A SCORE TEST FOR THE MULTIVARIATE BURR AND OTHER WEIBULL MIXTURE DISTRIBUTIONS

The p-variate Burr distribution has been derived, developed, discussed and deployed by various authors. In this paper a score statistic for testing independence of the components, equivalent to testing for p in dependent Weibull distributions against a p-variate Burr alternative, is obtained. Its null and non-null properties are investigated with an d without nuisance parameters and including the possibility of censori ng. Two applications to real data are described. The test is also disc ussed in the context of other Weibull mixture models.