Browsing by Author "Huang, Xuelin"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Estimating marginal survival in the presence of dependent and independent censoring: With applications to dividend initiation policy(2005) Fix, Gretchen Abigail; Ensor, Katherine B.; Huang, XuelinIn many survival analysis settings, the assumption of non-informative (i.e. independent) censoring is not valid. Zheng and Klein (1995, 1996) develop a copula-based method for estimating the marginal survival functions of bivariate dependent competing risks data. We expand upon this earlier work and adapt their method to data in which there are three competing risks representing both dependent and independent censoring. Specifically, our extension allows for the estimation of the survival functions of dependent competing risks X and Y in the presence of a third independent competing risk Z. An application to dividend initiation data is presented.Item Regression survival analysis with dependent censoring and a change point for the hazard rate: With application to the impact of the Gramm-Leach-Bliley Act to insurance companies' survival(2010) Zhang, Nan (Jenny); Huang, Xuelin; Cox, Dennis D.This dissertation is aiming to find out the impact of the Gramm-Leach-Bliley Act on insurance companies' survival. The events of interest are bankruptcy and acquisition, which are correlated and censor each other. A statistical survival analysis method is developed first and then applied to the real insurance companies' survival data. In the methodology development, we first assess the effect of assuming independent censoring on the regression parameter estimates in Cox proportional hazard model. Then we apply the copula function to model the dependent censoring. Next, we propose an extended partial likelihood function maximized with an iteration algorithm to estimate the regression parameters and to derive the marginal survival functions under a dependent censoring setting. Simulations are conducted to demonstrate the method's performance, and sensitivity analyses are performed to assess the impact of the dependent censoring on the regression parameter estimates. In the last part of methodology, we propose a method to test the existence and to identify the location of a change-point in a hazard function. The application of our methodology to real insurance companies' survival data discloses important influence of the GLB Act on insurance companies survival.