A flexible multivariate model for high-dimensional correlated count data

Abstract We propose a flexible multivariate stochastic model for over-dispersed count data. Our methodology is built upon mixed Poisson random vectors ( Y 1 ,…, d ), where the { i } are conditionally independent variables. The rates of distributions with arbitrary non-negative margins linked by copula function. present basic properties these and provide several examples. A particular case geometric negative binomial marginal studied in detail. illustrate an application our conducting high-dimensional simulation motivated RNA-sequencing