Understanding statistical power using noncentral probability distributions: Chi-squared, G-squared, and ANOVA

Abstract

This paper presents a graphical way of interpreting effect sizes when more than two groups are involved in a statistical analysis. This method uses noncentral distributions to specify the alternative hypothesis, and the statistical power can thus be directly computed. This principle is illustrated using the chi-squared distribution and the F distribution. Examples of chi-squared and ANOVA statistical tests are provided to further illustrate the point. It is concluded that power analyses are an essential part of statistical analysis, and that using noncentral distributions provides an argument in favour of using a factorial ANOVA over multiple t tests.