|
Hojin Moon, PhD Associate Professor of Statistics
Department of Mathematics and Statistics
California State University -
Long Beach
|
||
|
RESEARCH |
||
Software tools :
This project initiated by Dr. Hojin Moon was supported in part by NIH grant R29 CA77289 (PI: Hongshik Ahn, 1998-2003) and the Tobacco Settlement Funds approved by the Texas State Legislature (J. Jack Lee). This research has been conducted in collaboration with Dr. Hongshik Ahn at Stony Brook University and Dr. Ralph Kodell at University of Arkansas for Medical Sciences, and J. Jack Lee and Rumiana Nikolova at M. D. Anderson Cancer Center. We have developed a new Web-based sample size and power simulator for animal carcinogenicity studies to detect a dose-related trend in tumor incidence following exposure to a putative carcinogen. It is applicable for studies of occult tumors for which the time to tumor onset is not directly observable. The development of this statistical tool was motivated by a lung cancer prevention study developed at M. D. Anderson Cancer Center. The particular goal was to evaluate the carcinogenic potential of the tobacco carcinogen NNK, a byproduct of tobacco smoke. This tool was applied to provide sufficient power to detect a dose-related trend of the occurrence of lung adenomas and adenocarcinomas. Monte Carlo simulation is introduced in this tool to simulate experiments of rodent bioassays because no closed-form solution is available. The estimation of sample size and power is conducted by the Peto test. The design parameters can be entered through the World Wide Web and pass to a core C program via Extensible Markup Language interface. Upon the completion of simulation, the results are sent back through the Web or by an e-mail.
|