Testing for clustering at many ranges inflates family-wise error rate FWEReport as inadecuate




Testing for clustering at many ranges inflates family-wise error rate FWE - Download this document for free, or read online. Document in PDF available to download.

International Journal of Health Geographics

, 14:4

First Online: 15 January 2015Received: 03 November 2014Accepted: 05 January 2015DOI: 10.1186-1476-072X-14-4

Cite this article as: Loop, M.S. & McClure, L.A. Int J Health Geogr 2015 14: 4. doi:10.1186-1476-072X-14-4

Abstract

BackgroundTesting for clustering at multiple ranges within a single dataset is a common practice in spatial epidemiology. It is not documented whether this approach has an impact on the type 1 error rate.

MethodsWe estimated the family-wise error rate FWE for the difference in Ripley’s K functions test, when testing at an increasing number of ranges at an alpha-level of 0.05. Case and control locations were generated from a Cox process on a square area the size of the continental US ≈3,000,000 mi. Two thousand Monte Carlo replicates were used to estimate the FWE with 95% confidence intervals when testing for clustering at one range, as well as 10, 50, and 100 equidistant ranges.

ResultsThe estimated FWE and 95% confidence intervals when testing 10, 50, and 100 ranges were 0.22 0.20 - 0.24, 0.34 0.31 - 0.36, and 0.36 0.34 - 0.38, respectively.

ConclusionsTesting for clustering at multiple ranges within a single dataset inflated the FWE above the nominal level of 0.05. Investigators should construct simultaneous critical envelopes available in spatstat package in R, or use a test statistic that integrates the test statistics from each range, as suggested by the creators of the difference in Ripley’s K functions test.

KeywordsRipley’s K function Overall clustering Point process Family wise error rate FWE Multiple testing  Download fulltext PDF



Author: Matthew Shane Loop - Leslie A McClure

Source: https://link.springer.com/







Related documents