Affiliation:
1. Faculté des Sciences de Sfax , Université de Sfax , B P 802, 3018 , Sfax , TUNISIA
Abstract
ABSTRACT
In this research paper, we propose a new class of bivariate distributions called Bivariate Generalized Gamma-Lindley (BGGL) distribution with four parameters. This model is a mixture of independent Gamma random variables and bivariate generalized Lindley distribution. We investigate various properties of the new bivariate distribution such as graphical representation, joint moments and correlation. Furthermore, we derive a measure of entropy of this bivariate distribution. We also derive the distributions of the random variables X
1 + X
2, X
1/(X
1 + X
2), X
1/X
2 and X
1
X
2 as well as the corresponding moment properties when X
1 and X
2 follow the BGGL distribution. Additionally, we address two approximations of the product of the proposed model and assess their goodness of fit. Next, we elaborate the expectation maximization (E.M) algorithm in order to estimate the BGGL model parameters. Finally, we provide two concrete examples to demonstrate the applicability of the results.
Reference27 articles.
1. [1] Dasgupta, P.: Two approximations for the distribution of double non-central beta, Sankhyā 30 (1968), 83–88.
2. [2] Dempster, A. P.—Laird, N. M.—Rubin, D. B.: Maximum likelihood from incomplete data via the EM algorithm, J. R. Stat. Soc. Ser. B. Stat. Methodol. 39(1) (1977), 1–38.
3. [3] Drouet-Mari, D.—Kotz, S.: Correlation and Dependence, Imperial College Press, London, 2001.
4. [4] Fan, D.-Y.: The distribution of the product of independent beta variables, Comm. Statist. Theory Methods 20 (1991), 4043–4052.
5. [5] Ghitany, M. E.—Atieh, B.—Nadarajah, S.: Lindley distribution and its application, Math. Comput. Simul. 78(4) (2008), 493–506.