In many situations count data have a large proportion of zeros and the zero-in(ated Poisson
regression (ZIP) model may be appropriate. A simple score test for zero-in(ation, comparing the
ZIP model with a constant proportion of excess zeros to a standard Poisson regression model,
was given by van den Broek (Biometrics, 51 (1995) 738–743). We extend this test to the more
general situation where the zero probability is allowed to depend on covariates. The performance
of this test is evaluated using a simulation study. To identify potentially important covariates in
the zero-in(ation model a composite test is proposed. The use of the general score test and the
composite procedure is illustrated on two examples from the literature. The composite score test
is found to suggest appropriate models