Maximum Empirical Likelihood Estimator in a Partially Linear Errors-in-variables Regression Model

Aim at the estimation of a partially linear regression model with errors in covariables,by using the empirical likelihood method,the proposed maximum empirical likelihood estimators of unknown parameters are proved to be asymptotically normal under some conditions.Furthermore,the authors also achieve the optimal convergence rate O_P(n^-1/3) of the nonparametric estimator.