An Examination of Spatial Scan Statistics Based on Time-to-Event Data

• Activity Number: 36
• Type: Contributed
• Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Iram Usman* and Rhonda Jean Rosychuk
• Companies: University of Alberta and University of Alberta
• Keywords: spatial scan ; time to event ; Weibull ; cluster detection ; geographic analysis ; atrial fibrillation/flutter

Abstract

The spatial scan statistic (SSS) has been used for the identification of geographical clusters of higher numbers of cases of an illness than expected. Disease outbreaks in a geographic area are a typical example. These statistics can also identify geographic areas with longer time to events if the SSS uses appropriate distributions. Other authors have proposed Exponential and Weibull distributions for the event times. We propose the log-Weibull as an alternative distribution for the SSS and compare and contrast the three distributions through simulation studies to investigate Type I censoring. Methods are also illustrated on time to specialist visit (cardiology or internal medicine) data for discharged patients presenting to Emergency Departments for atrial fibrillation and flutter in Alberta during 2010-2011.