Modeling clustered long‐term survivors using marginal mixture cure model

Abstract

There is a great deal of recent interests in modeling right-censored clustered survival time data with a possible fraction of cured subjects who are nonsusceptible to the event of interest using marginal mixture cure models. In this paper, we consider a semiparametric marginal mixture cure model for such data and propose to extend an existing generalized estimating equation approach by a new unbiased estimating equation for the regression parameters in the latency part of the model. The large sample properties of the regression effect estimators in both incidence and the latency parts are established. The finite sample properties of the estimators are studied in simulation studies. The proposed method is illustrated with a bone marrow transplantation data and a tonsil cancer data.

Modelling the Survival of Western Honey Bee <i>Apis mellifera</i> and the African Stingless Bee <i>Meliponula ferruginea</i> Using Semiparametric Marginal Proportional Hazards Mixture Cure Model

“…Based on the simulation study done by Niu et al [17] the ES method does not always outperform the PTY [15] and the NP [16] methods. When the correlation Journal of Data Analysis and Information Processing within the cluster is strong and the cluster size is large, the ES method has smaller mean squared errors in β and γ than those from the PTY and the NP methods hence performs better [17]. The PTY method appeared to be adequate compared to the ES and the NP methods when the correlation within the cluster was weak.…”

“…, , : Niu and Peng [16] and Niu et al [17] proposed an approach based on the ES algorithm to estimate (…”

“…In this study, we will implement a marginal semi-parametric proportional hazards mixture cure model (PHMC) models which was first proposed by Niu and Peng [16] and later extended by Niu et al [17] to the data employing independence and exchangeable correlation structures. This method (denoted as ES method), compared with the existing marginal and random effects approaches con-P. Isiaho et al Journal of Data Analysis and Information Processing sider the correlation structure explicitly in the model as the random effects methods do, but it also enjoys the simplicity of the marginal methods.…”