Cuzick–Edwards test

{{Short description|Statistical significance test}}

In statistics, the Cuzick–Edwards test{{cite journal|title=Spatial clustering for inhomogeneous populations|author=Jack Cuzick and Robert Edwards|journal=Journal of the Royal Statistical Society, Series B|issn=0035-9246|year=1990|volume=52|issue=1|pages=73–104|doi=10.1111/j.2517-6161.1990.tb01773.x |jstor=2345652|s2cid=115231821 }}

is a significance test whose aim is to detect the possible clustering of sub-populations within a clustered or non-uniformly-spread overall population. Possible applications of the test include examining the spatial clustering of childhood leukemia and lymphoma within the general population, given that the general population is spatially clustered.{{cn|date=May 2023}}

The test is based on:{{cn|date=May 2023}}

:*using control locations within the general population as the basis of a second or "control" sub-population in addition to the original "case" sub-population;

:*using "nearest-neighbour" analyses to form statistics based on either:

:**the number of other "cases" among the neighbours of each case;

:**the number "cases" which are nearer to each given case than the k-th nearest "control" for that case.

An example application of this test was to spatial clustering of leukaemias and lymphomas among young people in New Zealand.{{Cite journal|last1=Dockerty|first1=J. D.|last2=Sharples|first2=K. J.|author2-link= Katrina Sharples |last3=Borman|first3=B.|date=March 1999|title=An assessment of spatial clustering of leukaemias and lymphomas among young people in New Zealand|url= |journal=Journal of Epidemiology and Community Health |volume=53 |issue=3 |pages=154–158 |doi=10.1136/jech.53.3.154 |issn=0143-005X |pmc=1756850 |pmid=10396492}}