An adaptive estimation of dimension reduction space

被引:660
作者
Xia, YC
Tong, H
Li, WK
Zhu, LX
机构
[1] Univ Cambridge, Cambridge CB2 1TN, England
[2] Jinan Univ, Jinan, Peoples R China
[3] Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China
[4] Univ London London Sch Econ & Polit Sci, London WC2A 2AE, England
[5] Chinese Acad Sci, Beijing, Peoples R China
关键词
average derivative estimation; dimension reduction; generalized linear models; local linear smoother; multiple time series; non-linear time series analysis; nonparametric regression; principal Hessian direction; projection pursuit; semi parametrics; sliced inverse regression estimation;
D O I
10.1111/1467-9868.03411
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
Searching for an effective dimension reduction space is an important problem in regression, especially for high dimensional data. We propose an adaptive approach based on semiparametric models, which we call the (conditional) minimum average variance estimation (MAVE) method, within quite a general setting. The MAVE method has the following advantages. Most existing methods must undersmooth the nonparametric link function estimator to achieve a faster rate of consistency for the estimator of the parameters (than for that of the nonparametric function). In contrast, a faster consistency rate can be achieved by the MAVE method even without undersmoothing the nonparametric link function estimator. The MAVE method is applicable to a wide range of models, with fewer restrictions on the distribution of the covariates, to the extent that even time series can be included. Because of the faster rate of consistency for the parameter estimators, it is possible for us to estimate the dimension of the space consistently. The relationship of the MAVE method with other methods is also investigated. In particular, a simple outer product gradient estimator is proposed as an initial estimator. In addition to theoretical results, we demonstrate the efficacy of the MAVE method for high dimensional data sets through simulation. Two real data sets are analysed by using the MAVE approach.
引用
收藏
页码:363 / 388
页数:26
相关论文
共 37 条
[1]  
AUESTAD B, 1990, BIOMETRIKA, V77, P669, DOI 10.2307/2337091
[2]  
Breiman L., 1984, BIOMETRICS, DOI DOI 10.2307/2530946
[3]   Functional-coefficient regression models for nonlinear time series [J].
Cai, ZW ;
Fan, JQ ;
Yao, QW .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2000, 95 (451) :941-956
[4]   Generalized partially linear single-index models [J].
Carroll, RJ ;
Fan, JQ ;
Gijbels, I ;
Wand, MP .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1997, 92 (438) :477-489
[5]  
CARROLL RJ, 1995, STAT SINICA, V5, P667
[6]  
CHAN CH, 1989, STAT SINICA, V8, P289
[7]  
CHAUDHURI P, 1994, STAT SINICA, V4, P143
[8]  
CHEN H, 1991, ANN STAT, V19, P142
[9]  
CHENG B, 1992, J ROY STAT SOC B MET, V54, P427
[10]   ON THE INTERPRETATION OF REGRESSION PLOTS [J].
COOK, RD .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1994, 89 (425) :177-189