A Comparative Study of Semiparametric Estimation in Partially Linear Single-index Models

被引:0
作者
Kim, Young-Ju [1 ]
机构
[1] Kangwon Natl Univ, Dept Stat, Chunchon, South Korea
基金
新加坡国家研究基金会;
关键词
Boosting; Partial spline; Partially linear model; Penalized likelihood; Project pursuit regression; Single-index; SPLINE ESTIMATION; REGRESSION;
D O I
10.1080/03610918.2014.909935
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We consider a semiparametric method based on partial splines for estimating the unknown function and partially linear regression parameters in partially linear single-index models. Three methodsproject pursuit regression (PPR), average derivative estimation (ADE), and a boosting methodare considered for estimating the single-index parameters. Simulations revealed that PPR with partial splines was superior in estimating single-index parameters, while the boosting method with partial splines performed no better than PPR and ADE. All three methods performed similarly in estimating the partially linear regression parameters. The relative performances of the methods are also illustrated using a real-world data example.
引用
收藏
页码:2577 / 2585
页数:9
相关论文
共 18 条
[1]  
Antoniadis A, 2004, STAT SINICA, V14, P1147
[2]   SMOOTHING NOISY DATA WITH SPLINE FUNCTIONS [J].
WAHBA, G .
NUMERISCHE MATHEMATIK, 1975, 24 (05) :383-393
[3]  
Friedman J., 2001, SERIES IN STAT, V1
[4]   Penalized likelihood regression: general formulation and efficient approximation [J].
Gu, C ;
Kim, YJ .
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE, 2002, 30 (04) :619-628
[5]  
Gu C., 2002, SPR S STAT, DOI 10.1007/978-1-4757-3683-0
[6]   OPTIMAL SMOOTHING IN SINGLE-INDEX MODELS [J].
HARDLE, W ;
HALL, P ;
ICHIMURA, H .
ANNALS OF STATISTICS, 1993, 21 (01) :157-178
[7]  
Hristache M, 2001, ANN STAT, V29, P1537
[8]  
Hristache M, 2001, ANN STAT, V29, P595
[9]   Smoothing parameter selection in nonparametric regression using an improved Akaike information criterion [J].
Hurvich, CM ;
Simonoff, JS ;
Tsai, CL .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1998, 60 :271-293
[10]   SEMIPARAMETRIC LEAST-SQUARES (SLS) AND WEIGHTED SLS ESTIMATION OF SINGLE-INDEX MODELS [J].
ICHIMURA, H .
JOURNAL OF ECONOMETRICS, 1993, 58 (1-2) :71-120