A note on sensitivity of principal component subspaces and the efficient detection of influential observations in high dimensions
作者： Luke A. Prendergast
DOI: 10.1214/08-EJS201
关键词: Mathematics 、 Mathematical analysis 、 Estimator 、 Mathematical statistics 、 Linear subspace 、 Principal component analysis 、 Eigenvalues and eigenvectors 、 Applied mathematics 、 Symmetric matrix 、 Sensitivity (control systems) 、 Measure (mathematics)
摘要: In this paper we introduce an influence measure based on second order expansion of the RV and GCD measures for comparison between unperturbed perturbed eigenvectors a symmetric matrix estimator. Example estimators are considered to highlight how compliments recent analysis. Importantly, also show sample version can be used accurately efficiently detect influential observations in practice.
harvard.edu
arxiv.org
sci-hub.st 参考文章(27)
P. Robert, Y. Escoufier, A Unifying Tool for Linear Multivariate Statistical Methods: The RV- Coefficient Applied Statistics. ,vol. 25, pp. 257- 265 ,(1976) , 10.2307/2347233
Ed Anderson, Lapack Users' Guide ,(1995)
F Rellich, Perturbation theory of eigenvalue problems ,(1969)
R. Dennis Cook, Principal Hessian Directions Revisited Journal of the American Statistical Association. ,vol. 93, pp. 84- 94 ,(1998) , 10.1080/01621459.1998.10474090
Frank R. Hampel, The Influence Curve and Its Role in Robust Estimation Journal of the American Statistical Association. ,vol. 69, pp. 383- 393 ,(1974) , 10.1080/01621459.1974.10482962
Jacques Bénasséni, Sensitivity coefficients for the subspaces spanned by principal components Communications in Statistics-theory and Methods. ,vol. 19, pp. 2021- 2034 ,(1990) , 10.1080/03610929008830306
SUSAN J. DEVLIN, R. GNANADESIKAN, J. R. KETTENRING, Robust estimation and outlier detection with correlation coefficients Biometrika. ,vol. 62, pp. 531- 545 ,(1975) , 10.1093/BIOMET/62.3.531
Hendrik P. Lopuhaa, On the relation between S-estimators and M-estimators of multivariate location and covariance Annals of Statistics. ,vol. 17, pp. 1662- 1683 ,(1989) , 10.1214/AOS/1176347386
Elvezio M. Ronchetti, Peter J. Rousseeuw, Werner A. Stahel, Frank R. Hampel, Robust statistics: the approach based on influence functions ,(1986)
Luke Anthony. Prendergast, Jodie Ann. Smith, Sensitivity of principal Hessian direction analysis Electronic Journal of Statistics. ,vol. 1, pp. 253- 267 ,(2007) , 10.1214/07-EJS064