Date of Award
Mathematics and Statistics
CC BY-NC-ND 4.0
Robust procedures are proposed for testing the equality of several group means for equal and unequal group variances. These statistics are obtained by modifying the usual F test for equal variances and the Welch's W and Brown-Forsythe's F* for unequal variances by using the trimmed mean and the sine-wave M-estimator. Approximate distributions of these new statistics are obtained under normality. Their performances are evaluated by Monte Carlo sampling experiments under various long-tailed symmetric distributions, comparing among themselves and with some nonparametric tests. For the cases studied, the proposed statistics are shown to be robust in the sense that they are mildly suboptimal under exact normality but perform well over a broad spectrum of long-tailed symmetric distributions.Dept. of Mathematics and Statistics. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1982 .L335. Source: Dissertation Abstracts International, Volume: 43-03, Section: B, page: 0750. Thesis (Ph.D.)--University of Windsor (Canada), 1982.
LEE, HYUNSHIK., "ROBUST PROCEDURES FOR MULTI-SAMPLE LOCATION PROBLEMS." (1982). Electronic Theses and Dissertations. 3357.