1
|
Xiong W, Tian M, Tang M, Pan H. Robust and sparse learning of varying coefficient models with high-dimensional features. J Appl Stat 2022; 50:3312-3336. [PMID: 37969890 PMCID: PMC10637205 DOI: 10.1080/02664763.2022.2109129] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2021] [Accepted: 07/28/2022] [Indexed: 10/15/2022]
Abstract
Varying coefficient model (VCM) is extensively used in various scientific fields due to its capability of capturing the changing structure of predictors. Classical mean regression analysis is often complicated in the existence of skewed, heterogeneous and heavy-tailed data. For this purpose, this work employs the idea of model averaging and introduces a novel comprehensive approach by incorporating quantile-adaptive weights across different quantile levels to further improve both least square (LS) and quantile regression (QR) methods. The proposed procedure that adaptively takes advantage of the heterogeneous and sparse nature of input data can gain more efficiency and be well adapted to extreme event case and high-dimensional setting. Motivated by its nice properties, we develop several robust methods to reveal the dynamic close-to-truth structure for VCM and consistently uncover the zero and nonzero patterns in high-dimensional scientific discoveries. We provide a new iterative algorithm that is proven to be asymptotic consistent and can attain the optimal nonparametric convergence rate given regular conditions. These introduced procedures are highlighted with extensive simulation examples and several real data analyses to further show their stronger predictive power compared with LS, composite quantile regression (CQR) and QR methods.
Collapse
Affiliation(s)
- Wei Xiong
- School of Statistics, University of International Business and Economics, Beijing, People's Republic of China
| | - Maozai Tian
- Center for Applied Statistics, School of Statistics, Renmin University of China, Beijing, People's Republic of China
| | - Manlai Tang
- Department of Mathematics, College of Engineering, Design and Physical Sciences, Brunel University London, London, UK
| | - Han Pan
- School of Statistics, University of International Business and Economics, Beijing, People's Republic of China
| |
Collapse
|
2
|
Hu YP, Liang HY. Empirical likelihood in single-index partially functional linear model with missing observations. COMMUN STAT-THEOR M 2022. [DOI: 10.1080/03610926.2022.2094413] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/03/2022]
Affiliation(s)
- Yan-Ping Hu
- School of Mathematical Sciences, Tongji University, Shanghai, P.R. China
| | - Han-Ying Liang
- School of Mathematical Sciences, Tongji University, Shanghai, P.R. China
| |
Collapse
|
3
|
Jiang R, Sun M. Single-index composite quantile regression for ultra-high-dimensional data. TEST-SPAIN 2022. [DOI: 10.1007/s11749-021-00785-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
4
|
Yuan X, Li Y, Dong X, Liu T. Optimal subsampling for composite quantile regression in big data. Stat Pap (Berl) 2022. [DOI: 10.1007/s00362-022-01292-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
5
|
Zou Y, Wu C, Fan G, Zhang R. Jackknife empirical likelihood of error variance for partially linear varying-coefficient model with missing covariates. COMMUN STAT-THEOR M 2021. [DOI: 10.1080/03610926.2021.1938128] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
Affiliation(s)
- Yuye Zou
- College of Economics and Management, Shanghai Maritime University, Shanghai, China
- Key Laboratory of Advanced Theory and Application in Statistics and Data Science - MOE, School of Statistics, East China Normal University, Shanghai, China
| | - Chengxin Wu
- School of Mathematics, Hefei University of Technology, Hefei, China
- School of Mathematics and Statistics, Huangshan University, Huangshan, China
| | - Guoliang Fan
- College of Economics and Management, Shanghai Maritime University, Shanghai, China
| | - Riquan Zhang
- Key Laboratory of Advanced Theory and Application in Statistics and Data Science - MOE, School of Statistics, East China Normal University, Shanghai, China
| |
Collapse
|
6
|
Liang HY, Wang BH, Shen Y. Quantile regression of partially linear single-index model with missing observations. STATISTICS-ABINGDON 2021. [DOI: 10.1080/02331888.2021.1883613] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
Affiliation(s)
- Han-Ying Liang
- School of Mathematical Sciences, Tongji University, Shanghai, People's Republic of China
| | - Bao-Hua Wang
- School of Mathematical Sciences, Tongji University, Shanghai, People's Republic of China
| | - Yu Shen
- School of Mathematical Sciences, Tongji University, Shanghai, People's Republic of China
| |
Collapse
|
7
|
Li C, Li Y, Ding X, Dong X. DGQR estimation for interval censored quantile regression with varying-coefficient models. PLoS One 2020; 15:e0240046. [PMID: 33170868 PMCID: PMC7654815 DOI: 10.1371/journal.pone.0240046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2020] [Accepted: 08/05/2020] [Indexed: 11/29/2022] Open
Abstract
This paper propose a direct generalization quantile regression estimation method (DGQR estimation) for quantile regression with varying-coefficient models with interval censored data, which is a direct generalization for complete observed data. The consistency and asymptotic normality properties of the estimators are obtained. The proposed method has the advantage that does not require the censoring vectors to be identically distributed. The effectiveness of the method is verified by some simulation studies and a real data example.
