© 1973 by Biometrika Trust
On the multivariate Behrens-Fisher problem
University of Manitoba
This paper is concerned with the relative merits of statistical procedures for the classical Behrens-Fisher problem in the p-dimensional case. There are three such methods considered here: (i) the approximate degrees-of-freedom solution put forward by Yao (1965), (ii) James's (1954) asymptotic series solution and (iii) Bennett's (1951) extension of Soheffé's (1943) solution to the univariate problem. Monte-Carlo studies are made of the level of significance and power function.
Key Words: Behrens-Fisher problem Level of significance of multivariate tests Power of a test Simulation Monte Carlo
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
W. T. Coombs, J. Algina, and D. O. Oltman Univariate and Multivariate Omnibus Hypothesis Tests Selected to Control Type I Error Rates When Population Variances Are Not Necessarily Equal Review of Educational Research, January 1, 1996; 66(2): 137 - 179. [Abstract] [PDF] |
||||
