An Illness-Death Model for the Study of the Carcinogenic Process Using Survival/Sacrifice Data

A semi-Markov model for describing the development of a specific type of tumor which is followed by death from that tumor is proposed. This provides a method for investigating the observable phases of tumor development, when time to appearance of tumor in individual animals is not directly measurable. Parameters of the model are estimated by the method of maximum likelihood. The modeling and estimation procedures are illustrated with liver tumors induced by benzidine dihydrochloride in mice, and inferences with respect to strain, sex and dose differences are made.