Small sample profile analysis with many variables.

Monte Carlo methods were used to investigate the adequacy of 2 approaches to data analysis in a repeated measures design in which the number of repeated levels was large and the sample size was relatively small. The techniques examined were G. E. Box's (1954) ε?-adjustment and H. Huynh and L. S. Feldt's (1976) ε?-adjustment. Results show that approximate univariate approaches to repeated measures can successfully be used even when the number of Ss is smaller than the number of levels of the repeated factor. (22 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)