Dissertation/Thesis Abstract

Nonparametric alternative to Poly-k test in animal tumorigenicity studies
by Dill, Kristina Dionne, M.S., California State University, Long Beach, 2012, 89; 1521617
Abstract (Summary)

In the Food and Drug Administration, statistical testing for dose related trend is recommended to examine tumorigenicity in long term animal experiments. The survival-adjusted Cochran-Armitage test, known as the Poly-k test, is used for detecting a linear trend in the incidence of an occult tumor of interest across dose groups. Usually, in long term animal tumorigenicity studies the Poly-3 test with the shape parameter 3 is used. In this research, an age-adjusted bootstrap-based method is developed as a nonparametric alternative to the Poly-3 test in animal carcinogenicity data. An empirical distribution of the Poly-3 trend test statistic is investigated by comparing the proposed age-adjusted bootstrap method to the Poly-3 test statistic. The proposed method is applied to National Toxicology Program data sets to evaluate a dose-related trend of a test substance on the incidence of tumors. Further investigations will be conducted in a simulation study to evaluate the robustness of these tests to various Weibull-family tumor onset distributions.

Indexing (document details)
Advisor: Moon, Hojin
Commitee: Kim-Park, Yong Hee, Moon, Hojin, Suaray, Kagba
School: California State University, Long Beach
Department: Mathematics and Statistics
School Location: United States -- California
Source: MAI 51/04M(E), Masters Abstracts International
Subjects: Biostatistics, Statistics, Oncology
Publication Number: 1521617
ISBN: 9781267790460
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy