Penalized empirical likelihood for high-dimensional generalized linear models

We develop penalized empirical likelihood for parameter estimation and variable selection in high-dimensional generalized linear models. By using adaptive lasso penalty function, we show that the proposed estimator has the oracle property. Also, we consider the problem of testing hypothesis, and show that the nonparametric profiled empirical likelihood ratio statistic has asymptotic chi-square distribution. Some simulations and an application are given to illustrate the performance of the proposed method.