Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
418277 | Computational Statistics & Data Analysis | 2007 | 10 Pages |
Abstract
In this paper, we consider identifying the minimum effective dose (MED) in a dose–response study when survival data are subject to random right-censorship, where the MED is defined to be the smallest dose level under study that has survival advantage over the zero-dose control. To this end, we suggest single-step-down testing procedures based on three different types of weighted logrank statistics, respectively. The comparative results of a Monte Carlo error rate and power/bias study for a variety of survival and censoring distributions are then presented and discussed. The application of the testing procedures for identifying the MED is finally illustrated by using a numerical example of prostate cancer data.
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
Yuh-Ing Chen, Yu-Mei Chang,