UnifyPow: A SAS Macro for Sample-Size Analysis

UnifyPow is a freeware SAS ® macro that performs statistical power analysis and other matters related to sample-size choice. Its functionality covers an extensive set of methods. One-group tests include the t and Wilcoxon for H 0 : μ = μ 0 ; the binomial and Z approximation for H 0 : π = π 0 ; t and Wilcoxon for paired means; McNemar's for paired proportions; and Fishers's r-to-Z for H 0 : ρ = ρ 0 . Two-group tests include t and Wilcoxon-MannWhitney for H 0 : μ 1 – μ 2 = δ 0 ; χ 2 , likelihood ratio (LR), and Fisher's exact for H 0 : π 1 = π 2 (association in 2 × 2 tables); r-to-Z for H 0 : ρ 1 = ρ 2 . J-group tests include ANOVA via the cell-means model with general linear contrasts; χ 2 and LR tests for proportions (2 × J tables) with general linear contrasts on J logits. Also covered are the test of H 0 : β j = β j0 in a multiple regression model predicting Y from q Xs (“Y | q Xs”) in which X j has tolerance Tol(X j ) = 1 – R 2 (X j | other q – 1 Xs); the comparison of R 2 (Y | q full Xs) versus R 2 (Y | q reduced Xs) from nested linear models; and G 2 or –2lnL from full vs. reduced logistic, loglinear, or Cox survival models. All methods handle unequal n designs. Any set of alpha-levels may be specified and results for directional (one-tailed) tests are given when potentially appropriate. Both tabular and graphical output are available. A simple syntax unifies concepts and specifications across methods. For the current status of this ongoing project and information on downloading, see http://www.bio.ri.ccf.org/power.html