Discrete count outcome

Counts can be considered in different ways. If the count represents simple counting of observations, the Poisson model may be an appropriate starting point. However, if there is over-dispersion, the negative binomial may better capture the data.

If the counts are of the number of successes in repeated binary trials, then the binomial model is appropriate.

In cases where there is an over-representation of zeroes in the data, this can be modelled with zero-inflated versions of the distributions. Alternatively, hurdle models are useful when the process generating the zero counts is conceptually different from the one generating the positive counts.