Return to search

Adaptive L1 regularized second-order least squares method for model selection

The second-order least squares (SLS) method in regression model proposed by Wang (2003, 2004) is based on the first two conditional moments of the response variable given the observed predictor variables. Wang and Leblanc (2008) show that the SLS estimator (SLSE) is asymptotically more efficient than the ordinary least squares estimator (OLSE) if the third moment of the random error is nonzero. We apply the SLS method to variable selection problems and propose the adaptively weighted L1 regularized SLSE (L1-SLSE). The L1-SLSE is robust against the shape of error distributions in variable selection problems. Finite sample simulation studies show that the L1-SLSE is more efficient than L1-OLSE in the case of asymmetric error distributions. A real data application with L1-SLSE is presented to demonstrate the usage of this method. / October 2015

Identiferoai:union.ndltd.org:MANITOBA/oai:mspace.lib.umanitoba.ca:1993/30757
Date11 September 2015
CreatorsXue, Lin
ContributorsWang, Liqun (Statistics) Jiang, Depeng (Community Health Sciences), Fu, James (Statistics) Torabi, Mahmoud (Community Health Sciences)
Source SetsUniversity of Manitoba Canada
Detected LanguageEnglish

Page generated in 0.0014 seconds