Empirical Likelihood-Based Subset Selection for Partially Linear Autoregressive Models
报 告 人:: 韩玉
报告地点:: 数学与统计学院四楼报告厅
报告时间:: 2017年12月21日星期四16:45-17:30

The subset selection and hypothesis test for the parameters in a partially linear autoregressive model are investigated based on the empirical likelihood method. On one hand, we show that the empirical log-likelihood ratio at the true parameters converges to the standard chi-square distribution. On the other hand, we present the definitions of the empirical likelihood-based Bayes information criteria(EBIC) and Akaike information criteria(EAIC). The results show that EBIC is consistent at selecting subset variables while EAIC isn't. The different simulation studies demonstrate that the proposed empirical likelihood confidence regions have better coverage probabilities than the least square method does, and EBIC has a higher chance to select the true model than EAIC.

发 布 人:科研助理 发布时间: 2017-12-20