Tables for determining sample size in correlational research

Abstract

Many educational and psychological researchers determine the sample size in their research without any guideline except for the vague “as many as possible” principle. This article presents easy-to-use tables for determining the sample size in a research involving the use of the Pearson product-moment correlation coefficient. To use the tables, the researcher needs to specify the expected size of the sample correlation and the desired width of the 95% or 99% confidence interval for the population correlation. The construction of the tables is based on the large sample theory with Fisher's Z transformation. © 1986, The Japanese Association of Educational Psychology. All rights reserved.