Probabilistic representation of the temporal rainfall process by a modified Neyman‐Scott Rectangular Pulses Model: Parameter estimation and validation

The capability of the Neyman‐Scott clustered stochastic point process model of rainfall to preserve various observed statistics is considered. Randomization of the cell duration parameter from storm to storm is shown to considerably improve the wet‐dry period, joint distribution, and extreme value statistics. A simple procedure for parameter estimation is introduced and applied.