An approximation for the distribution of the scan statistic

Publisher Website
Google Scholar
Abstract
The scan statistic evaluates whether an apparent cluster of disease in time is due to chance. The statistic employs a ‘moving window’ of lengthwand finds the maximum number of cases revealed through the window as it scans or slides over the entire time periodT. Computation of the probability of observing a certain size cluster, under the hypothesis of a uniform distribution, is infeasible whenN, the total number of events, is large, andwis of moderate or small size relative toT. We give an approximation that is an asymptotic upper bound, easy to compute, and, for the purposes of hypothesis testing, more accurate than other approximations presented in the literature. The approximation applies both whenNis fixed, and whenNhas a Poisson distribution. We illustrate the procedure on a data set of trisomic spontaneous abortions observed in a two year period in New York City.

This publication has 27 references indexed in Scilit: