A fast unbinned test on event clustering in Poisson processes

An unbinned statistical test on cluster-like deviations from Poisson processes for point process data is introduced, presented in the context of time variability analysis of astrophysical sources in count rate experiments. The measure of deviation of the actually obtained temporal event distribution from that of a Poisson process is derived from the distribution of time differences between two consecutive events in a natural way. The differential character of the measure suggests this test in particular for the search of irregular burst-like structures in experimental data. The construction allows the application of the test even for very low event numbers. Furthermore, the test can easily be applied in the case of varying acceptance of the detector as well. The simple and direct use of background events simultaneously acquired under the same conditions to account for acceptance variations is possible, allowing for easy application especially in earth-bound gamma-ray experiments. Central features are the fast and simple calculation of its measure, and the existence of an analytical approximation that describes the general test statistics to a high degree of precision.