When the response is a count (a positive integer), we can use a count regression
model to explain this response in terms of the given predictors. Sometimes, the total
count is bounded, in which case a binomial response regression should probably be
used. In other cases, the counts might be sufficiently large that a normal approxima-
tion is justified so that a normal linear model may be used. We shall consider two
distributions for counts. The Poisson and, less commonly, the negative binomial.