A Q-Q plot (or Quantile-Quantile plot) is used to compare quantile distribution of a sample to a theoretical quantile distribution. Often, this is used to visually estimate whether a sample distribution is (close to) normal, in which case the quantiles are nicely aligned in the plot. Note that this type of visual estimation does not replace a proper statistical test for normality.

We will see how to use ggplot() to code for a Q-Q plot representing a sample which is normally distributed. Here is the dataframe:

# dataframe
df <- data.frame(ID, values)



In ggplot2, Q-Q plots are drawn by the functions stat_qq() and geom_qq(). Here we use stat_qq():

ggplot(df, aes(sample=values)) +
  stat_qq()



It is of course possible to tune the look of the plot with, for example, size= and color=:

ggplot(df, aes(sample=values)) +
  stat_qq(size = 2, color = "blue")



To better verify the alignment of the dots, one can add a quantile-quantile line by the mean of stat_qq_line(). This line can also be tuned with similar arguments:

ggplot(df, aes(sample=values)) +
  stat_qq(size = 2, color = "blue") + 
  stat_qq_line(size=1.25, color="red")



Adding plot title, axis titles, ticks, labels and other essential elements

In this section, you will learn how to set/modify all the necessary elements that make a plot complete and comprehensible. Such elements are: