Model averaging for semiparametric additive partial linear models  

作　　者：Deng GuoHua Liang Hua 

机构地区：[1]Jiangxi Univ Finance & Econ, Sch Finance & Stat, Nanchang 330013, Peoples R China [2]Univ Rochester, Dept Biostat & Computat Biol, Rochester, NY 14642 USA

出　　处：《Science China Mathematics》2010年第5期326-339,共14页中国科学：数学（英文版）

基　　金：supported by US National Science Foundation (Grant No.DMS-0806097)

摘　　要：To improve the prediction accuracy of semiparametric additive partial linear models(APLM) and the coverage probability of confidence intervals of the parameters of interest,we explore a focused information criterion for model selection among ALPM after we estimate the nonparametric functions by the polynomial spline smoothing,and introduce a general model average estimator.The major advantage of the proposed procedures is that iterative backfitting implementation is avoided,which thus results in gains in computational simplicity.The resulting estimators are shown to be asymptotically normal.A simulation study and a real data analysis are presented for illustrations.To improve the prediction accuracy of semiparametric additive partial linear models(APLM) and the coverage probability of confidence intervals of the parameters of interest,we explore a focused information criterion for model selection among ALPM after we estimate the nonparametric functions by the polynomial spline smoothing,and introduce a general model average estimator.The major advantage of the proposed procedures is that iterative backfitting implementation is avoided,which thus results in gains in computational simplicity.The resulting estimators are shown to be asymptotically normal.A simulation study and a real data analysis are presented for illustrations.

关 键 词：BACKFITTING FOCUSED information criterion POLYNOMIAL SPLINE MODEL selection MODEL uncertainty 

分 类 号：N[自然科学总论]