Stand mortality models play an important role in simulating stand dynamic processes. Periodic stand mortality data from permanent plots tend to be dispersed, and frequently contain an excess of zero counts. Such data have commonly been analyzed using the Poisson distribution and Poisson mixture models, such as the zero-inflated Poisson model (ZIP), and the Hurdle Poisson model (HP). Based on mortality data obtained from sixty Chinese pine (Pinus tabulaeformis) permanent plots near Beijing, we added the random-effects to the Poisson mixture models. Results showed that the random-effects in the ZIP model was not convergent, and HP mixed-effects model performed better in modeling stand mortality than the Poisson fixed-effects model, the Poisson mixed-effects model, the ZIP fixed-effects model and the HP fixed-effects model. Moreover, the HP model accounts for two sources of dispersion, the first accounting for extra zeros and the second accounting to some extent for the dispersion due by individual heterogeneity in the positive set. We also found that stand mortality was negatively related to stand arithmetic mean diameter and positively related to dominant height.