Browsing by Author "Jan, SL"

Now showing 1 - 3 of 3

Nonparametric multiple test procedures for dose finding
(2004)
Jan, SL
;
Shieh, G
;
管理科學系
;
Department of Management Science
We consider identifying the minimum effective dose (MED) in a one-way layout, where the MED is defined to be the lowest dose level that is more effective than the zero-dose control. Proposed herein are two rank-based nonparametric step-down closed testing procedures that do not make order assumptions on the dose-response relationship. The corresponding p-value for the estimated MED is computed. A numerical example is given to illustrate the proposed tests. Finally, the results of a Monte Carlo study of the relative error rate and power performances are reported.
On power and sample size determinations for the Wilcoxon-Mann-Whitney test
(2006-01-01)
Shieh, G
;
Jan, SL
;
Randles, RH
;
管理科學系
;
Department of Management Science
This article considers power and sample size calculations for the Wilcoxon-Mann-Whitney test. An exact variance large-sample method is introduced and explicit formulas are derived for the uniform, normal, double exponential and exponential shift models. A Monte Carlo Simulation Study is conducted to evaluate the exact variance procedure and compare its performance with some other large sample methods. The results show the remarkable accuracy of the suggested formula and the fundamental limitations of the other approximations. Practical considerations in determination of sample size for the two-sample location problem are also discussed.
The effectiveness of randomized complete block design
(2004-02-01)
Shieh, G
;
Jan, SL
;
管理科學系
;
Department of Management Science
This paper examines the relative efficiency of randomized complete block design as compared with that of completely randomized design. The most widely used measure of relative efficiency considers only the error variances of the two designs, therefore it does not provide the complete information concerning the sensitivity of the experiment in the final results. We study three alternative criteria related to the sensitivity issue and design planning consideration. The proposed relative measures employ the p-value, Scheffe confidence interval estimation and power of both designs. The distinct feature of this study is the focus on the estimated relative efficiency measures and their relation with the coefficient of partial determination between responses and block effects, given that treatment effects are present in the models. Furthermore, informative visual representations and numerical assessments of various aspects of their properties are also presented.