TY - JOUR
T1 - Shrinkage and model selection with correlated variables via weighted fusion
AU - Daye, Z. John
AU - Jeng, X. Jessie
N1 - Funding Information:
The authors are very grateful to Jayanta K. Ghosh, Jian Zhang, Ji Zhu, and Michael Yu Zhu for helpful comments and discussions. In addition, we thank Mary Ellen Bock, Jiashun Jin, and Jun Xie for brief but fruitful discussions. Appreciation also goes to two reviewers and the associate editor for very helpful suggestions. Xinge Jessie Jeng is supported by a grant from NSF (DMS-0639980) and Zhongyin John Daye by Ross Fellowship. Computing resources and support were provided by the Department of Statistics, Purdue University, and the Rosen Center for Advanced Computing of Information Technology at Purdue.
PY - 2009/2/15
Y1 - 2009/2/15
N2 - In this paper, we propose the weighted fusion, a new penalized regression and variable selection method for data with correlated variables. The weighted fusion can potentially incorporate information redundancy among correlated variables for estimation and variable selection. Weighted fusion is also useful when the number of predictors p is larger than the number of observations n. It allows the selection of more than n variables in a motivated way. Real data and simulation examples show that weighted fusion can improve variable selection and prediction accuracy.
AB - In this paper, we propose the weighted fusion, a new penalized regression and variable selection method for data with correlated variables. The weighted fusion can potentially incorporate information redundancy among correlated variables for estimation and variable selection. Weighted fusion is also useful when the number of predictors p is larger than the number of observations n. It allows the selection of more than n variables in a motivated way. Real data and simulation examples show that weighted fusion can improve variable selection and prediction accuracy.
UR - http://www.scopus.com/inward/record.url?scp=58549097639&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58549097639&partnerID=8YFLogxK
U2 - 10.1016/j.csda.2008.11.007
DO - 10.1016/j.csda.2008.11.007
M3 - Article
AN - SCOPUS:58549097639
SN - 0167-9473
VL - 53
SP - 1284
EP - 1298
JO - Computational Statistics and Data Analysis
JF - Computational Statistics and Data Analysis
IS - 4
ER -