Adjusting Moran's I for population density by N. Oden, Statistics in Medicine, 14, 17–26 (1995)

✍ Scribed by T. Tango

• Publisher: John Wiley and Sons
• Year: 1998
• Tongue: English
• Weight: 72 KB
• Volume: 17
• Category: Article
• ISSN: 0277-6715
• DOI: 10.1002/(sici)1097-0258(19980515)17:9<1055::aid-sim708>3.0.co;2-n

✦ Synopsis

Shirokanedai 4 Chome Minato-ku ¹okyo 108, Japan Recently, Oden proposed two test statistics, I and I* , to detect disease clustering in space, which have been introduced by adjusting Moran's I for population density. Oden has shown the superiority of I* according to the results of power study showing the order: I* ' 'I 'I. (1) Further, Oden et al. have compared the power of three tests for spatial clustering and also shown the superiority of I* in most cases. However, I have to conclude the superiority of I* to be incorrect, at least in general, judging by several important points discussed below.