日時 2004年 12月 7日(火) 15時〜16時40分 場所 経済学部新棟3階第3教室 講演者 Kunihiko Takahashi* and Toshiro Tango(Department of Technology Assessment and Biostatistics, National Institute of Public Health) 演題 A flexible scan statistic for spatial cluster detection 概要: Kulldorff's spatial scan statistic(1997) has been applied in a wide variety of epidemiological studies for spatial cluster detection. His scan statistic, however, uses a circular window to define the potential cluster areas and thus has a difficulty of correctly identifying actual noncircular clusters. We propose a flexible scan statistic that can identify clusters of any shape. The performance of the proposed procedure is compared with that of Kulldorff's circle-based scan statistic via Monte Carlo simulation by considering several circular and noncircular hot-spot cluster models. To compare the performance of these tests, we introduced (1)bivariate power function classified by the number of regions detected as the most likely cluster and the number of hot-spot regions included in the most likely cluster and (2) a new performance measure including the usual power as a special case. The proposed flexible scan statistic is shown to have higher usual powers and also to identify the noncircular hot-spot clusters more accurately than Kulldorff's scan statistic.
Tokyo University