The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
Bayesian model selection for group studies
Open accessAbstract
Bayesian model selection (BMS) is a powerful method for determining the most likely among a set of competing hypotheses about the mechanisms that generated observed data. BMS has recently found widespread application in neuroimaging, particularly in the context of dynamic causal modelling (DCM). However, so far, combining BMS results from several subjects has relied on simple (fixed effects) metrics, e.g. the group Bayes factor (GBF), that do not account for group heterogeneity or outliers. In this paper, we compare the GBF with two random effects methods for BMS at the between-subject or group level. These methods provide inference on model-space using a classical and Bayesian perspective respectively. First, a classical (frequentist) approach uses the log model evidence as a subject-specific summary statistic. This enables one to use analysis of variance to test for differences in log-evidences over models, relative to inter-subject differences. We then consider the same problem in Bayesian terms and describe a novel hierarchical model, which is optimised to furnish a probability density on the models themselves. This new variational Bayes method rests on treating the model as a random variable and estimating the parameters of a Dirichlet distribution which describes the probabilities for all models considered. These probabilities then define a multinomial distribution over model space, allowing one to compute how likely it is that a specific model generated the data of a randomly chosen subject as well as the exceedance probability of one model being more likely than any other model. Using empirical and synthetic data, we show that optimising a conditional density of the model probabilities, given the log-evidences for each model over subjects, is more informative and appropriate than both the GBF and frequentist tests of the log-evidences. In particular, we found that the hierarchical Bayesian approach is considerably more robust than either of the other approaches in the presence of outliers. We expect that this new random effects method will prove useful for a wide range of group studies, not only in the context of DCM, but also for other modelling endeavours, e.g. comparing different source reconstruction methods for EEG/MEG or selecting among competing computational models of learning and decision-making.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Such hidden individual differences can be detected by formulating alternative computational models, each reflecting different cognitive strategies, and subjecting them to Bayesian model selection (62).”
From Can Bayesian Theories of Autism Spectrum Disorder Help Improve Clinical Practice? (2016) · cites this paper as [62]
In the citing paper
“As is made clear in [19] the GBF approach implicitly assumes that every subject uses the same model. It is therefore a Fixed Effects analysis.”
From Comparing families of dynamic causal models (2010) · cites this paper as [19]
In the citing paper
“The robustness and accuracy of this method was verified via simulations using data from synthetic populations with known frequencies of competing models [19].”
From Comparing families of dynamic causal models (2010) · cites this paper as [19]
In the citing paper
“Additionally, the use of Gibbs sampling allows us to relax the assumption made in VB that the posterior densities over and factorise [19].”
From Comparing families of dynamic causal models (2010) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
On Information and Sufficiency
Kullback, S., & Leibler, R. A. (1951) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177729694 · Cited by 20,193
Kass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Pattern Recognition and Machine Learning
(2007) · Kybernetes · doi:10.1108/03684920710743466 · Cited by 8,545
Information theory, inference, and learning algorithms
