Abstract: This paper studies the determinants of the dynamics of a handball match. The model accounts for the binary character of the dependent variable, and for unobserved heterogeneity. This model is rather general, and may be used in many economic applications. The setting is dynamic in two ways: the probability of scoring may depend on past performance, and its impact is itself time-varying. Three models are considered according to the parameter dynamics: a fixed coefficient model (dummy variables), and two random coefficient specifications, namely a stationary process and an AR(1) model. A constant parameter specification is also considered for the sake of comparison.