평균-분산 가속화 실패시간 모형에서의 벌점화 변수선택 연구

Abstract

Accelerated failure time (AFT) model represents a linear relationship between the log-survival time and covariates. We are interested in the inference of covariate's effect affecting the variation of survival times in the AFT model. Thus, we need to model the variance as well as the mean of survival times. We call the resulting model mean and variance AFT (MV-AFT) model. In this thesis, we study about the inference of MV-AFT model. We also propose a variable selection procedure of regression parameters of mean and variance in MV-AFT model using penalized likelihood function. For the variable selection, we use four penalty functions, i.e. LASSO, adaptive LASSO (ALASSO), SCAD and hierarchical likelihood (HL). These methods lead to estimate covariates-effect parameters and select important covariates, simultaneously. The proposed method is demonstrated using simulation studies and two practical example data.