Likelihood Ratio Test For The Multivariate Normal Generalized Variance

Main Article Content

Roger Almeida Pereira Melo
https://orcid.org/0009-0000-2933-108X
Marcel Irving Pereira Melo
Daniel Furtado Ferreira

Abstract

An interesting measure of variability in multivariate populations is the determinant of the covariance matrix Σp×p, denoted as |Σ|, commonly referred to as generalized variance. This measure succinctly captures the dispersion of a multivariate population into a single value, while accounting for inter-variable dependencies. Consequently, it finds applications across various domains concerned with assessing dispersion within multivariate populations of interest. In this study, we introduce a likelihood ratio test for the generalized variance of multivariate normal distributions, accompanied by a theoretical exposition on the distribution theory of sample generalized variances. We propose both the Likelihood Ratio Test (LRT) and the Bartlett-Corrected Likelihood Ratio Test (BCLRT) for assessing the hypothesis that the generalized variance equals a parameter η, where η ∈ R. The development of these tests is purely theoretical. Our recommendation is to employ the BCLRT test primarily in scenarios where p = 2, particularly when n > 30. As for the LRT test, we suggest its application in cases where p = 2 or p = 3, provided that n > 30, and for p = 5 when n > 50.

Article Details

How to Cite
Melo, R. A. P. ., Melo, M. I. P. ., & Ferreira, D. F. . (2024). Likelihood Ratio Test For The Multivariate Normal Generalized Variance. Brazilian Journal of Biometrics, 42(4), 351–384. https://doi.org/10.28951/bjb.v42i4.711
Section
Articles

References

Anderson, T. W. An introduction to multivariate statistical analysis 3rd ed., 722 (John Wiley and Sons, Hoboken, 2003).

Arvanitis, L. G. & Afonja, B. Use of the generalized variance and the gradient projection method in multivariate stratified sampling. Biometrics 27, 119–127 (1971). https://doi.org/10.2307/2528931

Bartlett, M. S.On the theory of statistical regression. Proceedings of the Royal Society of Edinburgh 53, 260–283 (1934). https://doi.org/10.1017/S0370164600015637

Bersimis, S., Psarakis, S.&Panaretos, J. Multivariate statistical process control charts: an overview. Qual. Reliab. Eng. Int. 5, 517–543 (2007). https://doi.org/10.1002/qre.829

Bhandary, M. Test for generalized variance in signal processing. Statatistical and Probability Letters 27, 155–162 (1996). https://doi.org/10.1016/0167-7152(95)00058-5

Djauhari, M. A. Improved monitoring of multivariate process variability. Journal of Quality Technology 37, 32–39 (2005). https://doi.org/10.1080/00224065.2005.11980298

Djauhari, M. A., Mashuri, M. & Herwindiati, D. E. Multivariate process variability monitoring. Communication in Statistics - Theory and Methods 37, 1742–1754 (2008). https://doi.org/10.1080/03610920701826286

Djauhari, M. A. Asymptotic distribution of sample covariance determinant. Mathematika 25, 79–85 (2009).

Eaton, M. L. The Generalized Variance: Testing and Ranking Problem. The Annals of Mathematical Statistics 38, 941–943. (2024) (1967). DOI: 10.1214/aoms/1177698892

Gupta, A. S. Tests for simultaneously determining numbers of clusters and their shapewith multivariate data. Statatistical and Probability Letters 1, 46–50 (1982). https://doi.org/10.1016/0167-7152(82)90013-X

Jafari, A. A. & Kazemi, M. R. Inference on the generalized variance under normality. JIRSS 13, 57–67 (2014).

Johnson, R. A. &Wichern, D. W. Applied multivariate statistical analysis 4th ed., 816 (Prentice Hall, New Jersey, 1998).

Kollo, T. & von Rosen, D. Advanced multivariate statistics with matrices 1st ed. (Springer Netherlands, Dordrecht, 2005).

Lee, M. H. & Khoo, M. B. C. Combined synthetic and |S| chart for monitoring process dispersion. Communications in Statistics - Simulation and Computation 46, 5698–5711 (2017). https://doi.org/10.1080/03610918.2016.1171349

Mittelhammer, R. C. Mathematical statistics for economics and business 2nd ed., 742 (Springer, New York, 2013).

Mood, A. M., Graybill, F. A. & Boes, D. C. Introduction to the theory of statistics 3rd ed., 480 (McGraw-Hill, Singapore, 1974).

Muirhead, R. J. Aspects of multivariate statistical theory 673 (JohnWiley, New York, 1982).

Najarzadeh, D. Testing equality of generalized variances of k multivariate normal populations. Communications in Statistics - Simulation and Computation 46, 6414–6423 (2017). https://doi.org/10.1080/03610918.2016.1204457

Najarzadeh, D. Testing equality of standardized generalized variances of k multivariate normal populations with arbitrary dimensions. Statistical Methods and Applications, 1–31 (2019). https://doi.org/10.1007/s10260-019-00456-y

Noor, A. M. & Djauhari, M. A. Monitoring the variability of beltline moulding process using Wilks’s statistic. Malays J. Fundam. Appl. Sci. 6, 116–120 (2014). https://doi.org/10.11113/mjfas.v6n2.193

Pukelsheim, F. Optimal design of experiments 454 (SIAM, New York, 2006).

R CORE TEAM. R: A Language and Environment for Statistical Computing R Foundation for Statistical Computing (Vienna, Austria, 2019). https://www.R-project.org/.

Royston, J. P. Some techniques for assessing multivariate normality based on the Behrens-Fisher W. Applied Statistics - Journal of the Royal Statistical Society - Series C 32, 121–133 (1983).

Sarkar, S. K. On improving the shortest length confidence interval for the generalized variance. Journal of Multivariate Analysis 31, 136–147 (1989). https://doi.org/10.1016/0047-259X(89)90056-0

Sengupta, A. Generalizations of Barlett’s and Hartley’s tests of homogeneity using overall variability. Communication in Statistics - Theory and Methods 16, 987–996 (1987). https://doi.org/10.1080/03610928708829417

Sengupta, A. Tests for standardized generalized variances of multivariate normal populations of possibly different dimensions. Journal Multivariate Analysis 23, 209–219 (1987). https://doi.org/10.1016/0047-259X(87)90153-9

Tallis, G. M. & Light, R. The use of fractional moments for estimating the parameters of a mixed exponential distribution. Technometrics 10, 161–175 (1968). https://doi.org/10.1080/00401706.1968.10490543

Yeh, A. B., J., L. D. K. & McGrath, R. N. Multivariate control charts for monitoring covariance matrix: a review. Qual. Technol. Quant. Manag. 4, 415–436 (2006). https://doi.org/10.1080/16843703.2006.11673124

Yeh, A. B., J., L. D. K., Zhou, H. & Venkataramani, C. A multivariate exponentially weighted moving average control chart for monitoring process variability. Journal of Applied Statistics 30, 507–536 (2003). https://doi.org/10.1080/0266476032000053655

Most read articles by the same author(s)