Post-hoc Power Calculator

Study Group Design

vs.

Two independent
study groups

vs.

One study group
vs. population

Primary Endpoint

Dichotomous (yes/no)

Continuous (means)

Statistical Parameters

Endpoint Means
Group 1	±
Group 2	±
Number of Subjects
Group 1	subjects
Group 2	subjects

Study Incidence
Group 1	%
Group 2	%
Number of Subjects
Group 1	subjects
Group 2	subjects

Study Incidence
Known population	%
Study group	%
Number of Subjects
Study group	subjects

Endpoint Mean
Known Population	±
Study group
Number of Subjects
Study group	subjects

Type I/II Error Rate
Alpha
Load an Example

About This Calculator

This calculator uses a variety of equations to calculate the statistical power of a study after the study has been conducted.¹

"Power" is the ability of a trial to detect a difference between two different groups. If a trial has inadequate power, it may not be able to detect a difference even though a difference truly exists. This false conclusion is called a type II error.

Just like sample size calculation, statistical power is based on the baseline incidence of an outcome, the population variance, the treatment effect size, alpha, and the sample size of a study.

The Dangers of Post-Hoc Analysis

Post-hoc power analysis has been criticized as a means of interpreting negative study results.² Because post-hoc analyses are typically only calculated on negative trials (p ≥ 0.05), such an analysis will produce a low post-hoc power result, which may be misinterpreted as the trial having inadequate power.

As an alternative to post-hoc power, analysis of the width and magnitude of the 95% confidence interval (95% CI) may be a more appropriate method of determining statistical power.

Sample Size Calculation

To calculate an adequate sample size for a future or planned trial, please visit the sample size calculator.

References