 and 386 DF, p-value: < 2.2e-16
# Contrasts for the ShelveLoc variable
attach(Carseats)
contrasts(ShelveLoc)
## Good Medium
## Bad 0 0
## Good 1 0
## Medium 0 1
#Detach the dataset
detach(Carseats)
#exercise 8
# Load required libraries
library(ISLR2)
# Load the Auto dataset
data(Auto)
# (a) Perform simple linear regression
lm.fit <- lm(mpg ~ horsepower, data = Auto)
# Display the summary of the linear regression model
summary(lm.fit)
##
## Call:
## lm(formula = mpg ~ horsepower, data = Auto)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.5710 -3.2592 -0.3435 2.7630 16.9240
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 39.935861 0.717499 55.66 <2e-16 ***
## horsepower -0.157845 0.006446 -24.49 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.906 on 390 degrees of freedom
## Multiple R-squared: 0.6059, Adjusted R-squared: 0.6049
## F-statistic: 599.7 on 1 and 390 DF, p-value: < 2.2e-16
# (b) Plot the response and the predictor
plot(Auto$horsepower, Auto$mpg, xlab = "Horsepower", ylab = "MPG", main = "Scatterplot of MPG vs Horsepower")
abline(lm.fit, col = "red")
# (c) Diagnostic plots
par(mfrow = c(2, 2))
plot(lm.fit)
# (d) Predicted mpg associated with a horsepower of 98
horsepower_98 <- data.frame(horsepower = 98)
predicted_mpg <- predict(lm.fit, newdata = horsepower_98)
# Confidence and prediction intervals
intervals <- predict(lm.fit, newdata = horsepower_98, interval = "confidence")
# Display results
cat("Predicted MPG for horsepower = 98:", predicted_mpg, "\n")
## Predicted MPG for horsepower = 98: 24.46708
cat("95% Confidence Interval:", intervals[, 2], "to", intervals[, 3], "\n")
## 95% Confidence Interval: 23.97308 to 24.96108
#exercise10
# Load required libraries
library(ISLR2)
# Load the Carseats dataset
data(Carseats)
# (a) Fit a multiple regression model
lm.fit <- lm(Sales ~ Price + Urban + US, data = Carseats)
# (b) Interpretation of coefficients
summary(lm.fit)
##
## Call:
## lm(formula = Sales ~ Price + Urban + US, data = Carseats)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.9206 -1.6220 -0.0564 1.5786 7.0581
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.043469 0.651012 20.036 < 2e-16 ***
## Price -0.054459 0.005242 -10.389 < 2e-16 ***
## UrbanYes -0.021916 0.271650 -0.081 0.936
## USYes 1.200573 0.259042 4.635 4.86e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.472 on 396 degrees of freedom
## Multiple R-squared: 0.2393, Adjusted R-squared: 0.2335
## F-statistic: 41.52 on 3 and 396 DF, p-value: < 2.2e-16
# (c) Write out the model in equation form
# Sales = b0 + b1 * Price + b2 * Urban_Yes + b3 * US_Yes + epsilon
# (d) Hypothesis testing for each predictor
# Use summary(lm.fit) and look for "Pr(>|t|)" values.
# (e) Fit a smaller model
lm.fit_smaller <- lm(Sales ~ Price + Urban + US, data = Carseats)
# (f) Model fit comparison
summary(lm.fit)
##
## Call:
## lm(formula = Sales ~ Price + Urban + US, data = Carseats)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.9206 -1.6220 -0.0564 1.5786 7.0581
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.043469 0.651012 20.036 < 2e-16 ***
## Price -0.054459 0.005242 -10.389 < 2e-16 ***
## UrbanYes -0.021916 0.271650 -0.081 0.936
## USYes 1.200573 0.259042 4.635 4.86e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.472 on 396 degrees of freedom
## Multiple R-squared: 0.2393, Adjusted R-squared: 0.2335
## F-statistic: 41.52 on 3 and 396 DF, p-value: < 2.2e-16
summary(lm.fit_smaller)
##
## Call:
## lm(formula = Sales ~ Price + Urban + US, data = Carseats)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.9206 -1.6220 -0.0564 1.5786 7.0581
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.043469 0.651012 20.036 < 2e-16 ***
## Price -0.054459 0.005242 -10.389 < 2e-16 ***
## UrbanYes -0.021916 0.271650 -0.081 0.936
## USYes 1.200573 0.259042 4.635 4.86e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.472 on 396 degrees of freedom
## Multiple R-squared: 0.2393, Adjusted R-squared: 0.2335
## F-statistic: 41.52 on 3 and 396 DF, p-value: < 2.2e-16
# (g) 95% confidence intervals for coefficients
confint(lm.fit_smaller)
## 2.5 % 97.5 %
## (Intercept) 11.76359670 14.32334118
## Price -0.06476419 -0.04415351
## UrbanYes -0.55597316 0.51214085
## USYes 0.69130419 1.70984121
# (h) Check for outliers or high leverage observations
par(mfrow = c(2, 2))
plot(lm.fit_smaller)
#exercise14
# (a) Create the linear model
set.seed(1)
