Approximation of the Likelihood Ratio Statistics in Competing Risks Model Under Informative Random Censorship From Both Sides

It is clear that the likelihood ratio statistics plays an important role in theories of asymptotical estimation and hypothesis testing. The aim of the paper is to investigate the asymptotic properties of likelihood ratio statistics in competing risks model with informative random censorship from both sides. We prove the approximation version of the locally asymptotically normality of the likelihood ratio statistics. The results have asymptotic representation of the likelihood ratio statistics using the strong approximation method where local asymptotic normality is obtained as a consequence.