Power Analysis

Posted on Dec 27, 2017 0 Comments

Applications

In hypothesis testing situations,

1. Determine the sample size required to detect an effect of a given size with a given degree of confidence
2. Determine the probability of detecting an effect of a given size with a given level of confidence, under sample size constraints. (If the probability is unacceptably low, you’d wise be wise to alter or abandon the experiment.)

Null hypothesis significance experiment (NHST)

Four quantities

1. sample size
2. significance level
3. power
4. effect size

Implementation

Plots

Sample sizes for detecting significant effects in a one-way ANOVA

Sample size curves for detecting correlations of various sizes

Reference

Kabacoff RI. R in Action. manning; 2010.