Bayesian model reduction and empirical Bayes for group (DCM) studies
Wellcome Centre for Human Neuroimaging · University College London · +5 more institutions
Abstract
This technical note describes some Bayesian procedures for the analysis of group studies that use nonlinear models at the first (within-subject) level - e.g., dynamic causal models - and linear models at subsequent (between-subject) levels. Its focus is on using Bayesian model reduction to finesse the inversion of multiple models of a single dataset or a single (hierarchical or empirical Bayes) model of multiple datasets. These applications of Bayesian model reduction allow one to consider parametric random effects and make inferences about group effects very efficiently (in a few seconds). We provide the relatively straightforward theoretical background to these procedures and illustrate their application…
Citation impact
- FWCI
- 28.95
- Percentile
- 100%
- References
- 31
Authors
8- KFKarl Friston
Wellcome Centre for Human Neuroimaging, University College London, National Hospital for Neurology and Neurosurgery
- VLVladimir Litvak
Wellcome Centre for Human Neuroimaging, National Hospital for Neurology and Neurosurgery, University College London
- AOAshwini Oswal
Wellcome Centre for Human Neuroimaging, University College London, National Hospital for Neurology and Neurosurgery
- ARAdeel Razi
National Hospital for Neurology and Neurosurgery, Wellcome Centre for Human Neuroimaging, NED University of Engineering and Technology, University College London
- KΕKlaas Ε. Stephan
Wellcome Centre for Human Neuroimaging, National Hospital for Neurology and Neurosurgery, University of Zurich, University College London, ETH Zurich, Institute for Biomedical Engineering
Topics & keywords
- Bayesian probability
- Computer science
- Variable-order Bayesian network
- Bayesian inference
- Bayes factor
- Bayes' theorem
- Machine learning
- Artificial intelligence