UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Robust Bayesian general linear models

Penny, WD; Kilner, J; Blankenburg, F; (2007) Robust Bayesian general linear models. NEUROIMAGE , 36 (3) 661 - 671. 10.1016/j.neuroimage.2007.01.058.

Full text not available from this repository.

Abstract

We describe a Bayesian learning algorithm for Robust General Linear Models (RGLMs). The noise is modeled as a Mixture of Gaussians rather than the usual single Gaussian. This allows different data points to be associated with different noise levels and effectively provides a robust estimation of regression coefficients. A variational inference framework is used to prevent overtitting and provides a model order selection criterion for noise model order. This allows the RGLM to default to the usual GLM when robustness is not required. The method is compared to other robust regression methods and applied to synthetic data and fMRI. (c) 2007 Elsevier Inc. All rights reserved.

Type:Article
Title:Robust Bayesian general linear models
DOI:10.1016/j.neuroimage.2007.01.058
Keywords:Bayesian, fMRI, artefact, mixture model, robust estimation, FMRI TIME-SERIES
UCL classification:UCL > School of Life and Medical Sciences > Faculty of Brain Sciences > Psychology and Language Sciences (Division of) > Institute of Cognitive Neuroscience
UCL > School of Life and Medical Sciences > Faculty of Brain Sciences > Institute of Neurology > Imaging Neuroscience
UCL > School of Life and Medical Sciences > Faculty of Brain Sciences > Institute of Neurology > Motor Neuroscience and Movement Disorders
UCL > School of Life and Medical Sciences > Faculty of Life Sciences

Archive Staff Only: edit this record