Comparing Dynamic Causal Models using AIC, BIC and Free Energy

被引：195

作者：

Penny, W. D. ^{[1
]}

机构：

[1] UCL, Wellcome Trust Ctr Neuroimaging, London WC1N 3BG, England

来源：

NEUROIMAGE | 2012年 / 59卷 / 01期

基金：

英国惠康基金;

关键词：

Bayesian; Model comparison; Brain connectivity; Dynamic Causal Modelling; fMRI; INFERENCE; SELECTION; BAYES;

D O I：

10.1016/j.neuroimage.2011.07.039

中图分类号：

Q189 [神经科学];

学科分类号：

071006 ;

摘要：

In neuroimaging it is now becoming standard practise to fit multiple models to data and compare them using a model selection criterion. This is especially prevalent in the analysis of brain connectivity. This paper describes a simulation study which compares the relative merits of three model selection criteria (i) Akaike's Information Criterion (AIC), (ii) the Bayesian Information Criterion (BIC) and (iii) the variational Free Energy. Differences in performance are examined in the context of General Linear Models (GLMs) and Dynamic Causal Models (DCMs). We find that the Free Energy has the best model selection ability and recommend it be used for comparison of DCMs. (C) 2011 Elsevier Inc. All rights reserved.

引用

页码：319 / 330

页数：12

共 50 条

[1] Comparing the Markov Order Estimators AIC, BIC and EDC
Dorea, Chang C. Y.
Resende, Paulo A. A.
Goncalves, Catia R.
[J]. TRANSACTIONS ON ENGINEERING TECHNOLOGIES, 2015, : 41 - 54
[2] Comparing dynamic causal models
Penny, WD
Stephan, KE
Mechelli, A
Friston, KJ
[J]. NEUROIMAGE, 2004, 22 (03) : 1157 - 1172
[3] Comparing Families of Dynamic Causal Models
Penny, Will D.
Stephan, Klaas E.
Daunizeau, Jean
Rosa, Maria J.
Friston, Karl J.
Schofield, Thomas M.
Leff, Alex P.
[J]. PLOS COMPUTATIONAL BIOLOGY, 2010, 6 (03)
[4] Evaluating the performance of AIC and BIC for selecting spatial econometric models
Christos Agiakloglou
Apostolos Tsimpanos
[J]. Journal of Spatial Econometrics, 2023, 4 (1):
[5] FAST STEPWISE PROCEDURES OF SELECTION OF VARIABLES BY USING AIC AND BIC CRITERIA BIC CRITERIA
安鸿志
顾岚
[J]. Acta Mathematicae Applicatae Sinica, 1989, (01) : 60 - 67
[6] Selecting high-dimensional mixed graphical models using minimal AIC or BIC forests
David Edwards
Gabriel CG de Abreu
Rodrigo Labouriau
[J]. BMC Bioinformatics, 11 (1)
[7] Selecting high-dimensional mixed graphical models using minimal AIC or BIC forests
Edwards, David
de Abreu, Gabriel C. G.
Labouriau, Rodrigo
[J]. BMC BIOINFORMATICS, 2010, 11
[8] AIC, BIC, Bayesian evidence against the interacting dark energy model
Szydlowski, Marek
Krawiec, Adam
Kurek, Aleksandra
Kamionka, Michal
[J]. EUROPEAN PHYSICAL JOURNAL C, 2015, 75 (01):
[9] AIC, BIC, Bayesian evidence against the interacting dark energy model
Marek Szydłowski
Adam Krawiec
Aleksandra Kurek
Michał Kamionka
[J]. The European Physical Journal C, 2015, 75
[10] GENE SELECTION USING LOGISTIC REGRESSIONS BASED ON AIC, BIC AND MDL CRITERIA
Zhou, Xiaobo
Wang, Xiaodong
Dougherty, Edward R.
[J]. NEW MATHEMATICS AND NATURAL COMPUTATION, 2005, 1 (01) : 129 - 145

← 1 2 3 4 5 →