PowerAnalyses - KravitzLab/KreedLabWiki GitHub Wiki

Statistical Power is the probability of detecting a significant result in your sample when it exists in the population (i.e a true positive).

In other words, a study with low power might fail to find significance even when there is a real effect, leading you to incorrectly conclude that an effect does not exist. Understanding statistical power can help you answer questions like:

• What is the chance my results will replicate if someone else tries the same experiment as me?
• How many subjects should I use in my study?

There are many simpler web-based calculators for statistical power that can help you understand the statistical power in your experiments: Russ Lenth's Java applets for power and sample size Statistics Kingdom web based power calculators

The Pingouin stats package also has power calculators for common statistical tests like t-test.

You can also check out Lex's lecture on Power Analyses to learn more!