报告题目：Error DensityEstimation and Its Asymptotic Properties in High Dimensional Linear Model
报 告 人：崔恒建教授（首都师范大学）
This talk isconcerned with the error density estimation in high dimensional sparse linearmodel, where the number of variables may be larger than the sample size. Animproved two stage refitted cross-validation procedure by random splittingtechnique is used to obtain the residuals of the model, and then traditionalkernel density method is applied to estimate the error density. Under suitablesparse conditions, the large sample properties of the estimator including theweak and strong consistency, as well as normality and the law of the iteratedlogarithm are obtained. A real data example is presented.