Collapse
Affiliation(s)
- ChunJing Li
- School of Mathematics and Statistics, Changchun University of Technology, Changchun, China
| | - Yun Li
- School of Mathematics and Statistics, Changchun University of Technology, Changchun, China
| | - Xue Ding
- School of Mathematics and Statistics, Changchun University of Technology, Changchun, China
| | - XiaoGang Dong
- School of Mathematics and Statistics, Changchun University of Technology, Changchun, China
| |
Collapse
|
8
|
Penalized weighted composite quantile regression for partially linear varying coefficient models with missing covariates. Comput Stat 2020. [DOI: 10.1007/s00180-020-01012-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
9
|
Wang BH, Liang HY. Empirical likelihood in varying-coefficient quantile regression with missing observations. COMMUN STAT-THEOR M 2020. [DOI: 10.1080/03610926.2020.1747629] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
Affiliation(s)
- Bao-Hua Wang
- School of Mathematical Sciences, Tongji University, Shanghai, P. R. China
| | - Han-Ying Liang
- School of Mathematical Sciences, Tongji University, Shanghai, P. R. China
| |
Collapse
|
10
|
An improvement on the efficiency of complete-case-analysis with nonignorable missing covariate data. Comput Stat 2020. [DOI: 10.1007/s00180-020-00964-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
11
|
Fan GL, Xu HX, Liang HY. Dimension reduction estimation for central mean subspace with missing multivariate response. J MULTIVARIATE ANAL 2019. [DOI: 10.1016/j.jmva.2019.104542] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
12
|
Affiliation(s)
- Rong Jiang
- Department of Applied Mathematics, College of Science, Donghua University, Shanghai, People's Republic of China
| | - Xueping Hu
- School of Mathematics and Computational Science, Anqing Normal University, Anqing, People's Republic of China
| | - Keming Yu
- Department of Mathematics, Brunel University London, Middlesex, UK
| | - Weimin Qian
- School of Mathematical Sciences, Tongji University, Shanghai, People's Republic of China
| |
Collapse
|
13
|
Shen Y, Liang HY. Quantile regression for partially linear varying-coefficient model with censoring indicators missing at random. Comput Stat Data Anal 2018. [DOI: 10.1016/j.csda.2017.07.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
14
|
Jiang R, Qian WM, Zhou ZG. Weighted composite quantile regression for partially linear varying coefficient models. COMMUN STAT-THEOR M 2017. [DOI: 10.1080/03610926.2017.1366522] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- Rong Jiang
- Department of Applied Mathematics, College of Science, Donghua University, Shanghai, China
| | - Wei-Min Qian
- Department of Mathematics, Tongji University, Shanghai, China
| | | |
Collapse
|
15
|
Shen Y, Liang HY, Fan GL. Penalized empirical likelihood for quantile regression with missing covariates and auxiliary information. COMMUN STAT-THEOR M 2017. [DOI: 10.1080/03610926.2017.1335413] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- Yu Shen
- School of Mathematical Science, Tongji University, Shanghai, P. R. China
| | - Han-Ying Liang
- School of Mathematical Science, Tongji University, Shanghai, P. R. China
| | - Guo-Liang Fan
- School of Mathematics and Physics, Anhui Polytechnic University, Wuhu, P. R. China
| |
Collapse
|
16
|
Zhao P, Zhao H, Tang N, Li Z. Weighted composite quantile regression analysis for nonignorable missing data using nonresponse instrument. J Nonparametr Stat 2017. [DOI: 10.1080/10485252.2017.1285030] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- Puying Zhao
- Department of Statistics, Yunnan University, People's Republic of China
- Department of Statistics, George Washington University, USA
| | - Hui Zhao
- Department of Statistics, Yunnan University, People's Republic of China
| | - Niansheng Tang
- Department of Statistics, Yunnan University, People's Republic of China
| | - Zhaohai Li
- Department of Statistics, George Washington University, USA
| |
Collapse
|
17
|
Sun J, Ma Y. Empirical likelihood weighted composite quantile regression with partially missing covariates. J Nonparametr Stat 2016. [DOI: 10.1080/10485252.2016.1272692] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Affiliation(s)
- Jing Sun
- School of Mathematics and Statistics Science, Ludong University, Yantai, People's Republic of China
| | - Yunyan Ma
- School of Mathematics and Statistics Science, Ludong University, Yantai, People's Republic of China
| |
Collapse
|
18
|
Zhou Z, Tang L. Testing for parametric component of partially linear models with missing covariates. Stat Pap (Berl) 2016. [DOI: 10.1007/s00362-016-0848-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
19
|
Sun J, Sun Q. An improved and efficient estimation method for varying-coefficient model with missing covariates. Stat Probab Lett 2015. [DOI: 10.1016/j.spl.2015.09.009] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|