Abstract
Analysis of variance (ANOVA) is often used in quality control studies. It assumes equal variabilities within groups, and no exact procedures have been available for cases with unequal variabilities. In this paper exact procedures are given and illustrated. An indication of the losses to be incurred by using the traditional F test when variances are unequal is given.
Additional information
Notes on contributors
Edward J. Dudewicz
Dr. Dudewicz is a Professor in the Department of Statistics and a Senior Member of ASQC.
Thomas A. Bishop
Dr. Bishop is Principal Research Scientist.