Permutation tests for equality of distributions in highdimensional settings
(2002) In Biometrika 89(2). p.359374 Abstract
 Motivated by applications in highdimensional settings, we suggest a test of the hypothesis H0 that two sampled distributions are identical. It is assumed that two independent datasets are drawn from the respective populations, which may be very general. In particular, the distributions may be multivariate or infinitedimensional, in the latter case representing, for example, the distributions of random functions from one Euclidean space to another. Our test uses a measure of distance between data. This measure should be symmetric but need not satisfy the triangle inequality, so it is not essential that it be a metric. The test is based on ranking the pooled dataset, with respect to the distance and relative to any fixed data value, and... (More)
 Motivated by applications in highdimensional settings, we suggest a test of the hypothesis H0 that two sampled distributions are identical. It is assumed that two independent datasets are drawn from the respective populations, which may be very general. In particular, the distributions may be multivariate or infinitedimensional, in the latter case representing, for example, the distributions of random functions from one Euclidean space to another. Our test uses a measure of distance between data. This measure should be symmetric but need not satisfy the triangle inequality, so it is not essential that it be a metric. The test is based on ranking the pooled dataset, with respect to the distance and relative to any fixed data value, and repeating this operation for each fixed datum. A permutation argument enables a critical point to be chosen such that the test has concisely known significance level, conditional on the set of all pairwise distances. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/334616
 author
 Hall, P and Tajvidi, Nader ^{LU}
 organization
 publishing date
 2002
 type
 Contribution to journal
 publication status
 published
 subject
 keywords
 rank test, resampling, multivariate analysis, local alternative, hypothesis test, hypergeometric distribution, bootstrap, functional data analysis
 in
 Biometrika
 volume
 89
 issue
 2
 pages
 359  374
 publisher
 Oxford University Press
 external identifiers

 wos:000176520500008
 scopus:22944460361
 ISSN
 00063444
 DOI
 10.1093/biomet/89.2.359
 language
 English
 LU publication?
 yes
 id
 2ce5c9acb70a47cd96952814e5c08d6d (old id 334616)
 date added to LUP
 20160401 15:43:09
 date last changed
 20201222 02:51:28
@article{2ce5c9acb70a47cd96952814e5c08d6d, abstract = {Motivated by applications in highdimensional settings, we suggest a test of the hypothesis H0 that two sampled distributions are identical. It is assumed that two independent datasets are drawn from the respective populations, which may be very general. In particular, the distributions may be multivariate or infinitedimensional, in the latter case representing, for example, the distributions of random functions from one Euclidean space to another. Our test uses a measure of distance between data. This measure should be symmetric but need not satisfy the triangle inequality, so it is not essential that it be a metric. The test is based on ranking the pooled dataset, with respect to the distance and relative to any fixed data value, and repeating this operation for each fixed datum. A permutation argument enables a critical point to be chosen such that the test has concisely known significance level, conditional on the set of all pairwise distances.}, author = {Hall, P and Tajvidi, Nader}, issn = {00063444}, language = {eng}, number = {2}, pages = {359374}, publisher = {Oxford University Press}, series = {Biometrika}, title = {Permutation tests for equality of distributions in highdimensional settings}, url = {http://dx.doi.org/10.1093/biomet/89.2.359}, doi = {10.1093/biomet/89.2.359}, volume = {89}, year = {2002}, }