A TEST FOR DETECTION OF CLUSTERING OVER TIME

Abstract
The use of the scan statistic in testing for clustering in time is discussed with particular reference to a reported clustering of trisomles in spontaneous abortions in New York City. The scan statistic is the maximum number of observed cases in an interval of preselected length, as the interval is allowed to scan, or slide along, the time frame of interest. A table of the lower tail of the distribution of this statistic is given.

This publication has 2 references indexed in Scilit: