Partial Factor Modeling: Predictor-Dependent Shrinkage for Linear Regression

P. Richard Hahn

doi:10.1080/01621459.2013.779843

Partial Factor Modeling: Predictor-Dependent Shrinkage for Linear Regression

2013-09-01

17

PRE

AI

DOI：10.1080/01621459.2013.779843

Original

Original request for help

Save

Abstract

En 中文

We develop a modified Gaussian factor model for the purpose of inducing predictor-dependent shrinkage for linear regression. The new model predicts well across a wide range of covariance structures, on real and simulated data. Furthermore, the new model facilitates variable selection in the case of correlated predictor variables, which often stymies other methods.

Keywords:

g Prior

Prediction

Shrinkage estimators

Variable selection

Partial Factor Modeling: Predictor-Dependent Shrinkage for Linear Regression

Abstract

Journal

Organization