Comparing Families of Dynamic Causal Models

By W. D. Penny, Klaas E. Stephan, Jean Daunizeau, Maria João Duarte Rosa, Karl J. Friston, T. Schofield, Alexander P. Leff. PLoS Comput. Biol., 2010

739 citations recorded by the source corpus.

Mathematical models of scientific data can be formally compared using Bayesian model evidence. Previous applications in the biological sciences have mainly focussed on model selection in which one first selects the model with the highest evidence and then makes inferences based on the parameters of that model. This “best model” approach is very useful but can become brittle if there are a large number of models to compare, and if different subjects use different models. To overcome this shortcoming we propose the combination of two further approaches: (i) family level inference and (ii) Bayesian model averaging within families. Family level inference removes uncertainty about aspects of model structure other than the characteristic of interest. For example: What are the inputs to the system? Is processing serial or parallel? Is it linear or nonlinear? Is it mediated by a single, crucial connection? We apply Bayesian model averaging within families to provide inferences about parameters that are independent of further assumptions about model structure. We illustrate the methods using Dynamic Causal Models of brain imaging data.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2f88070d894eb8d1a96c8f92c726f0422f3bcccd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Comparing Dynamic Causal Models using AIC, BIC and Free Energy (2012, methodology): “In this regime it may be a better idea to make inferences over families of models (Penny et al., 2010) and to look for consistent differences over a group of subjects (Stephan et al.”
Different Neural Mechanisms within Occipitotemporal Cortex Underlie Repetition Suppression across Same and Different-Size Faces (2012, methodology): “It is less susceptible to outliers than a FFX approach (Penny et al. 2010).”
EEG and MEG Data Analysis in SPM8 (2011, methodology): “SPM8 is integrated with the FieldTrip toolbox , making it possible for users to combine a variety of standard analysis methods with new schemes implemented in SPM and build custom analysis tools using powerful graphical user interface (GUI) and batching tools.”
Sensory reliability shapes perceptual inference via two mechanisms. (2015, background): “Likewise, family inference (Penny et al., 2010) demonstrated the highest posterior probability for the model averaging strategy for the auditory localization task and the threshold (CITh–0.”
Understanding DCM: Ten simple rules for the clinician (2013, positive): “This process of comparing the evidence for different models is known as Bayesian model selection (BMS) and has been extended to compare models in group studies, and compare different families of similar models (Penny et al., 2004, 2010; Stephan et al., 2009a,b).”
VBA: A Probabilistic Treatment of Nonlinear Models for Neurobiological and Behavioural Data (2014, methodology): “We also performed family-inference, which consists in partitioning model space into subsets of models [23].”
Bayesian model reduction and empirical Bayes for group (DCM) studies (2016, methodology): “This paper has introduced a general empirical Bayesian framework to model comparison at the group-level which differs from previous group-level Bayesian model selection approaches (Stephan et al., 2009; Penny et al., 2010; Rigoux et al., 2014) in a number of ways.”
The salience network is responsible for switching between the default mode network and the central executive network: Replication from DCM (2014, methodology): “Stochastic DCMs also include random fluctuations in the state equations that better accounts for spontaneous neuronal fluctuations.”
Audiovisual Synchrony Improves Motion Discrimination via Enhanced Connectivity between Early Visual and Auditory Areas (2010, methodology): “, the model with the highest posterior probability), we implemented a fixed-effects group analysis (Penny et al., 2010).”
Mapping the self in the brain's default mode network (2016, neutral): “The model space was partitioned according to whether broad self drove MPFC or PCC, and average connectivity estimates (weighted by their posterior model probabilities) were obtained from models in the winning family (Penny et al., 2010).”
Attention Reverses the Effect of Prediction in Silencing Sensory Signals (2011, neutral): “2009) and family level inference (Penny et al. 2010), contained modulatory influences of prediction on the selfconnection of V1, while the model in which prediction did not modulate this connection (model B) performed the worst (Supplementary Tables S2 and S3).”
Bayesian model selection for group studies - Revisited (2014, positive): “While the random effects BMS procedure suggested in Stephan et al. (2009) and Penny et al. (2010) has proven useful in practice— and has been employed by more than hundred published studies to date, some conceptual issues are still outstanding.”