A FORTRAN Program to Determine Sample Sizes and Generate Power Curves for Completely Randomized and Randomized Complete Block Designs

Abstract

A FORTRAN program is presented which calculates power curves and determines sample sizes for a balanced ANOVA for either a one-way layout or a randomized complete block design. The user specifies the number of treatment groups, the Type I Error probability, and either an alternative hypothesis in a specific form and a desired power or a sample size. If an alternative hypothesis and desired power is specified by the user, the program determines the required sample size. If the user specifies a particular sample size, a power curve is presented in either tabulated or plotted form.

Additional information

Notes on contributors

Thomas P. Turiel

Dr. Turiel is a Statistician. He is a Member of ASQC.