Annals of Statistics
- Ann. Statist.
- Volume 45, Number 3 (2017), 1342-1374.
Asymptotics of empirical eigenstructure for high dimensional spiked covariance
Abstract
We derive the asymptotic distributions of the spiked eigenvalues and eigenvectors under a generalized and unified asymptotic regime, which takes into account the magnitude of spiked eigenvalues, sample size and dimensionality. This regime allows high dimensionality and diverging eigenvalues and provides new insights into the roles that the leading eigenvalues, sample size and dimensionality play in principal component analysis. Our results are a natural extension of those in [Statist. Sinica 17 (2007) 1617–1642] to a more general setting and solve the rates of convergence problems in [Statist. Sinica 26 (2016) 1747–1770]. They also reveal the biases of estimating leading eigenvalues and eigenvectors by using principal component analysis, and lead to a new covariance estimator for the approximate factor model, called Shrinkage Principal Orthogonal complEment Thresholding (S-POET), that corrects the biases. Our results are successfully applied to outstanding problems in estimation of risks for large portfolios and false discovery proportions for dependent test statistics and are illustrated by simulation studies.
Article information
Source
Ann. Statist., Volume 45, Number 3 (2017), 1342-1374.
Dates
Received: September 2015
Revised: June 2016
First available in Project Euclid: 13 June 2017
Permanent link to this document
https://projecteuclid.org/euclid.aos/1497319697
Digital Object Identifier
doi:10.1214/16-AOS1487
Mathematical Reviews number (MathSciNet)
MR3662457
Zentralblatt MATH identifier
1373.62299
Subjects
Primary: 62H25: Factor analysis and principal components; correspondence analysis
Secondary: 62H10: Distribution of statistics
Keywords
Asymptotic distributions principal component analysis diverging eigenvalues approximate factor model relative risk management false discovery proportion
Citation
Wang, Weichen; Fan, Jianqing. Asymptotics of empirical eigenstructure for high dimensional spiked covariance. Ann. Statist. 45 (2017), no. 3, 1342--1374. doi:10.1214/16-AOS1487. https://projecteuclid.org/euclid.aos/1497319697
Supplemental materials
- Technical proofs [Wang and Fan (2017)]. This document contains technical lemmas for Section 3 and the comparison of assumptions and theoretical proofs for Section 4.Digital Object Identifier: doi:10.1214/16-AOS1487SUPP