Estimating the number of clusters in a data set via the gap statistic Export

@article{citeulike:3483426, abstract = {We propose a method (the 'gap statistic') 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.}, address = {Stanford University, USA}, author = {Tibshirani, Robert and Walther, Guenther and Hastie, Trevor}, citeulike-article-id = {3483426}, citeulike-linkout-0 = {http://dx.doi.org/10.1111/1467-9868.00293}, citeulike-linkout-1 = {http://www.ingentaconnect.com/content/bpl/rssb/2001/00000063/00000002/art00012}, citeulike-linkout-2 = {http://www3.interscience.wiley.com/cgi-bin/abstract/118994756/ABSTRACT}, doi = {10.1111/1467-9868.00293}, issn = {1467-9868}, journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)}, keywords = {cluster, clustering, gap, number, of, statistic}, number = {2}, pages = {411--423}, posted-at = {2008-11-05 22:38:54}, priority = {2}, publisher = {Blackwell Publishing}, title = {Estimating the number of clusters in a data set via the gap statistic}, url = {http://dx.doi.org/10.1111/1467-9868.00293}, volume = {63}, year = {2001} }

TY - JOUR ID - citeulike:3483426 L3 - citeulike-article-id:3483426 N2 - We propose a method (the 'gap statistic') 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. IS - 2 JF - Journal of the Royal Statistical Society: Series B (Statistical Methodology) SN - 1467-9868 AD - Stanford University, USA EP - 423 TI - Estimating the number of clusters in a data set via the gap statistic PB - Blackwell Publishing VL - 63 SP - 411 KW - cluster KW - clustering KW - gap KW - number KW - of KW - statistic AU - Tibshirani, Robert AU - Walther, Guenther AU - Hastie, Trevor PY - 2001/// UR - http://dx.doi.org/10.1111/1467-9868.00293 ER -