x1 <- runif(100)
x2 <- 0.5 * x1 + rnorm(100) / 10
y <- 2 + 2 * x1 + 0.3 * x2 + rnorm(100)
# (b) Correlation and scatterplot
cor(x1, x2)
## [1] 0.8351212
plot(x1, x2, main = "Scatterplot of x1 and x2", xlab = "x1", ylab = "x2")
# (c) Fit least squares regression to predict y using x1 and x2
lm.fit <- lm(y ~ x1 + x2)
summary(lm.fit)
##
## Call:
## lm(formula = y ~ x1 + x2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8311 -0.7273 -0.0537 0.6338 2.3359
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.1305 0.2319 9.188 7.61e-15 ***
## x1 1.4396 0.7212 1.996 0.0487 *
## x2 1.0097 1.1337 0.891 0.3754
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.056 on 97 degrees of freedom
## Multiple R-squared: 0.2088, Adjusted R-squared: 0.1925
## F-statistic: 12.8 on 2 and 97 DF, p-value: 1.164e-05
# (d) Fit least squares regression to predict y using only x1
lm.fit_x1 <- lm(y ~ x1)
summary(lm.fit_x1)
##
## Call:
## lm(formula = y ~ x1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.89495 -0.66874 -0.07785 0.59221 2.45560
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.1124 0.2307 9.155 8.27e-15 ***
## x1 1.9759 0.3963 4.986 2.66e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.055 on 98 degrees of freedom
## Multiple R-squared: 0.2024, Adjusted R-squared: 0.1942
## F-statistic: 24.86 on 1 and 98 DF, p-value: 2.661e-06
# (e) Fit least squares regression to predict y using only x2
lm.fit_x2 <- lm(y ~ x2)
summary(lm.fit_x2)
##
## Call:
## lm(formula = y ~ x2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.62687 -0.75156 -0.03598 0.72383 2.44890
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3899 0.1949 12.26 < 2e-16 ***
## x2 2.8996 0.6330 4.58 1.37e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.072 on 98 degrees of freedom
## Multiple R-squared: 0.1763, Adjusted R-squared: 0.1679
## F-statistic: 20.98 on 1 and 98 DF, p-value: 1.366e-05
# (f) Interpretation of results
# Compare coefficients and hypothesis testing results from (c), (d), and (e)
# (g) Add one mismeasured observation
x1 <- c(x1, 0.1)
x2 <- c(x2, 0.8)
y <- c(y, 6)
# Re-fit the linear models
lm.fit_new <- lm(y ~ x1 + x2)
summary(lm.fit_new)
##
## Call:
## lm(formula = y ~ x1 + x2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.73348 -0.69318 -0.05263 0.66385 2.30619
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2267 0.2314 9.624 7.91e-16 ***
## x1 0.5394 0.5922 0.911 0.36458
## x2 2.5146 0.8977 2.801 0.00614 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.075 on 98 degrees of freedom
## Multiple R-squared: 0.2188, Adjusted R-squared: 0.2029
## F-statistic: 13.72 on 2 and 98 DF, p-value: 5.564e-06
lm.fit_x1_new <- lm(y ~ x1)
summary(lm.fit_x1_new)
##
## Call:
## lm(formula = y ~ x1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.8897 -0.6556 -0.0909 0.5682 3.5665
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.2569 0.2390 9.445 1.78e-15 ***
## x1 1.7657 0.4124 4.282 4.29e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.111 on 99 degrees of freedom
## Multiple R-squared: 0.1562, Adjusted R-squared: 0.1477
## F-statistic: 18.33 on 1 and 99 DF, p-value: 4.295e-05
lm.fit_x2_new <- lm(y ~ x2)
summary(lm.fit_x2_new)
##
## Call:
## lm(formula = y ~ x2)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.64729 -0.71021 -0.06899 0.72699 2.38074
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3451 0.1912 12.264 < 2e-16 ***
## x2 3.1190 0.6040 5.164 1.25e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.074 on 99 degrees of freedom
## Multiple R-squared: 0.2122, Adjusted R-squared: 0.2042
## F-statistic: 26.66 on 1 and 99 DF, p-value: 1.253e-06
# Check the influence of the new observation
influencePlot(lm.fit_new)
## StudRes Hat CookD
## 11 -0.2489926 0.06007045 0.001333503
## 55 -2.2721101 0.04102604 0.070619547
## 82 -2.6440366 0.01803646 0.040336698
## 101 2.1134793 0.41472837 1.019021038
influencePlot(lm.fit_x1_new)
## StudRes Hat CookD
## 27 0.4791689 0.04437352 0.005372491
## 47 1.0630915 0.04301726 0.025367592
## 55 -2.3782673 0.03693100 0.103577409
## 82 -2.7027733 0.01534390 0.053508995
## 101 3.4384051 0.03347156 0.184539234
influencePlot(lm.fit_x2_new)
## StudRes Hat CookD
## 6 -1.395202 0.05673185 0.05798336
## 21 2.299499 0.03005459 0.07852116
## 55 -2.332104 0.03700440 0.10001086
## 82 -2.545873 0.01028483 0.03190995
## 101 1.140964 0.10131060 0.07315390