Empirical likelihood for semiparametric regression model with missing response data

Abstract

a b s t r a c tA bias-corrected technique for constructing the empirical likelihood ratio is used to study a semiparametric regression model with missing response data. We are interested in inference for the regression coefficients, the baseline function and the response mean. A class of empirical likelihood ratio functions for the parameters of interest is defined so that undersmoothing for estimating the baseline function is avoided. The existing data-driven algorithm is also valid for selecting an optimal bandwidth. Our approach is to directly calibrate the empirical log-likelihood ratio so that the resulting ratio is asymptotically chi-squared. Also, a class of estimators for the parameters of interest is constructed, their asymptotic distributions are obtained, and consistent estimators of asymptotic bias and variance are provided. Our results can be used to construct confidence intervals and bands for the parameters of interest. A simulation study is undertaken to compare the empirical likelihood with the normal approximation-based method in terms of coverage accuracies and average lengths of confidence intervals. An example for an AIDS clinical trial data set is used for illustrating our methods.

A systematic survey of the methods literature on the reporting quality and optimal methods of handling participants with missing outcome data for continuous outcomes in randomized controlled trials

“…Based on classification in the literature [12,14,26,27,35] and consensus among authors, we created two classification systems for the methods investigated. The first was a 14category list of approaches including the following: classic complete case analysis, modified complete case analysis, classic single imputation, modified single imputation, classic LOCF, modified LOCF, classic MI, modified MI, classic mixed model, modified mixed model, classic GEE, modified GEE, classic robust regression, and modified robust regression Categories labeled ''classic'' referred to approaches conducting analyses while assuming data are based on ignorable missingness, although some can also be applied to data MNAR.…”

Likelihood Inference on Semiparametric Models With Generated Regressors

“…Xue (2006),Zhu, et al (2010), andXue and Xue (2011)). See alsoNewey (1994) andNewey, Hsieh and Robins (2004) for analogous discussions in the context of semiparametric Mestimators.…”

Likelihood Inference on Semiparametric Models: Average Derivative and Treatment Effect

“…This idea has been investigated in the literature for different examples (e.g. Bertail, ; Zhu and Xue, ; and Xue and Xue, ). Bravo et al .…”

“…This idea has been investigated in the literature for different examples (e.g. Bertail, 2006;Zhu and Xue, 2006;and Xue and Xue, 2011). Bravo et al (2015) establish a general theory to correct the moment function by utilizing the pathwise derivative with respect to the nonparametric component.…”