Unsupervised Forward Selection: A Method for Eliminating Redundant Variables

@article{citeulike:2133755, abstract = {Abstract: An unsupervised learning method is proposed for variable selection and its performance assessed using three typical QSAR data sets. The aims of this procedure are to generate a subset of descriptors from any given data set in which the resultant variables are relevant, redundancy is eliminated, and multicollinearity is reduced. Continuum regression, an algorithm encompassing ordinary least squares regression, regression on principal components, and partial least squares regression, was used to construct models from the selected variables. The variable selection routine is shown to produce simple, robust, and easily interpreted models for the chosen data sets.}, address = {Centre for Molecular Design, Institute of Biomedical and Biomolecular Science, University of Portsmouth, King Henry Building, King Henry I Street, Portsmouth, PO1 2DY, U.K., and ChemQuest, Delamere House, 1, Royal Crescent, Sandown, Isle of Wight, PO36 8LZ, U.K.}, author = {Whitley, D. C. and Ford, M. G. and Livingstone, D. J. }, citeulike-article-id = {2133755}, doi = {http://dx.doi.org/10.1021/ci000384c}, journal = {J. Chem. Inf. Comput. Sci.}, keywords = {clustering, dimensionality, reduction, selection, unsupervised, variable}, month = {September}, number = {5}, pages = {1160--1168}, posted-at = {2008-06-04 16:26:50}, priority = {2}, title = {Unsupervised Forward Selection: A Method for Eliminating Redundant Variables}, url = {http://dx.doi.org/10.1021/ci000384c}, volume = {40}, year = {2000} }

TY - JOUR ID - citeulike:2133755 L3 - citeulike-article-id:2133755 N2 - Abstract: An unsupervised learning method is proposed for variable selection and its performance assessed using three typical QSAR data sets. The aims of this procedure are to generate a subset of descriptors from any given data set in which the resultant variables are relevant, redundancy is eliminated, and multicollinearity is reduced. Continuum regression, an algorithm encompassing ordinary least squares regression, regression on principal components, and partial least squares regression, was used to construct models from the selected variables. The variable selection routine is shown to produce simple, robust, and easily interpreted models for the chosen data sets. IS - 5 JF - J. Chem. Inf. Comput. Sci. AD - Centre for Molecular Design, Institute of Biomedical and Biomolecular Science, University of Portsmouth, King Henry Building, King Henry I Street, Portsmouth, PO1 2DY, U.K., and ChemQuest, Delamere House, 1, Royal Crescent, Sandown, Isle of Wight, PO36 8LZ, U.K. EP - 1168 TI - Unsupervised Forward Selection: A Method for Eliminating Redundant Variables VL - 40 SP - 1160 KW - clustering KW - dimensionality KW - reduction KW - selection KW - unsupervised KW - variable AU - Whitley, DC AU - Ford, MG AU - Livingstone, DJ PY - 2000/09/25/ UR - http://dx.doi.org/10.1021/ci000384c ER -