A Weighted Poisson Distribution for Underdispersed Count Data

In this paper, we present a new weighted Poisson distribution for modeling underdispersed count data. Weighted occurs naturally in contexts where the probability that particular observation of variable enters sample gets multiplied by some non-negative weight function. Suppose realization y Y random investigator’s record with proportional to w(y): Clearly, recorded is not an on Y, but Yw, which said be version Y. This two-parameter from exponential family, it includes and generalizes weighting. It discrete more flexible than other distributions have been proposed data, example, extended (Dimitrov Kolev, 2000). We moment properties estimate its parameters. One classical example considered compare fits distribution.