Approximation of power in multivariate analysis

We consider the calculation of power functions in classical multivariate analysis. In this context, power can be expressed in terms of tail probabilities of certain noncentral distributions. The necessary noncentral distribution theory was developed between the 1940s and 1970s by a number of authors. However, tractable methods for calculating the relevant probabilities have been lacking. In this paper we present simple yet extremely accurate saddlepoint approximations to power functions associated with the following classical test statistics: the likelihood ratio statistic for testing the general linear hypothesis in MANOVA; the likelihood ratio statistic for testing block independence; and Bartlett's modified likelihood ratio statistic for testing equality of covariance matrices.

[1]  G. Box,et al.  A general distribution theory for a class of likelihood criteria. , 1949, Biometrika.

[2]  M. Srivastava,et al.  Saddlepoint method for obtaining tail probability of Wilks' likelihood ratio test , 1989 .

[3]  A. J. Collins,et al.  Introduction To Multivariate Analysis , 1981 .

[4]  J. Booth,et al.  Saddlepoint Approximations for Tests of Block Independence, Sphericity and Equal Variances and Covariances , 1993 .

[5]  R. Muirhead.  On the Test of Independence Between Two Sets of Variates , 1972 .

[6]  Asymptotic formulas for the hyperġeometric function2F1 of matrix argument, useful in multivariate analysis , 1974 .

[7]  C. Herz.  BESSEL FUNCTIONS OF MATRIX ARGUMENT , 1955 .

[8]  Ronald W. Butler,et al.  Saddlepoint approximations for P-values of some tests of covariance matrices , 1995 .

[9]  S. Rice,et al.  Saddle point approximation for the distribution of the sum of independent random variables , 1980, Advances in Applied Probability.

[10]  Jens Ledet Jensen,et al.  A Large Deviation-Type Approximation for the “Box Class” of Likelihood Ratio Criteria , 1991 .

[11]  B. N. Nagarsenker,et al.  An Asymptotic Expansion of the Nonnull Distribution of Wilks Criterion for Testing the Multivariate Linear Hypothesis , 1984 .

[12]  A. James.  The Distribution of the Latent Roots of the Covariance Matrix , 1960 .

[13]  R. Butler,et al.  Saddlepoint approximations for the generalized variance and Wilks statistic , 1992 .

[14]  R. Butler,et al.  A Dimensional CLT for Non‐Central Wilks’ Lambda in Multivariate Analysis , 2004 .

[15]  A. James.  Zonal Polynomials of the Real Positive Definite Symmetric Matrices , 1961 .

[16]  George Henry Dunteman,et al.  Introduction To Multivariate Analysis , 1984 .

[17]  N. Sugiura.  Further asymptotic formulas for the non-null distributions of three statistics for multivariate linear hypothesis , 1973 .

[18]  K. Muller,et al.  Power Calculations for General Linear Multivariate Models Including Repeated Measures Applications. , 1992, Journal of the American Statistical Association.

[19]  N. Sugiura,et al.  Asymptotic non-null distributions of the likelihood ratio criteria for covariance matrix under local alternatives , 1973 .

[20]  N. Sugiura.  Asymptotic solutions of the hypergeometric function1F1 of matrix argument, useful in multivariate analysis , 1972 .

[21]  Yasunori Fujikoshi,et al.  Asymptotic Expansions of the Non-Null Distributions of the Likelihood Ratio Criteria for Multivariate Linear Hypothesis and Independence , 1969 .

[22]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

[23]  A. Constantine.  Some Non-Central Distribution Problems in Multivariate Analysis , 1963 .

[24]  Andrew T. A. Wood,et al.  Laplace approximations for hypergeometric functions with matrix argument , 2002 .

[25]  Yoong-Sin Lee.  Distribution of the Canonical Correlations and Asymptotic Expansions for Distributions of Certain Independence Test Statistics , 1971 .

[26]  Keith E. Muller,et al.  Practical methods for computing power in testing the multivariate general linear hypothesis , 1984 .