Bayesian incidence analysis of animal tumorigenicity data

Statistical inference about tumorigenesis should focus on the tumour incide nce rate. Unfortunately, in most animal carcinogenicity experiments, tumour s are not observable in live animals and censoring of the tumour onset time s is informative. In this paper. we propose a Bayesian method for analysing data from such studies. Our approach focuses on the incidence of tumours a cid accommodates occult tumours and censored onset times without restrictin g tumour lethality, relying on cause-of-death data, or requiring interim sa crifices. We represent the underlying state of nature by a multistate stoch astic process and assume general probit models for the time-specific transi tion rates. These models allow the incorporation of covariates, historical control data and subjective prior information. The inherent flexibility of this approach facilitates the interpretation of results, particularly when the sample size is small or the data are sparse. We use a Gibbs sampler to estimate the relevant poster[or distributions. The methods proposed are app lied to data from a US National Toxicology Program carcinogenicity study.