(2004) · Choice Reviews Online · doi:10.5860/choice.41-5949 · Cited by 6,536
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937
A Bayesian Analysis of Some Nonparametric Problems
Ferguson, T. S. (1973) · The Annals of Statistics · doi:10.1214/aos/1176342360 · Cited by 4,814
Friston, K. J., Harrison, L., & Penny, W. (2003) · NeuroImage · doi:10.1016/s1053-8119(03)00202-7 · Cited by 4,583
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Items 101–130 of 130
Action-specific value signals in reward-related regions of the human brain
FitzGerald, T. H. B., Friston, K. J., & Dolan, R. J. (2012) · The Journal of Neuroscience · doi:10.1523/jneurosci.3254-12.2012 · Cited by 68
Self-citationDiwadkar, V. A. (2012) · Archives of General Psychiatry · doi:10.1001/archgenpsychiatry.2011.1349 · Cited by 66
Crossmodal interactions in audiovisual emotion processing
Müller, V. I., Cieslik, E. C., Turetsky, B. I., & Eickhoff, S. B. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2011.12.007 · Cited by 65
Dima, D., Frangou, S., Burge, L., Braeutigam, S., & James, A. C. (2012) · Schizophrenia Research · doi:10.1016/j.schres.2011.12.024 · Cited by 65
The neural correlates of hierarchical predictions for perceptual decisions
Weilnhammer, V. A., Stuke, H., Sterzer, P., & Schmack, K. (2018) · The Journal of Neuroscience · doi:10.1523/jneurosci.2901-17.2018 · Cited by 57
Reorganisation of brain networks in frontotemporal dementia and progressive supranuclear palsy
Hughes, L. E., Ghosh, B. C. P., & Rowe, J. B. (2013) · NeuroImage: Clinical · doi:10.1016/j.nicl.2013.03.009 · Cited by 60
Corticostriatal pathways contribute to the natural time course of positive mood
Admon, R., & Pizzagalli, D. A. (2015) · Nature Communications · doi:10.1038/ncomms10065 · Cited by 57
Sevel, L. S., Letzen, J. E., Staud, R., & Robinson, M. E. (2016) · Brain Connectivity · doi:10.1089/brain.2015.0405 · Cited by 56
Green tea extract enhances parieto-frontal connectivity during working memory processing
Schmidt, A., Hammann, F., Wölnerhanssen, B., Meyer-Gerspach, A. C., Drewe, J., Beglinger, C., & Borgwardt, S. (2014) · Psychopharmacology · doi:10.1007/s00213-014-3526-1 · Cited by 57
Clarke, H. F., Cardinal, R. N., Rygula, R., Hong, Y. T., Fryer, T. D., Sawiak, S. J., Ferrari, V., Cockcroft, G., Aigbirhio, F. I., Robbins, T. W., et al. (2014) · The Journal of Neuroscience · doi:10.1523/jneurosci.0718-14.2014 · Cited by 54
Bönstrup, M., Schulz, R., Feldheim, J., Hummel, F. C., & Gerloff, C. (2016) · NeuroImage · doi:10.1016/j.neuroimage.2015.08.052 · Cited by 56
Galea, J. M., Bestmann, S., Beigi, M., Jahanshahi, M., & Rothwell, J. C. (2012) · The Journal of Neuroscience · doi:10.1523/jneurosci.3621-11.2012 · Cited by 52
De Baene, W., Kühn, S., & Brass, M. (2012) · Human Brain Mapping · doi:10.1002/hbm.21234 · Cited by 52
Altered inhibition-related frontolimbic connectivity in obsessive–compulsive disorder
van Velzen, L. S., de Wit, S. J., Ćurĉić‐Blake, B., Cath, D. C., de Vries, F. E., Veltman, D. J., van der Werf, Y. D., & van den Heuvel, O. A. (2015) · Human Brain Mapping · doi:10.1002/hbm.22898 · Cited by 50
Dauvermann, M. R., Whalley, H. C., Romaniuk, L., Valton, V., Owens, D. G. C., Johnstone, E. C., Lawrie, S. M., & Moorhead, T. W. J. (2013) · NeuroImage · doi:10.1016/j.neuroimage.2013.01.063 · Cited by 49
Sapey-Triomphe, L.-A., Weilnhammer, V. A., & Wagemans, J. (2022) · Autism · doi:10.1177/13623613211045026 · Cited by 45
Model-based dynamical analysis of functional disconnection in schizophrenia
Bányai, M., Diwadkar, V. A., & Érdi, P. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2011.06.046 · Cited by 40
Human inference reflects a normative balance of complexity and accuracy
Tavoni, G., Doi, T., Pizzica, C., Balasubramanian, V., & Gold, J. I. (2022) · Nature Human Behaviour · doi:10.1038/s41562-022-01357-z · Cited by 35
Neural correlates of hierarchical predictive processes in autistic adults
Sapey-Triomphe, L.-A., Pattyn, L., Weilnhammer, V., Sterzer, P., & Wagemans, J. (2023) · Nature Communications · doi:10.1038/s41467-023-38580-9 · Cited by 35
