Statistical hypothesis testing is a formal statistical procedure for drawing conclusions about relationships or values ​​in a population based on a sample. It is defined as a procedure for testing a hypothesis about the value of a parameter, based on data collected from a sample.

The purpose of hypothesis testing is to reject or fail to reject a specific null hypothesis based on data collected from a sample.

The statistical significance of a hypothesis is assessed using the p-value: the probability of obtaining test results at least as extreme as the results actually observed, under the assumption that the null hypothesis is correct.

The method was developed in the early 20th century through the synthesis of two competing approaches: the significance testing of Sir Ronald Fisher, and the hypothesis testing framework of Jerzy Neyman and Egon Pearson.