In statistical hypothesis testing and power analysis, an effect size is the size of a statistically significant treatment effect – that is, a difference between a mathematical characteristic (often the mean) of a distribution of a dependent variable associated with a specific level of an independent variable and the same characteristic of all distributions defined by different levels of the independent variable. For example, if the mean of the mean scores of all experimental groups taking a test is 100, one of the groups is defined as consisting of men, and men's mean score is 102, the treatment effect for men is 102 - 100 = 2.
Since dependent variables are measured on many different scales, analysis of effect size often requires converting them to standard formats, for example:
