Abstract:In this paper, the matrix variate $\theta$-generalized normal distribution is introduced. Then its properties are studied. In particular, it is proved that this distribution has maximal entropy in a certain class of distributions.
R. Goodman and S. Kotz, Multivariate $\theta$-generalized normal distributions, J. Multivariate Anal. 3 (1973), 204-219.
K. Gupta and T. Varga, Characterization of matrix variate normal distributions, J. Multivariate Anal. 41 (1992), 80-88.
—, Elliptically contoured models in statistics, Kluwer Academic, Dordrecht, 1993.
J. Muirhead, Aspects of multivariate statistical theory, Wiley, New York, 1982.
- © Copyright 1995 American Mathematical Society
- Journal: Trans. Amer. Math. Soc. 347 (1995), 1429-1437
- MSC: Primary 62H10; Secondary 60E05, 62E15
- DOI: https://doi.org/10.1090/S0002-9947-1995-1277112-9
- MathSciNet review: 1277112