統計学輪講（第２９回）

時	2000年10月24日(火)    15時〜16時40分
場所	経済学部5階視聴覚室
講演者　Toshiro Tango ( National Institute of Public Health )
演題　	Score Tests for Detecting  Excess Risks Around Putative Sources
概要
   Focused clustering studies examine raised disease risk around prespecified
 point sources. As statistical methods to detect such clusters, 
 Stone's maximum likelihood ratio test against the general ordered 
 alternatives and score tests which scores each case the reciprocal of the  
 distance from a point source as a surrogate exposure are popular among others.
   In this talk, I present some extensions of score tests in that 
 (1) it can allow us to select the best among pre-specified parametric 
 exposure functions to avoid multiple testing problems and (2) it can be
 applied to a possible situation that the hazardous substance levels   
 have a peak at some distance from a point source. 
   The proposed tests are illustrated with hypothetical data as well as
 simulated data to be expected in an epidemiological study currently
 in progress regarding an excess risk of perinatal undersirable outcomes
 near municipal solid waste incinerators in Japan.