PARAMETRIC REGRESSION MODELING OF COMPETING RISK USING CARDIOVASCULAR DISEASE PATIENT'S SURVIVAL DATA

In the field of survival or medical studies, it was more interesting to examine death (mortality) due to different reasons of failures (competing events) than combining all the causes whereas the occurrence of one of the outcomes of interest stops the occurrence of other outcomes of interest are called competing risks. In this paper, we made an attempt on competing risk model in the presence of covariates whereas the cause of risks assumes to follow some lifetime distributions like exponential, Weibull, Gamma, generalized Gamma. Also, we assume that competing events are uncorrelated and that each subject can experience only one type of event at any particular time. Maximum likelihood estimation procedure is used to estimate the parameters in the parametric models. The results are compared with the proposed models. Validity of the model is assessed using -2LL, AIC, BIC.