Modeling by shortest data description

Rissanen, Jorma

doi:10.1016/0005-1098(78)90005-5

Cited by 5,054 publications

(2,864 citation statements)

References 4 publications

Supporting

Mentioning

2,822

Contrasting

Unclassified

Order By: Relevance

“…Application of Schwartz criterion also yielded a model order of one. In addition to AIC and SC, Rissanen's Minimum Description Length (MDL) [Rissanen, 1978], which is based on the entirely different concept of information theory, also gave an order of one. Therefore, the choice of order selection method is not critical for the present study.…”

Section: Discussionmentioning

confidence: 99%

Multivariate Granger causality analysis of fMRI data

Deshpande

LaConte

James

et al. 2008

Human Brain Mapping

217

214

View full text Add to dashboard Cite

This article describes the combination of multivariate Ganger causality analysis, temporal down-sampling of fMRI time series, and graph theoretic concepts for investigating causal brain networks and their dynamics. As a demonstration, this approach was applied to analyze epoch-to-epoch changes in a hand-gripping, muscle fatigue experiment. Causal influences between the activated regions were analyzed by applying the directed transfer function (DTF) analysis of multivariate Granger causality with the integrated epoch response as the input, allowing us to account for the effects of several relevant regions simultaneously. Integrated responses were used in lieu of originally sampled time points to remove the effect of the spatially varying hemodynamic response as a confounding factor; using integrated responses did not affect our ability to capture its slowly varying affects of fatigue. We separately modeled the early, middle, and late periods in the fatigue. We adopted graph theoretic concepts of clustering and eccentricity to facilitate the interpretation of the resultant complex networks. Our results reveal the temporal evolution of the network and demonstrate that motor fatigue leads to a disconnection in the related neural network.

show abstract

Section: Discussionmentioning

confidence: 99%

Multivariate Granger causality analysis of fMRI data

Deshpande

LaConte

James

et al. 2008

Human Brain Mapping

217

214

View full text Add to dashboard Cite

show abstract

“…The results from these test pairs indicate that some subjects (35%) consistently made RAT decisions, others (13%) consistently made TTB decisions, and still others (52%) were inconsistent in their choice of strategy. In addition to analyzing subjects' performance on these test pairs, Lee and Cummins (2004) fit versions of the RAT and TTB models to subjects' choice data with a model fit criterion known as minimum description length (MDL; Rissanen, 1978). The average fits for RAT (MDL ϭ 130.7) and TTB (MDL ϭ 138.6) were similar, so neither model was conclusively favored.…”

Section: Experiments On the Use Of Ttb And Ratmentioning

confidence: 99%

A response-time approach to comparing generalized rational and take-the-best models of decision making.

Bergert

Nosofsky

2007

Journal of Experimental Psychology: Learning, Memory, and Cogni

118

View full text Add to dashboard Cite

The authors develop and test generalized versions of take-the-best (TTB) and rational (RAT) models of multiattribute paired-comparison inference. The generalized models make allowances for subjective attribute weighting, probabilistic orders of attribute inspection, and noisy decision making. A key new test involves a response-time (RT) approach. TTB predicts that RT is determined solely by the expected time required to locate the 1st discriminating attribute, whereas RAT predicts that RT is determined by the difference in summed evidence between the 2 alternatives. Critical test pairs are used that partially decouple these 2 factors. Under conditions in which ideal observer TTB and RAT strategies yield equivalent decisions, both the RT results and the estimated attribute weights suggest that the vast majority of subjects adopted the generalized TTB strategy. The RT approach is also validated in an experimental condition in which use of a RAT strategy is essentially forced upon subjects.Keywords: decision making, response times, paired-comparison inference Recent research in decision making has introduced heuristics that dramatically simplify processing while maintaining a high level of accuracy. Gigerenzer and Todd (1999) and Gigerenzer and Selten (2001) refer to these heuristics as "the adaptive toolbox." They theorize that much decision making results from an application of one or more of these simple heuristics, instead of from an application of the classically "rational" strategies that make exhaustive use of all available information. Such heuristics as recognition and take-the-best (TTB) are thought to be adaptations to natural information environments, and they constitute an alternative vision of rationality, called ecological rationality or bounded rationality (Gigerenzer & Goldstein, 1996;Gigerenzer & Selten, 2001;Goldstein & Gigerenzer, 2002;Simon, 1956).A great deal of research has been devoted to comparing the predictions from the TTB model and classically rational models of decision making. In this article, however, we suggest that the compared models make quite strong assumptions. For example, within the framework of the compared models, it is often assumed that subjects attach certain ideal observer weights to the multiple attributes that compose the alternatives and also that the underlying choice mechanisms are fully deterministic in nature. The main purpose of the present research was to consider generalized versions of the models that relax these assumptions, leading to what we view as more psychologically plausible models. Furthermore, we introduce a new response-time method for distinguishing between the predictions from the generalized models. The TTB ModelIn making a decision about which of two alternatives is higher on some variable of interest, TTB considers the features of the alternatives in order of diagnosticity and makes a decision according to the first feature found that distinguishes between the alternatives. For example, suppose first that the presence of a professional basketb...

show abstract

“…Selection between such competing models can be made on the basis of a parsimony principle (see, e.g. Burnham and Anderson 2002); formalised in approaches such as Akaike's Information Criterion (Akaike 1974), and Rissanen's Minimum Description Length (Rissanen 1978). Other methods which are also proving very useful in this area include Markov-chain Monte Carlo (MCMC) methods, using, for example, single channel data to determine model structure and parameterisation (e.g.…”

Section: Initiative 2: Reconciling Model Complexity With Data Availabmentioning

confidence: 99%

Cardiac cell modelling: Observations from the heart of the cardiac physiome project

Fink

Niederer

Cherry

et al. 2011

Progress in Biophysics and Molecular Biology

149

136

View full text Add to dashboard Cite

In this manuscript we review the state of cardiac cell modelling in the context of international initiatives such as the IUPS Physiome and Virtual Physiological Human Projects, which aim to integrate computational models across scales and physics. In particular we focus on the relationship between experimental data and model parameterisation across a range of model types and cellular physiological systems. Finally, in the context of parameter identification and model reuse within the Cardiac Physiome, we suggest some future priority areas for this field.

show abstract

Modeling by shortest data description

Cited by 5,054 publications

References 4 publications

Multivariate Granger causality analysis of fMRI data

Multivariate Granger causality analysis of fMRI data

A response-time approach to comparing generalized rational and take-the-best models of decision making.

Cardiac cell modelling: Observations from the heart of the cardiac physiome project

Contact Info

Product

Resources

About