Model-based feature construction for multivariate decoding
Brodersen, K. H., Haiss, F., Ong, C. S., Jung, F., Tittgemeyer, M., Buhmann, J. M., Weber, B., & Stephan, K. E. (2011) · NeuroImage · doi:10.1016/j.neuroimage.2010.04.036 · Cited by 36
Self-citationPool, E. R., Munoz Tord, D., Delplanque, S., Stussi, Y., Cereghetti, D., Vuilleumier, P., & Sander, D. (2022) · The Journal of Neuroscience · doi:10.1523/jneurosci.1124-21.2022 · Cited by 33
Modeling subjective relevance in schizophrenia and its relation to aberrant salience
Katthagen, T., Mathys, C., Deserno, L., Walter, H., Kathmann, N., Heinz, A., & Schlagenhauf, F. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1006319 · Cited by 29
Model-based prediction of muscarinic receptor function from auditory mismatch negativity responses
Schöbi, D., Homberg, F., Frässle, S., Endepols, H., Moran, R. J., Friston, K. J., Tittgemeyer, M., Heinzle, J., & Stephan, K. E. (2021) · NeuroImage · doi:10.1016/j.neuroimage.2021.118096 · Cited by 25
Self-citationModulation of the brain's core-self network by self-appraisal processes
Delahoy, R., Davey, C. G., Jamieson, A. J., Finlayson-Short, L., Savage, H. S., Steward, T., & Harrison, B. J. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.118980 · Cited by 22
Mahmoodi, A., Luo, S., Harbison, C., Piray, P., & Rushworth, M. F. S. (2024) · Neuron · doi:10.1016/j.neuron.2024.09.001 · Cited by 17
Mikus, N., Lamm, C., & Mathys, C. (2025) · Biological Psychiatry · doi:10.1016/j.biopsych.2024.08.021 · Cited by 16
Bayesian Workflow for Generative Modeling in Computational Psychiatry
Hess, A. J., Iglesias, S., Köchli, L., Marino, S., Müller-Schrader, M., Rigoux, L., Mathys, C., Harrison, O. K., Heinzle, J., Frässle, S., et al. (2025) · Computational Psychiatry · doi:10.5334/cpsy.116 · Cited by 10
Self-citationState and capacity in neural models of cognition and consciousness
Wang, P., Liu, H., Ilievski, F., Ganushchak, L., Zou, L., Laureys, S., & Paas, F. (2026) · Trends Open · doi:10.1016/j.treopn.2026.04.004 · Cited by 8
Hake, H. S., Sibert, C., & Stocco, A. (2022) · Topics in Cognitive Science · doi:10.1111/tops.12623 · Cited by 8
Berndt, L. C. S., Singh, K. D., & Shaw, A. D. (2026) · Schizophrenia Bulletin · doi:10.1093/schbul/sbaf149 · Cited by 3
Metadata
- Authors
- Stephan, K. E., Penny, W. D., Daunizeau, J., Moran, R. J., & Friston, K. J.
- Affiliations
- Wellcome Centre for Human Neuroimaging (GB)
- Corresponding author
- Stephan, Klaas Enno
- Venue
- NeuroImage
- Publisher
- Elsevier BV
- Published
- 2009-07
- Volume
- 46
- Issue
- 4
- Pages
- 1004-1017
- ISSN
- 1053-8119 (ISSN-L)
- PMC
- PMC2703732
- OpenAlex
- W2135173838
- Cited by
- 1,423
- References
- 49
- Citations by year
- 2026: 63 · 2025: 74 · 2024: 76 · 2023: 71 · 2022: 86 · 2021: 100 · 2020: 135 · 2019: 97 · 2018: 102 · 2017: 91 · 2016: 89 · 2015: 109 · 2014: 67 · 2013: 75 · 2012: 59
- FWCI
- 51.46
- Type
- journal article
- Language
- en
- Open access
- green
- www.zora.uzh.ch
- Licence
- Locations
- NeuroImage (publishedVersion)
- PubMed (publishedVersion)
- Zurich Open Repository and Archive (University of Zurich) (acceptedVersion, other-oa)
- PubMed Central (acceptedVersion)
- UCL Discovery (University College London) (submittedVersion)
- Explore Bristol Research (submittedVersion)
- UEA Digital Repository (University of East Anglia) (submittedVersion)
- Zurich Open Repository and Archive (University of Zurich) (submittedVersion, other-oa)
- Zurich Open Repository and Archive (University of Zurich)
- Funders
- Wellcome Trust (056750, 088130)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Keywords
- Bayesian model selection, group study, dynamic causal modeling, random effects, Bayesian hierarchical model, variational inference, outliers, exceedance probability, Dirichlet distribution, model comparison
- MeSH terms
- Algorithms, Bayes Theorem, Brain, Cognition, Diagnostic Imaging, Humans, Models, Neurological
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
