Pearson’s r interval estimation
|Approximate number of subjects required to obtain a confidence interval of the desired width for a planning estimate of the population (partial) Pearson correlation coefficient (r).
Significance level (α) = 0.05 translates to a 95% confidence interval, α = 0.01 to a 99% confidence interval.
Can be used to estimate the sample size (n) required to test a hypothesis regarding the planned value of a Pearson correlation with desired power. For example: for an expected Pearson r of 0.8, 56 subjects are needed to obtain a desired 95% confidence interval width of 0.2 (i.e., the value of Pearson r is between 0.7 and 0.9).
Bonett DG, Wright TA. Sample size requirements for estimating Pearson, Kendall and Spearman correlations. Psychometrika. 2000;65(1):23-28.
Calulator as Shiny app