Bayesian sigmoid shrinkage with improper variance priors and an application to wavelet denoising

Abstract

The normal Bayesian linear model is extended by assigning a flat prior to the δ power of the variance components of the regression coefficients (0<δ≤1⁄2) in order to improve prediction accuracy. In the case of orthonormal regressors, easy-to-compute analytic expressions are derived for the posterior distribution of the shrinkage and regression coefficients… (More)
DOI: 10.1016/j.csda.2006.06.011

Topics

6 Figures and Tables

Slides referencing similar topics