Date of Award


Publication Type

Doctoral Thesis

Degree Name



Mathematics and Statistics





Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.


Two-stage testing procedures are proposed for three statistical problems: one-way analysis of variance and testing the mean of a multivariate normal distribution with first known, and then unknown, covariance matrix. For the first and third problems, a method of obtaining critical values is proposed and evaluated using Monte Carlo simulations. Moreover, for these two problems, two versions of the general F-2 procedure proposed by Chase and Hewett in 1976 are examined. Comparisons between all of the procedures and the corresponding fixed sample size, or one-stage, procedures are made in terms of power and expected sample size. The two-stage procedures proposed here are shown to have power curves that are similar to the one-stage curves while producing lower expected sample size. Thus, the experimenter may use the two-stage procedures to reduce the average sample size without affecting the Type II error.Dept. of Mathematics and Statistics. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1981 .B388. Source: Dissertation Abstracts International, Volume: 42-03, Section: B, page: 1046. Thesis (Ph.D.)--University of Windsor (Canada), 1981.