Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Simulating the Power of Statistical Tests: A Collection of R Examples

Florian Wickelmaier

TL;DR

This paper illustrates how to calculate the power of a statistical test by computer simulation by providing R code for power simulations of several classical inference procedures including one- and two-sample t tests, chi-squared tests, regression, and analysis of variance.

Abstract

This paper illustrates how to calculate the power of a statistical test by computer simulation. It provides R code for power simulations of several classical inference procedures including one- and two-sample t tests, chi-squared tests, regression, and analysis of variance.

Simulating the Power of Statistical Tests: A Collection of R Examples

TL;DR

This paper illustrates how to calculate the power of a statistical test by computer simulation by providing R code for power simulations of several classical inference procedures including one- and two-sample t tests, chi-squared tests, regression, and analysis of variance.

Abstract

This paper illustrates how to calculate the power of a statistical test by computer simulation. It provides R code for power simulations of several classical inference procedures including one- and two-sample t tests, chi-squared tests, regression, and analysis of variance.

Paper Structure

This paper contains 46 sections, 1 figure.

Table of Contents

  1. One-sample tests
  2. Binomial test
  3. One-sample $z$ and $t$ test
  4. Variance test
  5. Sign test and Wilcoxon signed-rank test
  6. $\chi^2$ goodness-of-fit test
  7. Two-sample tests
  8. Independent samples
  9. Two-sample $z$, $t$ and Welch test
  10. Comparing two variances
  11. Wilcoxon rank-sum (Mann-Whitney) test
  12. Randomization test
  13. Dependent samples
  14. Paired two-sample $t$ test
  15. Paired two-sample Wilcoxon test
  16. ...and 31 more sections

Figures (1)

  • Figure 1: Power of the binomial test in the birth-rates example (H$_0$: $\pi = 0.5$) as a function of effect size and sample size. The dashed line marks the target effect of $d = 0.015$ where power hits about $0.8$ for $n = 9000$.