Q-Q plot

The Q-Q plot puts each measurement as a point against the value a normal distribution would predict. If the points lie close to the line, the normal distribution fits. Curves show skewness, single points far off the line at the ends show outliers.

Example: For body heights the points lie almost on the line. For waiting times they bend upward at the top end: a few very long waits.

Caution: With few values the points scatter randomly around the line. The Shapiro-Wilk test sums up the departure in one number but does not replace looking at the plot.