Sharp detection in PCA under correlations: all eigenvalues matter

DOI10.1214/16-AOS1514zbMath1486.62182arXiv1602.06896MaRDI QIDQ2403438

Edgar Dobriban

Publication date: 8 September 2017

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1602.06896

zbMATH Keywords

principal component analysislinear integral equationrandom matrix theorylinear spectral statisticoptimal testing

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Hypothesis testing in multivariate analysis (62H15) Fredholm integral equations (45B05)

Related Items (9)

Statistical inference for principal components of spiked covariance matrices ⋮ Optimal prediction in the linearly transformed spiked model ⋮ Fundamental limits of detection in the spiked Wigner model ⋮ Testing in high-dimensional spiked models ⋮ \(e\)PCA: high dimensional exponential family PCA ⋮ High-dimensional asymptotics of prediction: ridge regression and classification ⋮ Optimality and sub-optimality of PCA. I: Spiked random matrix models ⋮ Random matrix theory and its applications ⋮ Eigenvalue distributions of variance components estimators in high-dimensional random effects models

This page was built for publication: Sharp detection in PCA under correlations: all eigenvalues matter