Accession Number : ADA135666

Title :   A Robust Multiple Correlation Coefficient for the Rank Analysis of Linear Models.

Descriptive Note : Technical rept.,

Corporate Author : WESTERN MICHIGAN UNIV KALAMAZOO DEPT OF MATHEMATICS

Personal Author(s) : Sievers,G L

PDF Url : ADA135666

Report Date : Sep 1983

Pagination or Media Count : 26

Abstract : A multiple correlation coefficient is discussed to measure the degree of association between a random variable Y and a set of random variables X sub l, ..., X sub p. The coefficient is defined in terms of weighted Kendall's tau, suitably normalized. It is directly compatible with the rank statistic approach of analyzing linear models in a regression, prediction context. The population parameter equals the classical multiple correlation coefficient if the multivariate normal model holds but would be more robust for departures from this model. Some results are given on the consistency of the sample estimate and on a test for independence. (Author)

Descriptors :   *Correlation techniques, *Rank order statistics, *Coefficients, *Mathematical models, Linearity, Random variables, Predictions, Bivariate analysis, Multivariate analysis, Consistency

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE