In simple terms, a measure of effect size povides a standardized measure of the
strength or magnitude of an effect. A statistical significance test tells us how
confident we can be that there *is* an effect - for example, that hitting
people over the head will decrease their ability to recall items on a list. A measure
of effect size, such as Cohen's D, gives us a standardized way of assessing the
*magnitude* of the effect.

In practice, you're only ever likely to calculate an effect size if you already know the effect is statistically significant (because there's no point in calculating the size of an effect, if there is no good reason to suppose there is any effect), and the particular way an effect size is calculated is related to the significance test performed.

Note: To calculate an effect size, you need to know the means and standard deviations of your groups. If you have raw data, you can calculate means here and standard deviations here.

Choose Your Effect Size Calculator