# 3.6.1 to 3.6.6.
# Load the ISLR2 library
library(ISLR2)
# Load the Boston dataset
data("Boston")
# Attach the Boston dataset
attach(Boston)
# Fit a simple linear regression model with medv as response and lstat as predictor
lm.fit <- lm(medv ~ lstat, data = Boston)
# View basic information about the model
lm.fit
##
## Call:
## lm(formula = medv ~ lstat, data = Boston)
##
## Coefficients:
## (Intercept) lstat
## 34.55 -0.95
# View detailed information about the 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
# Extract coefficients using coef() function
coef(lm.fit)
## (Intercept) lstat
## 34.5538409 -0.9500494
# Calculate confidence intervals for coefficient estimates
confint(lm.fit)
## 2.5 % 97.5 %
## (Intercept) 33.448457 35.6592247
## lstat -1.026148 -0.8739505
# Predict medv for specific values of lstat 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
# Plot medv and lstat along with the regression line
plot(lstat, medv)
abline(lm.fit)
# Experiment with additional settings for plotting lines and points
abline(lm.fit, lwd = 3)
abline(lm.fit, lwd = 3, col = "red")
plot(lstat, medv, col = "red")
plot(lstat, medv, pch = 20)
plot(lstat, medv, pch = "+")
plot(1:20, 1:20, pch = 1:20)
# Diagnostic plots
par(mfrow = c(2, 2))
plot(lm.fit)
# Plot residuals against fitted values and studentized residuals
plot(predict(lm.fit), residuals(lm.fit))
plot(predict(lm.fit), rstudent(lm.fit))
# Compute leverage statistics and plot
plot(hatvalues(lm.fit))
which.max(hatvalues(lm.fit))
## 375
## 375
# Load the ISLR2 library
library(ISLR2)
# Load the Boston dataset
data("Boston")
# Fit a multiple linear regression model with medv as response and lstat and age as predictors
lm.fit <- lm(medv ~ lstat + age, data = Boston)
# View detailed information about the model
summary(lm.fit)
##
## Call:
## lm(formula = medv ~ lstat + age, data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.981 -3.978 -1.283 1.968 23.158
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 33.22276 0.73085 45.458 < 2e-16 ***
## lstat -1.03207 0.04819 -21.416 < 2e-16 ***
## age 0.03454 0.01223 2.826 0.00491 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.173 on 503 degrees of freedom
## Multiple R-squared: 0.5513, Adjusted R-squared: 0.5495
## F-statistic: 309 on 2 and 503 DF, p-value: < 2.2e-16
# Fit a multiple linear regression model using all predictors
lm.fit.all <- lm(medv ~ ., data = Boston)
# View detailed information about the model
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
# Fit a multiple linear regression model excluding the 'age' predictor
lm.fit.excluded <- lm(medv ~ . - age, data = Boston)
# View detailed information about the model
summary(lm.fit.excluded)
##
## 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
# Alternatively, use the update() function to exclude 'age' predictor
lm.fit.updated <- update(lm.fit, . ~ . - age)
# View detailed information about the updated model
summary(lm.fit.updated)
##
## 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
# Load the ISLR2 library
library(ISLR2)
# Load the Boston dataset
data("Boston")
# Fit a linear model with interaction term between lstat and age
lm_interaction <- lm(medv ~ lstat * age, data = Boston)
# View detailed information about the model
summary(lm_interaction)
##
## 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
# Load the ISLR2 library
library(ISLR2)
# Load the Boston dataset
data("Boston")
# Fit a linear model with lstat and lstat^2 as predictors
lm.fit2 <- lm(medv ~ lstat + I(lstat^2), data = Boston)
# View detailed information about the model
summary(lm.fit2)
##
## Call:
## lm(formula = medv ~ lstat + I(lstat^2), data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -15.2834 -3.8313 -0.5295 2.3095 25.4148
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 42.862007 0.872084 49.15 <2e-16 ***
## lstat -2.332821 0.123803 -18.84 <2e-16 ***
## I(lstat^2) 0.043547 0.003745 11.63 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.524 on 503 degrees of freedom
## Multiple R-squared: 0.6407, Adjusted R-squared: 0.6393
## F-statistic: 448.5 on 2 and 503 DF, p-value: < 2.2e-16
# Perform ANOVA to quantify the extent to which the quadratic fit is superior to the linear fit
lm.fit <- lm(medv ~ lstat, data = Boston)
anova(lm.fit, lm.fit2)
## Analysis of Variance Table
##
## Model 1: medv ~ lstat
## Model 2: medv ~ lstat + I(lstat^2)
## Res.Df RSS Df Sum of Sq F Pr(>F)
## 1 504 19472
## 2 503 15347 1 4125.1 135.2 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# Plot diagnostic plots for lm.fit2
par(mfrow = c(2, 2))
plot(lm.fit2)
# Fit a fifth-order polynomial model
lm.fit5 <- lm(medv ~ poly(lstat, 5), data = Boston)
# View detailed information about the model
summary(lm.fit5)
##
## Call:
## lm(formula = medv ~ poly(lstat, 5), data = Boston)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.5433 -3.1039 -0.7052 2.0844 27.1153
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 22.5328 0.2318 97.197 < 2e-16 ***
## poly(lstat, 5)1 -152.4595 5.2148 -29.236 < 2e-16 ***
## poly(lstat, 5)2 64.2272 5.2148 12.316 < 2e-16 ***
## poly(lstat, 5)3 -27.0511 5.2148 -5.187 3.10e-07 ***
## poly(lstat, 5)4 25.4517 5.2148 4.881 1.42e-06 ***
## poly(lstat, 5)5 -19.2524 5.2148 -3.692 0.000247 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.215 on 500 degrees of freedom
## Multiple R-squared: 0.6817, Adjusted R-squared: 0.6785
## F-statistic: 214.2 on 5 and 500 DF, p-value: < 2.2e-16
# Load the ISLR2 library
library(ISLR2)
# Load the Carseats dataset
data("Carseats")
# Fit a multiple regression model with interaction terms
lm.fit <- lm(Sales ~ . + Income:Advertising + Price:Age, data = Carseats)
# View detailed information about the model
summary(lm.fit)
##
## 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
# Use contrasts() function to check coding for dummy variables
contrasts(Carseats$ShelveLoc)
## Good Medium
## Bad 0 0
## Good 1 0
## Medium 0 1
# Optionally, you can use attach() to avoid using Carseats$ prefix
# attach(Carseats)
# Use ?contrasts to learn about other contrast coding methods
# 8
# Load the Auto dataset from ISLR2 library
library(ISLR2)
data("Auto")
# (a) Perform simple linear regression with mpg as the response and horsepower as the predictor
lm.fit <- lm(mpg ~ horsepower, data = Auto)
# Print the summary of the regression results
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, and display the least squares regression line
plot(Auto$horsepower, Auto$mpg, xlab = "Horsepower", ylab = "MPG", main = "Simple Linear Regression: MPG vs Horsepower")
abline(lm.fit, col = "red")
# (c) Produce diagnostic plots of the least squares regression fit
par(mfrow = c(2, 2)) # Set up a 2x2 grid for plots
plot(lm.fit)
#10
# Load the Carseats dataset
data("Carseats")
# (a) Fit a multiple regression model to predict Sales using Price, Urban, and US
lm.fit <- lm(Sales ~ Price + Urban + US, data = Carseats)
# (b) Interpretation of each coefficient
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 = β0 + β1 * Price + β2 * UrbanYes + β3 * USYes + ε
# (d) For which of the predictors can you reject the null hypothesis H0 : βj = 0?
# Examine the p-values in the summary output to determine which coefficients are statistically significant
# (e) Fit a smaller model that only uses the predictors for which there is evidence of association with the outcome
lm.fit_smaller <- lm(Sales ~ Price + US, data = Carseats)
# (f) Assess the model fit for both models (a) and (e)
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 + US, data = Carseats)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.9269 -1.6286 -0.0574 1.5766 7.0515
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.03079 0.63098 20.652 < 2e-16 ***
## Price -0.05448 0.00523 -10.416 < 2e-16 ***
## USYes 1.19964 0.25846 4.641 4.71e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.469 on 397 degrees of freedom
## Multiple R-squared: 0.2393, Adjusted R-squared: 0.2354
## F-statistic: 62.43 on 2 and 397 DF, p-value: < 2.2e-16
# (g) Obtain 95% confidence intervals for the coefficient(s) in the smaller model
confint(lm.fit_smaller)
## 2.5 % 97.5 %
## (Intercept) 11.79032020 14.27126531
## Price -0.06475984 -0.04419543
## USYes 0.69151957 1.70776632
# (h) Check for evidence of outliers or high leverage observations
# Use diagnostic plots such as residuals vs. fitted values plot, Cook's distance, etc.
plot(lm.fit_smaller)
#14
# Generate data
set.seed(1)
x1 <- runif(100)
x2 <- 0.5 * x1 + rnorm(100) / 10
# Calculate correlation
correlation <- cor(x1, x2)
print(correlation)
## [1] 0.8351212
# Create scatterplot
plot(x1, x2, main = "Scatterplot of x1 vs x2", xlab = "x1", ylab = "x2")
# Generate data
y <- 2 + 2 * x1 + 0.3 * x2 + rnorm(100)
# Fit least squares regression using only x1
lm.fit_x1 <- lm(y ~ x1)
# Describe the results
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
# Fit least squares regression using only x2
lm.fit_x2 <- lm(y ~ x2)
# Describe the results
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
# Add the additional observation
x1 <- c(x1, 0.1)
x2 <- c(x2, 0.8)
y <- c(y, 6)
# Refit the linear models
lm.fit_new <- lm(y ~ x1 + x2)
lm.fit_x1_new <- lm(y ~ x1)
lm.fit_x2_new <- lm(y ~ x2)
# Describe the results
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
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
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
