How to Measure Heteroscedasticity in Regression?
Heteroscedasticity in Regression, one of the easiest ways to measure heteroscedasticity is while using the Breusch-Pagan Test.
The test is mainly used to identify if heteroscedasticity is present in a regression analysis.
This tutorial explains how to execute a Breusch-Pagan Test in R.
pipe operator in R-Simplify Your Code with %>% »
Heteroscedasticity in Regression
Step 1: Fit a regression model.
First, we will fit a regression model using Wind as the response variable and Temp and Month as the two explanatory variables.
load the airquality dataset
data(airquality)
fit a regression model
model <- lm(Wind~Temp+Month, data= airquality)
view model summary
How to find dataset differences in R Quickly Compare Datasets »
summary(model)
Coefficients:
lm(formula = Wind ~ Temp + Month, data = airquality) Residuals: Min 1Q Median 3Q Max -8.5401 -2.4133 -0.2177 2.0019 9.7670 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 23.14224 2.15939 10.717 < 2e-16 *** Temp -0.17322 0.02978 -5.817 3.49e-08 *** Month 0.04382 0.19898 0.220 0.826 --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Multiple R-squared: 0.21, Adjusted R-squared: 0.1995 F-statistic: 19.94 on 2 and 150 DF, p-value: 2.097e-08
Kruskal Wallis test in R-One-way ANOVA Alternative »
Step 2: Perform a Breusch-Pagan Test.
Here we are going to measure the heteroscedasticity for that we can make utilize a Breusch-Pagan Test.
load lmtest library
library(lmtest)
Execute Breusch-Pagan Test
bptest(model)
studentized Breusch-Pagan test
data: model BP = 2.1131, df = 2, p-value = 0.3477
The test statistic is 2.1131 and the corresponding p-value is 0.3477. Since the p-value is greater than 0.05, we cannot reject the null hypothesis.
This indicates that we do not have sufficient evidence to reject the null hypothesis or sufficient evidence to say heteroscedasticity is present in the regression model.
