Principal varying coefficient estimator for high-dimensional models

被引：2

作者：

Zhao, Weihua ^{[1
]}

Zhang, Fode ^{[2
,3
]}

Wang, Xuejun ^{[4
]}

Li, Rui ^{[5
]}

Lian, Heng ^{[6
]}

机构：

[1] Nantong Univ, Sch Sci, Nantong, Peoples R China

[2] Southwestern Univ Finance & Econ, Ctr Stat Res, Chengdu, Sichuan, Peoples R China

[3] Southwestern Univ Finance & Econ, Sch Stat, Chengdu, Sichuan, Peoples R China

[4] Anhui Univ, Sch Math Sci, Hefei, Anhui, Peoples R China

[5] Shanghai Univ Int Business & Econ, Sch Stat & Informat, Shanghai, Peoples R China

[6] City Univ Hong Kong, Dept Math, Kowloon Tong, Hong Kong, Peoples R China

来源：

STATISTICS | 2019年 / 53卷 / 06期

关键词：

Asymptotic properties; B-splines; sub-Gaussian distribution; ultra-high dimensionality; NONCONCAVE PENALIZED LIKELIHOOD; VARIABLE SELECTION; QUANTILE REGRESSION; EFFICIENT ESTIMATION; LINEAR-MODELS; SHRINKAGE;

D O I：

10.1080/02331888.2019.1663521

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 principal varying coefficient models in the high-dimensional setting, combined with variable selection, to reduce the effective number of parameters in semiparametric modelling. The estimation is based on B-splines approach. For the unpenalized estimator, we establish non-asymptotic bounds of the estimator and then establish the (asymptotic) local oracle property of the penalized estimator, as well as non-asymptotic error bounds. Monte Carlo studies reveal the favourable performance of the estimator and an application on a real dataset is presented.

引用

页码：1234 / 1250

页数：17

共 39 条

[1] ESTIMATING LINEAR RESTRICTIONS ON REGRESSION COEFFICIENTS FOR MULTIVARIATE NORMAL DISTRIBUTIONS
ANDERSON, TW
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1951, 22 (03): : 327 - 351
[2] Breheny P, 2018, REGULARIZATION PATHS
[3] Group descent algorithms for nonconvex penalized linear and logistic regression models with grouped predictors
Breheny, Patrick
Huang, Jian
[J]. STATISTICS AND COMPUTING, 2015, 25 (02) : 173 - 187
[4] FUNCTIONAL-COEFFICIENT AUTOREGRESSIVE MODELS
CHEN, R
TSAY, RS
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1993, 88 (421) : 298 - 308
[5] Nonparametric Independence Screening in Sparse Ultra-High-Dimensional Varying Coefficient Models
Fan, Jianqing
Ma, Yunbei
Dai, Wei
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2014, 109 (507) : 1270 - 1284
[6] Nonconcave Penalized Likelihood With NP-Dimensionality
Fan, Jianqing
Lv, Jinchi
[J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2011, 57 (08) : 5467 - 5484
[7] Nonparametric Independence Screening in Sparse Ultra-High-Dimensional Additive Models
Fan, Jianqing
Feng, Yang
Song, Rui
[J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2011, 106 (494) : 544 - 557
[8] Fan JQ, 2008, STAT INTERFACE, V1, P179
[9] Statistical estimation in varying coefficient models
Fan, JQ
Zhang, WY
[J]. ANNALS OF STATISTICS, 1999, 27 (05) : 1491 - 1518
[10] Two-step estimation of functional linear models with applications to longitudinal data
Fan, JQ
Zhang, JT
[J]. JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2000, 62 : 303 - 322

← 1 2 3 4 →