TY - JOUR
T1 - On use of the multistage dose-response model for assessing laboratory animal carcinogenicity
AU - Nitcheva, Daniela K.
AU - Piegorsch, Walter W.
AU - West, R. Webster
N1 - Funding Information:
Portions of this research were conducted while all the authors were with the University of South Carolina. Thanks are due Drs. Ralph L. Kodell, Edsel A. Peña, and Brooke E. Buckley for their input during the research effort, and three anonymous reviewers for their helpful suggestions on the manuscript. This work was funded under Grant #R01-CA76031 from the US National Cancer Institute, STAR Grant #RD-83241901 from the US Environmental Protection Agency, and as part of the research arm of the US Department of Homeland Security’s Center of Excellence for the Study of Terrorism and Responses to Terrorism (START). Its contents are solely the responsibility of the authors and do not necessarily reflect the official views of these various agencies.
PY - 2007/7
Y1 - 2007/7
N2 - We explore how well a statistical multistage model describes dose-response patterns in laboratory animal carcinogenicity experiments from a large database of quantal response data. The data are collected from the US EPA's publicly available IRIS data warehouse and examined statistically to determine how often higher-order values in the multistage predictor yield significant improvements in explanatory power over lower-order values. Our results suggest that the addition of a second-order parameter to the model only improves the fit about 20% of the time, while adding even higher-order terms apparently does not contribute to the fit at all, at least with the study designs we captured in the IRIS database. Also included is an examination of statistical tests for assessing significance of higher-order terms in a multistage dose-response model. It is noted that bootstrap testing methodology appears to offer greater stability for performing the hypothesis tests than a more-common, but possibly unstable, "Wald" test.
AB - We explore how well a statistical multistage model describes dose-response patterns in laboratory animal carcinogenicity experiments from a large database of quantal response data. The data are collected from the US EPA's publicly available IRIS data warehouse and examined statistically to determine how often higher-order values in the multistage predictor yield significant improvements in explanatory power over lower-order values. Our results suggest that the addition of a second-order parameter to the model only improves the fit about 20% of the time, while adding even higher-order terms apparently does not contribute to the fit at all, at least with the study designs we captured in the IRIS database. Also included is an examination of statistical tests for assessing significance of higher-order terms in a multistage dose-response model. It is noted that bootstrap testing methodology appears to offer greater stability for performing the hypothesis tests than a more-common, but possibly unstable, "Wald" test.
KW - Bootstrap hypothesis test
KW - Cancer
KW - Dose-response modeling
KW - Multistage model
UR - http://www.scopus.com/inward/record.url?scp=34249664988&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34249664988&partnerID=8YFLogxK
U2 - 10.1016/j.yrtph.2007.03.002
DO - 10.1016/j.yrtph.2007.03.002
M3 - Article
C2 - 17490794
AN - SCOPUS:34249664988
SN - 0273-2300
VL - 48
SP - 135
EP - 147
JO - Regulatory Toxicology and Pharmacology
JF - Regulatory Toxicology and Pharmacology
IS - 2
ER -