Abstract
The exact distribution of the likelihood ratio test statistic to test the equality of several variance-covariance matrices has a non-manageable form. On the other hand, the existing asymptotic approximations do not exhibit the necessary precision for many applications. For these reasons, the development of near-exact approximations to the distribution of this statistic, arising from a different method of approximating distributions, emerges as a desirable goal. These distributions, while being manageable are much closer to the exact distribution than the usual asymptotic distributions and opposite to these, are also asymptotic for increasing number of variables and matrices involved. Computational modules to implement the near-exact distributions are made available on a web-site.
Similar content being viewed by others
References
Alberto RP, Coelho CA (2007) Study of the quality of several asymptotic and near-exact approximations based on moments for the distribution of the Wilks lambda statistic. J Stat Plan Inference 137: 1612–1626
Andersen H, Larsen S, Spliid H, Christensen ND (1999) Multivariate statistical analysis of organ weighs in toxicity studies. Toxicology 136: 67–77
Anderson TW (2003) An introduction to multivariate statistical analysis, 3rd edn. Wiley, New York
Anderson TW, Fang K-T, Hsu H (1986) Maximum-likelihood estimates and likelihood-ratio criteria for multivariate elliptically contoured distributions. Can J Stat 14: 55–59
Anderson TW, Fang K-T (1990) Inference in multivariate elliptically contoured distributions based on maximum likelihood. In: Fang K-T, Anderson TW (eds) Statistical inference in elliptically contoured and related distributions. Allerton Press, NY, pp 201–216
Bartlett MS (1937) Properties of sufficiency and statistical tests. Proc R Soc Lond Ser A Math Phys Sci 160: 268–282
Berry A (1941) The accuracy of the Gaussian approximation to the sum of independent variates. Trans Am Math Soc 49: 122–136
Booth JG, Butler RW, Huzurbazar S, Wood ATA (1995) Saddlepoint approximations for p-values of some tests of covariance matrices. J Stat Comput Simul 53: 165–180
Box GEP (1949) A general distribution theory for a class of likelihood criteria. Biometrika 36: 317–346
Coelho CA (1998) The generalized integer gamma distribution—a basis for distributions in multivariate statistics. J Multivar Anal 64: 86–102
Coelho CA (2004) The generalized near-integer gamma distribution: a basis for ’near-exact’ approximations to the distribution of statistics which are the product of an odd number of independent beta random variables. J Multivar Anal 89: 191–218
Coelho CA, Alberto RP, Grilo LM (2006) A mixture of generalized integer gamma distributions as the exact distribution of the product of an odd number of independent Beta random variables. J Interdiscip Math 9: 229–248
Coelho CA, Marques FJ (2009) Near-exact distributions for the independence and sphericity likelihood ratio test statistics. J Multivar Anal 101: 583–593
Coelho CA, Marques FJ (2009b) Near-exact distributions for the likelihood ratio test statistic for testing equality of several variance-covariance matrices (Revisited). Universidade Nova de Lisboa, Departamento de Matemática, Technical Report 9/2009 (http://www.dmat.fct.unl.pt/fct/servlet/DownloadFile?file=1162&sub=investiga&modo=prepub)
Esseen C-G (1945) Fourier analysis of distribution functions. A Math Study Laplace-Gaussian Law Acta Math 77: 1–125
Gil-Pelaez J (1951) Note on the inversion theorem. Biometrika 38: 481–482
Grilo LM, Coelho CA (2007) Development and study of two near-exact approximations to the distribution of the product of an odd number of independent beta random variables. J Stat Plan Inference 137: 1560–1575
Gupta AK, Tang J (1984) Distribution of the likelihood ratio statistic for testing equality of covariance matrices of multivariate Gaussian models. Biometrika 71: 555–559
Hwang H-K (1998) On convergence rates in the central limit theorems for combinatorial structures. Euro J Combin 19: 329–343
Jamshidiana M, Schott JR (2007) Testing equality of covariance matrices when data are incomplete. Comput Stat Data Anal 51: 4227–4239
Jensen DR, Good IJ (1981) Invariant distributions associated with matrix laws under structural symmetry. J Roy Stat Soc Ser B 43: 327–332
Jensen JL (1991) A large deviation-type approximation for the ‘Box class’ of likelihood ratio criteria. J Am Stat Assoc 86: 437–440
Jensen JL (1995) Correction to ‘A large deviation-type approximation for the ‘Box class’ of likelihood ratio criteria’. J Am Stat Assoc 90: 812
Kariya T (1981) Robustness of multivariate tests. Ann Stat 9: 1267–1275
Korin BP (1968) On testing equality for k covariance matrices. Biometrika 55: 216–218
Lo Y (2008) A likelihood ratio test of a homoscedastic normal mixture against a heteroscedastic normal mixture. Stat Comput 18: 233–240
Loève M (1977) Probability theory, vol I, 4th edn. Springer, New York
Marques FJ, Coelho CA (2008) Near-exact distributions for the sphericity likelihood ratio test statistic. J Stat Plan Inference 138: 726–741
Muirhead RJ (1982) Aspects of multivariate statistical theory. Wiley, New York
Perlman M (1980) Unbiasedness of the LRT for equality of several covariance matrices and equality of several multivariate normal populations. Biometrika 8: 247–263
Pitman EJG (1939) Tests of hypotheses concerning location and scale parameters. Biometrika 31: 200–215
Rigby RA (1997) Bayesian discrimination between two multivariate normal populations with equal covariance matrices. J Am Stat Assoc 92: 1151–1154
Srivastava MS (1967) Classification into multivariate normal populations when the population means are linearly restricted. Ann Inst Stat Math 19: 473–478
Widder DV (1934) The inversion of the Laplace integral and the related moment problem. Trans Am Math Soc 36: 107–200
Wilks SS (1932) Certain generalizations in the analysis of variance. Biometrika 24: 471–494
Zhang J, Boos D (1992) Bootstrap critical values for testing homogeneity of covariance matrices. J Am Stat Assoc 87: 425–429
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Coelho, C.A., Marques, F.J. Near-exact distributions for the likelihood ratio test statistic to test equality of several variance-covariance matrices in elliptically contoured distributions. Comput Stat 27, 627–659 (2012). https://doi.org/10.1007/s00180-011-0281-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-011-0281-1