Jackknife Empirical Likelihood Methods for the Cox Regression Model

In the thesis, we consider the Cox regression model. We develop the jackknife empirical likelihood (JEL), adjusted jackknife empirical likelihood (AJEL), mean jackknife empirical likelihood (MJEL), transformed jackknife empirical likelihood (TJEL) and (TAJEL) transformed adjusted jackknife empirical likelihood for the inference about the regression parameters. Additionally, the adjusted empirical likelihood (AEL), mean empirical likelihood (MEL), transformed empirical likelihood (TEL) and transformed adjusted empirical likelihood (TAEL) methods are developed. We compare methods under different distributions in terms of the coverage probability and average length of confidence interval for the regression parameter with simulation studies and three real data sets. The simulation analyses indicate that the MJEL, AJEL, and TAJEL methods are the best performing JEL methods while the MEL method was the best performing EL method. The real data analyses yielded results consistent with the simulation studies