set.seed(123)
n <- 100
x1 <- rnorm(n, mean = 50, sd = 10) # Quantitative predictor
x2 <- sample(0:1, n, replace = TRUE) # Dichotomous predictor
y <- 2*x1 + 0.5*x1^2 + 3*x2 + 0.5*x1*x2 + rnorm(n, mean = 0, sd = 5) # Dependent variable
data <- data.frame(y, x1, x2)
# Multiple regression model
model <- lm(y ~ x1 + I(x1^2) + x2 + x1:x2, data = data)
summary(model)
##
## Call:
## lm(formula = y ~ x1 + I(x1^2) + x2 + x1:x2, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.0471 -3.1952 -0.7353 2.2315 14.6579
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -15.306248 10.796547 -1.418 0.160
## x1 2.720654 0.437101 6.224 1.30e-08 ***
## I(x1^2) 0.491693 0.004397 111.825 < 2e-16 ***
## x2 -0.811403 5.691925 -0.143 0.887
## x1:x2 0.608250 0.109719 5.544 2.65e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.557 on 95 degrees of freedom
## Multiple R-squared: 0.9999, Adjusted R-squared: 0.9999
## F-statistic: 2.891e+05 on 4 and 95 DF, p-value: < 2.2e-16
# Residual analysis
par(mfrow = c(2, 2))
plot(model)
The points in the QQ plot approximately follow a straight line, indicating that the residuals are normally distributed.