You want to make a quantile-quantile (QQ) plot to compare an empirical distribution to a theoretical distribution.

Use qqnorm() to compare to a normal distribution. Give qqnorm() a vector of numerical values, and add a theoretical distribution line with qqline() (Figure 13-25):

library(gcookbook) # For the data set

# QQ plot of height
qqnorm(heightweight$heightIn)
qqline(heightweight$heightIn)

# QQ plot of age
qqnorm(heightweight$ageYear)
qqline(heightweight$ageYear)

Figure 13-25. Left: QQ plot of height, which is close to normally distributed; right: QQ plot of age, which is not normally distributed

The points for heightIn are close to the line, which means that the distribution is close to normal. In contrast, the points for ageYear veer far away from the line, especially on the left, indicating that the distribution is skewed. A histogram may also be useful for exploring how the data is distributed.