A prediction-based resampling method for estimating the number of clusters in a dataset.

@article{citeulike:259532, abstract = {BACKGROUND: Microarray technology is increasingly being applied in biological and medical research to address a wide range of problems, such as the classification of tumors. An important statistical problem associated with tumor classification is the identification of new tumor classes using gene-expression profiles. Two essential aspects of this clustering problem are: to estimate the number of clusters, if any, in a dataset; and to allocate tumor samples to these clusters, and assess the confidence of cluster assignments for individual samples. Here we address the first of these problems. RESULTS: We have developed a new prediction-based resampling method, Clest, to estimate the number of clusters in a dataset. The performance of the new and existing methods were compared using simulated data and gene-expression data from four recently published cancer microarray studies. Clest was generally found to be more accurate and robust than the six existing methods considered in the study. CONCLUSIONS: Focusing on prediction accuracy in conjunction with resampling produces accurate and robust estimates of the number of clusters.}, address = {Division of Biostatistics, School of Public Health, University of California Berkeley, 140 Earl Warren Hall, Berkeley, CA 94720-7360, USA. sandrine@stat.berkeley.edu}, author = {Dudoit, S. and Fridlyand, J. }, citeulike-article-id = {259532}, doi = {http://dx.doi.org/10.1186/gb-2002-3-7-research0036}, issn = {1465-6914}, journal = {Genome Biol}, keywords = {clustering-validity}, month = {June}, number = {7}, posted-at = {2008-05-06 20:53:42}, priority = {2}, title = {A prediction-based resampling method for estimating the number of clusters in a dataset.}, url = {http://dx.doi.org/10.1186/gb-2002-3-7-research0036}, volume = {3}, year = {2002} }

TY - JOUR ID - citeulike:259532 L3 - citeulike-article-id:259532 TI - A prediction-based resampling method for estimating the number of clusters in a dataset. JF - Genome Biol VL - 3 IS - 7 AD - Division of Biostatistics, School of Public Health, University of California Berkeley, 140 Earl Warren Hall, Berkeley, CA 94720-7360, USA. sandrine@stat.berkeley.edu SN - 1465-6914 N2 - BACKGROUND: Microarray technology is increasingly being applied in biological and medical research to address a wide range of problems, such as the classification of tumors. An important statistical problem associated with tumor classification is the identification of new tumor classes using gene-expression profiles. Two essential aspects of this clustering problem are: to estimate the number of clusters, if any, in a dataset; and to allocate tumor samples to these clusters, and assess the confidence of cluster assignments for individual samples. Here we address the first of these problems. RESULTS: We have developed a new prediction-based resampling method, Clest, to estimate the number of clusters in a dataset. The performance of the new and existing methods were compared using simulated data and gene-expression data from four recently published cancer microarray studies. Clest was generally found to be more accurate and robust than the six existing methods considered in the study. CONCLUSIONS: Focusing on prediction accuracy in conjunction with resampling produces accurate and robust estimates of the number of clusters. KW - clustering-validity AU - Dudoit, S AU - Fridlyand, J PY - 2002/06/25/ UR - http://dx.doi.org/10.1186/gb-2002-3-7-research0036 ER -