2016 Fiscal Year Final Research Report
Statistical models for detecting clusters of rare events
Project/Area Number |
26280008
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Statistical science
|
Research Institution | Teikyo University |
Principal Investigator |
Tango Toshiro 帝京大学, 大学院公衆衛生学研究科, 教授 (70124477)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Keywords | 空間疫学 / 疾病集積性 / 環境統計 |
Outline of Final Research Achievements |
In this study, we improved statistical models proposed by Tango et al. for detecting disease clusters and emerging disease outbreaks. Compared with other existing statistical models, Tango et al.’s models have shown a lot of good performance in actual epidemiological cluster detection but it has been said in the literature that (1) their models have low detection probability of the true cluster and (2) they have difficulty in correctly detecting the growth of space-time disease outbreaks. The first problem was improved by modifying a restricted likelihood ratio. To overcome the second problem we considered a improved space-time scan statistic for detecting localized emerging disease outbreaks which can detect outbreaks more timely and correctly. These properties are illustrated with data from the weekly surveillance of the number of absentees in primary schools in Kitakyushu-shi Japan, 2006.
|
Free Research Field |
総合領域
|