A comparison of some methods for the selection of a common eigenvector model for the covariance matrices of two groups

Pepler, P.T. , Uys, D.W. and Nel, D.G. (2016) A comparison of some methods for the selection of a common eigenvector model for the covariance matrices of two groups. Communications in Statistics: Simulation and Computation, 45(8), pp. 2917-2936. (doi:10.1080/03610918.2014.932801)

Full text not currently available from Enlighten.

Abstract

Two new non-parametric common principal component model selection procedures based on bootstrap distributions of the vector correlations of all combinations of the eigenvectors from two groups are proposed. The performance of these methods is compared in a simulation study to the two parametric methods previously suggested by Flury (1988), as well as modified versions of two non-parametric methods proposed by Klingenberg (1996) and Klingenberg and McIntyre (1998). The proposed bootstrap vector correlation distribution (BVD) method is shown to outperform all of the existing methods in most of the simulated situations considered.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Pepler, Dr Theo
Authors: Pepler, P.T., Uys, D.W., and Nel, D.G.
College/School:College of Medical Veterinary and Life Sciences > Institute of Biodiversity Animal Health and Comparative Medicine
Journal Name:Communications in Statistics: Simulation and Computation
Publisher:Taylor & Francis
ISSN:0361-0918
ISSN (Online):1532-4141
Published Online:30 October 2014

University Staff: Request a correction | Enlighten Editors: Update this record