{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T14:42:33Z","timestamp":1792075353282,"version":"4.4.0"},"reference-count":0,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2001,7,1]],"date-time":"2001-07-01T00:00:00Z","timestamp":993945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2001,7,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>We propose a method (the \u2018gap statistic\u2019) for estimating the number of clusters (groups) in a set of data. The technique uses the output of any clustering algorithm (e.g. K-means or hierarchical), comparing the change in within-cluster dispersion with that expected under an appropriate reference null distribution. Some theory is developed for the proposal and a simulation study shows that the gap statistic usually outperforms other methods that have been proposed in the literature.<\/jats:p>","DOI":"10.1111\/1467-9868.00293","type":"journal-article","created":{"date-parts":[[2003,3,12]],"date-time":"2003-03-12T14:36:38Z","timestamp":1047479798000},"page":"411-423","source":"Crossref","is-referenced-by-count":5030,"title":["Estimating the Number of Clusters in a Data Set Via the Gap Statistic"],"prefix":"10.1093","volume":"63","author":[{"given":"Robert","family":"Tibshirani","sequence":"first","affiliation":[{"name":"Stanford University , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guenther","family":"Walther","sequence":"additional","affiliation":[{"name":"Stanford University , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Hastie","sequence":"additional","affiliation":[{"name":"Stanford University , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2002,1,6]]},"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2F1467-9868.00293","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2F1467-9868.00293","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/63\/2\/411\/49590410\/jrsssb_63_2_411.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/63\/2\/411\/49590410\/jrsssb_63_2_411.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T05:43:43Z","timestamp":1679463823000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/63\/2\/411\/7083348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,7,1]]},"references-count":0,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2002,1,6]]},"published-print":{"date-parts":[[2001,7,1]]}},"URL":"https:\/\/doi.org\/10.1111\/1467-9868.00293","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2001,7]]},"published":{"date-parts":[[2001,7,1]]}}}