Lack of robustness in time-space disease clustering
作者:
Paula K. Roberson,
Lloyd Fisher,
期刊:
Communications in Statistics - Simulation and Computation
(Taylor Available online 1983)
卷期:
Volume 12,
issue 1
页码: 11-22
ISSN:0361-0918
年代: 1983
DOI:10.1080/03610918308812297
出版商: Marcel Dekker, Inc.
关键词: disease models;epidemiology
数据来源: Taylor
摘要:
The Knox and Mantel procedures of time-space disease clustering are shown to be nonrobust in certain situations. The effect of selecting the necessary constants by a trial-and-error approach drastically alters the nominal significance level. When the population is shifting over time or when the detection rate of the disease is not constant, this artificially induced space-time clustering can increase the probability of rejection to two or more times the nominal significance level.
点击下载:
PDF (248KB)
返 回