A new bivariate distribution with applications
We construct a bivariate distribution of (X, Y ) by assuming that the conditional distribution of Y given X is a two-parameter Gamma (s, ν(x)), where the scale parameter depends on X. If X is assumed to be any distribution, then clearly the joint distribution is well defined in all cases. We will study this new distribution by developing all possible properties, moments, shapes and estimation of parameters with a view towards applications of the distribution to data from many random number generation methods.^
Amarasekara, Sathya, "A new bivariate distribution with applications" (2014). ETD Collection for University of Texas, El Paso. AAI1564659.