Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1149576 | Journal of Statistical Planning and Inference | 2009 | 7 Pages |
Abstract
The vector correlation coefficient and other measures of association play a very important role in statistics and especially in multivariate analysis. In this paper a new measure of association is proposed and its upper bound is presented by using a matrix trace Wielandt inequality. Also given are relevant results involving Wishart matrices widely used in multivariate analysis, and especially a new alternative for the relative gain of the covariance adjusted estimator of a vector of parameters.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Shuangzhe Liu, Changyu Lu, Simo Puntanen,