Abstract
PASS is the Power Analysis and Sample Size program. It analyzes t-tests (one mean; two means), F-tests of several means, chi-square tests (goodness of fit; contingency table), tests of proportions (one; two), log-rank survival tests, correlations (single; two correlations), ANOVA (fixed effects; randomized block; repeated measures), log-rank tests, regression (multiple; logistic), and bioequiva- lence procedures. It then produces AScii and graphics files reporting power levels. It can also be used for determination of needed sample size to achieve a given power level with a given procedure. Rank- and-file social scientists who merely want to estimate sample size during the design process will find PASS too sophisticated and non- user-friendly for their needs. Methodologists who understand power analysis, however, will find PAss an extremely useful and effective tool.
Get full access to this article
View all access options for this article.