Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/314

Title: Transformation of Non Positive Semidefinite Correlation Matrices
Authors: Rousseeuw, Peter J.
Molenberghs, Geert
Keywords: Mathematical Statistics
Issue Date: 1993
Citation: Communications in Statistics, Theory and Methods, 22(4), p. 965-984
Abstract: In multivariate statistics, estimation of the covariance or correlation matrix is of crucial importance. Computational and other arguments often lead to the use of coordinate-dependent estimators, yielding matrices that are symmetric but not positive semidefinite. We briefly discuss existing methods, based on shrinking, for transforming such matrices into positive semidefinite matrices. A simple method based on eigenvalues is also considered. Taking into account the geometric structure of correlation matrices, a new method is proposed which uses techniques similar to those of multidimensional scaling.
URI: http://hdl.handle.net/1942/314
Link to publication: https://www.researchgate.net/publication/232858104_Transformation_of_Non_Positive_Semidefinite_Correlation_Matrices
DOI: 10.1080/03610928308831068
ISI #: A1993KZ73700002
ISSN: 0361-0926
Type: Journal Contribution
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version666.88 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.