Premium
A Global Rank Test for Geographical Clusters of Disease
Author(s) -
Möhner M.
Publication year - 1991
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710330311
Subject(s) - statistics , rank (graph theory) , goodness of fit , mathematics , test (biology) , distribution (mathematics) , econometrics , combinatorics , mathematical analysis , geology , paleontology
Abstract In the last years a considerable amount of effort has been put into the methodology of mapping and analysis of geographical distribution of cancer incidence or mortality. A test for geographical clusters, taking into account the rank order with respect to the cancer incidence was proposed in the Cancer Atlas of Scotland (K EMP et al. (1985)). But, unfortunately the test requires a time‐consuming simulation for the distribution function of the corresponding test statistics. In the present paper an easy calculable normal approximation of this rank‐test will be derived. A simulation study for two regions shows that the goodness of approximation is much better than it could be assumed by the corresponding bounds derived by the Berry‐Esseen‐inequality.