شماره ركورد كنفرانس :
3860
عنوان مقاله :
Group LASSO for high-dimensional partially linear errors-in variables models
پديدآورندگان :
Kazemi M m.kazemie64@yahoo.com Shahrood University of Technology , Shahsavani D Shahrood University of Technology , Arashi M Shahrood University of Technology
كليدواژه :
Adaptive group LASSO , Measurement errors , Partially linear model
عنوان كنفرانس :
دومين كنفرانس ملي محاسبات نرم
چكيده فارسي :
This article focuses on group variable selection for high dimensional partially linear models when the covariates are measured with additive errors. We apply the group least absolute and shrinkage operator (LASSO) penalty to simultaneously estimate and select significant variables. Finite sample performance of the proposed procedure is assessed by simulation studies, where we compare the naive and bias-corrected group LASSO estimators.
