Tests for equality of parameter matrices in two multivariate linear models

[摘要] An approximate degrees of freedom test is suggested for hypotheses of the kind H-0:C'Phi(1)M = C'Phi(2)M in two independent multivariate linear models: Y-i = X-i Phi(i)+epsilon(i), i = 1, 2, under the assumption of error matrix variate normality and heteroscedasticity. It is shown for specific vector choices of the matrices C and iM that the test reduces to approximate degrees of freedom solutions obtained by Nel (1989), Nel and van der Merwe (1986) and Welch (1947) for simpler models. (C) 1997 Academic Press.

[发布日期] 1997-04-01

[关键词] Behrens-Fisher problem;degrees of freedom approximation;heteroscedasticity;vec-operator