Use of the scan statistic to detect time-space clustering.

A test for time-space clustering is proposed based on the scan statistic, the maximum number of events in a 365-day period in each of several geographic units. The data under consideration should consist of the exact date and geographic unit for each event, and data should be available for several years for which the risk of disease can be assumed constant. The statistic is the ratio of the excess number of events summed over all the geographic regions, to the square root of the sum of the variances. This statistic is similar in construction to the Ederer-Myers-Mantel statistic (Biometrics 1964;20:626-38), but does not require that attention be limited to calendar years (January 1-December 31). Unlike other tests for time-space clustering, the scan statistic allows one to calculate measures of attributable risk and effect size. Data concerning adolescent suicide are used to illustrate the procedure. The tables and asymptotic formulas given for the mean and variance of the proposed statistic should be useful in the evaluation of both clustering in time and in time-space.