The firing activity of place cells of the hippocampus reflects movements of an animal in its experimental area. This well known fact was recently reinvestigated (Fenton and Muller, 1998) and it was found that while the activity was highly reliable in space, it did not retain the same reliability in time. The number of spikes discharged during different passes through the firing field were characteristically very different. We present a mathematical model based on a double stochastic Poisson process, which is able to reproduce the experimental findings. The model permits speculations about the neural mechanisms leading to overdispersion in the activity of the hippocampal place cells.