Model selection aims to find the best model. Selection in the presence of censored data arises in a variety of problems. In this paper we emphasize that the Kullback-Leibler divergence under complete data has a better advantage. Some procedures are provided to construct a tracking interval for the expected difference of Kullback-Leibler risks based on Type II right censored data. Simulation study shows that this procedure works properly for optimum model selection.
Sayareh A, Torkman P. Estimating the Difference of Kullback-Leibler Risks under Type II Right Censored Data for Non-Nested Models. JSS 2009; 3 (1) :59-78 URL: http://jss.irstat.ir/article-1-30-en.html
