Testing linear hypotheses in high-dimensional regressions

Type: Article

Publication Date: 2013-09-26

Citations: 32

DOI: https://doi.org/10.1080/02331888.2012.708031

Abstract

Abstract For a multivariate linear model, Wilk's likelihood ratio test (LRT) constitutes one of the cornerstone tools. However, the computation of its quantiles under the null or the alternative hypothesis requires complex analytic approximations, and more importantly, these distributional approximations are feasible only for moderate dimension of the dependent variable, say p≤20. On the other hand, assuming that the data dimension p as well as the number q of regression variables are fixed while the sample size n grows, several asymptotic approximations are proposed in the literature for Wilk's Λ including the widely used chi-square approximation. In this paper, we consider necessary modifications to Wilk's test in a high-dimensional context, specifically assuming a high data dimension p and a large sample size n. Based on recent random matrix theory, the correction we propose to Wilk's test is asymptotically Gaussian under the null hypothesis and simulations demonstrate that the corrected LRT has very satisfactory size and power, surely in the large p and large n context, but also for moderately large data dimensions such as p=30 or p=50. As a byproduct, we give a reason explaining why the standard chi-square approximation fails for high-dimensional data. We also introduce a new procedure for the classical multiple sample significance test in multivariate analysis of variance which is valid for high-dimensional data. Keywords: high-dimensional datamultivariate regressionmultivariate analysis of varianceWilk's testmultiple sample significance testrandom matrices AMS 2000 Subject Classifications : Primary 62H15secondary 62H10 Acknowledgements The authors acknowledge the support from the following research grants: NSFC grant 11171057 (Z.D. Bai), NSFC grant 11101181 and RFDP grant 20110061120005 (D. Jiang), HKU Start-up Fund (J. Yao) and NSFC-11171058 and NECT-11-0616 (S. Zheng).

Locations

  • arXiv (Cornell University) - View - PDF
  • DataCite API - View
  • Statistics - View

Similar Works

Action Title Year Authors
+ High Dimensional Analysis of Variance in Multivariate Linear Regression 2023 Zhipeng Lou
Xianyang Zhang
Wei Biao Wu
+ PDF Chat High-dimensional analysis of variance in multivariate linear regression 2023 Zhipeng Lou
Xianyang Zhang
Wei Biao Wu
+ Likelihood Ratio Test in Multivariate Linear Regression: from Low to High Dimension 2018 Yinqiu He
Tiefeng Jiang
Jiyang Wen
Gongjun Xu
+ PDF Chat Likelihood Ratio Test in Multivariate Linear Regression: from Low to High Dimension 2019 Yinqiu He
Tiefeng Jiang
Jiyang Wen
Gongjun Xu
+ PDF Chat Testing a single regression coefficient in high dimensional linear models 2016 Wei Lan
Ping-Shou Zhong
Runze Li
Hansheng Wang
Chih‐Ling Tsai
+ Scalar-Invariant Test for High-Dimensional Regression Coefficients 2015 Long Feng
+ Testing a Single Regression Coefficient in High Dimensional Regression Model 2016 Wei Lan
Ping‐Shou Zhong
Runze Li
Hansheng Wang
Chih‐Ling Tsai
+ The likelihood ratio test for high-dimensional linear regression model 2016 Junshan Xie
Nannan Xiao
+ Generalized<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" altimg="si57.gif" display="inline" overflow="scroll"><mml:mi>F</mml:mi></mml:math>test for high dimensional linear regression coefficients 2013 Siyang Wang
Hengjian Cui
+ Large Sample Covariance Matrices and High-Dimensional Data Analysis 2015 Jianfeng Yao
Shurong Zheng
Zhidong Bai
+ PDF Chat Nonasymptotic Analysis of the Lawley–Hotelling Statistic for High-Dimensional Data 2021 A. A. Lipatiev
Vladimir V. Ulyanov
+ Statistical significance in high-dimensional linear models 2013 Peter Bühlmann
+ PDF Chat Linear Hypothesis Testing in Dense High-Dimensional Linear Models 2017 Yinchu Zhu
Jelena Bradić
+ A new nonparametric test for high-dimensional regression coefficients 2016 Kai Xu
+ High-dimensional testing for proportional covariance matrices 2019 Koji Tsukuda
Shun Matsuura
+ PDF Chat Rank-based score tests for high-dimensional regression coefficients 2013 Long Feng
Changliang Zou
Zhaojun Wang
Бин Чэн
+ On the Phase Transition of Wilk's Phenomenon 2020 Yinqiu He
Bo Meng
Zhenghao Zeng
Gongjun Xu
+ High dimensional data challenges in estimating multiple linear regression 2020 Jassim N. Hussain
+ Testing in Linear Models 2014 Vladimir Spokoiny
Thorsten Dickhaus
+ Testing for Heteroscedasticity in High-dimensional Regressions 2015 Zhaoyuan Li
Jianfeng Yao