Electronic Journal of Statistics
- Electron. J. Statist.
- Volume 9, Number 1 (2015), 204-218.
High dimension low sample size asymptotics of robust PCA
Conventional principal component analysis is highly susceptible to outliers. In particular, a sufficiently outlying single data point, can draw the leading principal component toward itself. In this paper, we study the effects of outliers for high dimension and low sample size data, using asymptotics. The non-robust nature of conventional principal component analysis is verified through inconsistency under multivariate Gaussian assumptions with a single spike in the covariance structure, in the presence of a contaminating outlier. In the same setting, the robust method of spherical principal components is consistent with the population eigenvector for the spike model, even in the presence of contamination.
Electron. J. Statist., Volume 9, Number 1 (2015), 204-218.
First available in Project Euclid: 9 February 2015
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Zhou, Yi-Hui; Marron, J. S. High dimension low sample size asymptotics of robust PCA. Electron. J. Statist. 9 (2015), no. 1, 204--218. doi:10.1214/15-EJS992. https://projecteuclid.org/euclid.ejs/1423491229