Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR.

@article{citeulike:2087522, abstract = {Variable selection can be challenging, particularly in situations with a large number of predictors with possibly high correlations, such as gene expression data. In this article, a new method called the OSCAR (octagonal shrinkage and clustering algorithm for regression) is proposed to simultaneously select variables while grouping them into predictive clusters. In addition to improving prediction accuracy and interpretation, these resulting groups can then be investigated further to discover what contributes to the group having a similar behavior. The technique is based on penalized least squares with a geometrically intuitive penalty function that shrinks some coefficients to exactly zero. Additionally, this penalty yields exact equality of some coefficients, encouraging correlated predictors that have a similar effect on the response to form predictive clusters represented by a single coefficient. The proposed procedure is shown to compare favorably to the existing shrinkage and variable selection techniques in terms of both prediction error and model complexity, while yielding the additional grouping information.}, address = {Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, U.S.A.}, author = {Bondell, Howard D D. and Reich, Brian J J. }, citeulike-article-id = {2087522}, doi = {10.1111/j.1541-0420.2007.00843.x}, issn = {0006-341X}, journal = {Biometrics}, keywords = {model-selection, regression}, month = {June}, posted-at = {2007-12-11 02:36:18}, priority = {4}, title = {Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR.}, url = {http://dx.doi.org/10.1111/j.1541-0420.2007.00843.x}, year = {2007} }

TY - JOUR ID - citeulike:2087522 L3 - citeulike-article-id:2087522 TI - Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR. JF - Biometrics AD - Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, U.S.A. SN - 0006-341X N2 - Variable selection can be challenging, particularly in situations with a large number of predictors with possibly high correlations, such as gene expression data. In this article, a new method called the OSCAR (octagonal shrinkage and clustering algorithm for regression) is proposed to simultaneously select variables while grouping them into predictive clusters. In addition to improving prediction accuracy and interpretation, these resulting groups can then be investigated further to discover what contributes to the group having a similar behavior. The technique is based on penalized least squares with a geometrically intuitive penalty function that shrinks some coefficients to exactly zero. Additionally, this penalty yields exact equality of some coefficients, encouraging correlated predictors that have a similar effect on the response to form predictive clusters represented by a single coefficient. The proposed procedure is shown to compare favorably to the existing shrinkage and variable selection techniques in terms of both prediction error and model complexity, while yielding the additional grouping information. KW - model-selection KW - regression AU - Bondell, Howard D AU - Reich, Brian J PY - 2007/06/30/ UR - http://dx.doi.org/10.1111/j.1541-0420.2007.00843.x ER -