A plot for comparing two probability distributions, usually the sample distribution function and a theoretical distribution function. The sample values are ranked in order: x₍₁₎≤x₍₂₎≤⋯≤ x_(n). Define the sample cumulative proportion as p_j, typically calculated as (j−½)/n, and denote the theoretical distribution function by F. In a q-q plot, F⁻¹(p_j) is plotted against x_(j), for all j. If the sample has come from the theoretical distribution, the plotted values will lie on an approximate straight line. Specialized graph paper, that has the values of F⁻¹ marked for interesting values of p is called probability paper.

The p-p plot is entirely equivalent: F(x_(j)) is plotted against p_j. Once again, if the sample has come from the theoretical distribution, the plotted values will lie on an approximate straight line. A plot of this type is called a probability plot. See also Normal Probability Paper.