A nonparametric mixture model for cure rate estimation

Nonparametric methods have attracted less attention than their parametric c ounterparts for cure rate analysis. In this paper, we study a general nonpa rametric mixture model. The proportional hazards assumption is employed in modeling the effect of covariates on the failure time of patients who are n ot cured. The Ehl algorithm, the marginal likelihood approach, and multiple imputations are employed to estimate parameters of interest in the model. This model extends models and improves estimation methods proposed by other researchers. It also extends Cox's proportional hazards regression model b y allowing a proportion of event-free patients and investigating covariate effects on that proportion. The model and its estimation method are investi gated by simulations. An application to breast cancer data, including compa risons with previous analyses using a parametric model and an existing nonp arametric model by other researchers, confirms the conclusions from the par ametric model but not those from the existing nonparametric model.