Summary
The general nonnull distribution of Wilks statistic, the likelihood ratio statistic in MANOVA, can be expressed as a product of conditional beta variables [3]. Making use of this results, in the present paper, an upper bound for the nonnull distribution of Wilks statistic is obtained, which provides a conservative evaluation of the power of the likelihood ratio test for the cases when the alternative hypothesis is of rank 1, 2 or 3. Forp=2, wherep is the number of variables, and largef 2, the degrees of freedom, it has been shown that the results of this paper give a much better approximation to the power of Wilks statistic than Mikhail's approximation [10]. A few percentage points have also been computed forp=3 and selected values of the degrees of freedom and the noncentrality parameters, which in the linear case have been compared with the exact values obtained by the author [7].
Similar content being viewed by others
References
Anderson, T. W. (1946). The noncentral Wishart distribution and certain problems of multivariate statistics,Ann. Math. Statist.,17, 409–431.
Anderson, T. W. and Girshick, M. A. (1944). Some extensions of the Wishart distribution,Ann. Math. Statist.,15, 345–357.
Asoh, Y. H. and Okamoto, M. (1969). A note on the nonnull distribution of the Wilks statistic in MANOVA,Ann. Inst. Statist. Math.,21, 67–72.
Dasgupta, S., Anderson, T. W. and Mudholkar, G. S. (1964). Monotonocity of power functions of some tests of the multivariate linear hypothesis,Ann. Math. Statist.,35, 200–205.
Ghosh, M. N. (1964). On the admissibility of some tests of MANOVA,Ann. Math. Statist.,35, 789–794.
Gupta, A. K. (1968). Some central and noncentral distribution problems in multivariate analysis,Mimeo. Series, No. 139, Department of Statistics, Purdue University.
Gupta, A. K. (1971). Noncentral distribution of Wilks statistic in MANOVA,Ann. Math. Statist.,42, 1254–1261.
Katti, S. K. (1961). Distribution of the likelihood ratio for testing multivariate linear hypothesis,Ann. Math. Statist.,32, 333–335.
Kiefer, J. and Schwartz, R. (1965). Admissible Bayes character ofT 2,R 2-and other fully invariant tests for classical multivariate normal problems,Ann. Math. Statist.,36, 747–770.
Mikhail, N. N. (1965). A comparison of tests of the Wilks-Lawley hypothesis in multivariate analysis,Biometrika,52, 149–156.
Pearson, E. S. and Wilks, S. S. (1933). Methods of analysis appropriate fork samples of two variables,Biometrika,25, 353–378.
Pillai, K. C. S. and Gupta, A. K. (1969). On the exact distribution of Wilk's criterion,Biometrika,56, 109–118.
Pillai, K. C. S. and Jayachandran, K. (1967). Power comparisons of tests of two multivariate hypotheses based on four criteria,Biometrika,54, 195–210.
Schatzoff, M. (1966). Exact distribution of Wilks' likelihood-ratio criterion,Biometrika,53, 347–358.
Wijsman, R. A. (1957). Random orthogonal transformations and their use in some classical distribution problems in multivariate analysis,Ann. Math. Statist.,28, 415–423.
Wilks, S. S. (1932). Certain generalisations in the analysis of variance,Biometrika,24, 471–494.
Author information
Authors and Affiliations
Additional information
An erratum to this article is available at http://dx.doi.org/10.1007/BF02504735.
About this article
Cite this article
Gupta, A.K. On a stochastic inequality for the wilks statistic. Ann Inst Stat Math 27, 341–348 (1975). https://doi.org/10.1007/BF02504653
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02504653