A tutorial on Bayes factor estimation with the product space method

Lodewyckx, Tom; Kim, Woojae; Lee, Michael; Tuerlinckx, Francis; Kuppens, Peter; Wagenmakers, Eric‐Jan

doi:10.1016/j.jmp.2011.06.001

Cited by 98 publications

(104 citation statements)

References 53 publications

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…In case the data provides strong evidence in favor of one of the models, it is very unlikely that the MCMC sampler visits the other model and a posterior probability ratio cannot be computed correctly from the samples. Hence, we adapted a product space method (Lodewyckx et al, 2011) that iteratively adjusts prior model probabilities until the posterior probabilities are roughly equal. Then, the BF can be computed from the known prior model probabilities and the sampled posterior model probabilities.…”

Section: Computational Modelingmentioning

confidence: 99%

Nicotine deprivation, temporal discounting and choice consistency in heavy smokers

Roewer

Wiehler

Peters

2015

J Exper Analysis Behavior

View full text Add to dashboard Cite

The subjective value of rewards declines the longer rewards are delayed into the future ("delay discounting"). Discounting behavior varies both as a function of an individual's trait and current state. The degree of discounting has repeatedly been associated with relapse following treatment of addiction. Therefore, the effects of acute drug deprivation on discounting processes are potentially of high clinical relevance. In two testing sessions (24 hr of nicotine deprivation vs. normal smoking) 37 heavy smoking participants made choices between immediate and delayed rewards as well as between shorter and longer delayed rewards. We found no evidence for an effect of nicotine deprivation on delay discounting of potentially real monetary rewards in both types of decision tasks. Although choice stochasticity was numerically increased after deprivation, this effect was not significant (p>.1). Participants responded significantly slower after nicotine deprivation. Our study supports previous findings that choice impulsivity as measured using discounting tasks is not affected by nicotine deprivation, at least not if real monetary rewards of lower amounts are at stake.

show abstract

Section: Computational Modelingmentioning

confidence: 99%

Nicotine deprivation, temporal discounting and choice consistency in heavy smokers

Roewer

Wiehler

Peters

2015

J Exper Analysis Behavior

View full text Add to dashboard Cite

show abstract

“…Vandekerckhove et al (39) shows how to use posterior distributions obtained from WinBUGS and JAGS to compute Bayes factors for non-nested MPTs using importance sampling. Lodewyckx et al (14) outline a WinBUGS implementation of the product-space method, a transdimensional MCMC approach for computing Bayes factors for nested and non-nested models. Most recently, Gronau et al (7) provide a tutorial on bridge sampling-a new, potentially very powerful method that is under active development.…”

Section: Resultsmentioning

confidence: 99%

Bayesian inference for psychology, part III: Parameter estimation in nonstandard models

2017

View full text Add to dashboard Cite

We demonstrate the use of three popular Bayesian software packages that enable researchers to estimate parameters in a broad class of models that are commonly used in psychological research. We focus on WinBUGS, JAGS, and Stan, and show how they can be interfaced from R and MATLAB. We illustrate the use of the packages through two fully worked examples; the examples involve a simple univariate linear regression and fitting a multinomial processing tree model to data from a classic false-memory experiment. We conclude with a comparison of the strengths and weaknesses of the packages. Our example code, data, and this text are available via https://osf.io/ucmaz/.WinBUGS | JAGS | Stan | Bayesian estimation | Bayesian inference

show abstract

“…If the participant is classified as having linear-increase learning, the model inferences are a bounded line based on the learning rate parameter. In each panel, the Bayes factor, derived from the posterior expectation of the z i indicator parameters, is also shown (Lodewyckx et al, 2011). Thus, for example, the Bayes factor for participant 14 is 30 in favor of step-change learning, in which their accuracy improves from about 65% to about 90% at the sixth block, while the the Bayes factor for participant 15 is 26 in favor of linear-increase learning, in which their accuracy improves from 50% to about 90% over the blocks.…”

Section: Graphical Modelmentioning

confidence: 99%

A simple and flexible Bayesian method for inferring step changes in cognition

Lee

2018

Behav Res

Self Cite

View full text Add to dashboard Cite

Human behavioral data often shows patterns of sudden change over time. Sometimes the causes of these step changes are internal, such as learning curves changing abruptly when a learner implements a new rule. Sometimes the cause is external, such a people's opinions about a topic changing in response to a new relevant event. Detecting change points in sequences of binary data is a basic statistical problem, with many existing solutions, but they seem rarely to be used in psychological modeling. We develop a simple and flexible Bayesian approach to modeling step changes in cognition, implemented as a graphical model in JAGS. The model is able to infer how many change points are justified by the data, as well as the location of the change points. The basic model is also easily extended to include latent-mixture and hierarchical structures, allowing it to be tailored to specific cognitive modeling problems. We demonstrate the adequacy of the basic model by applying it to the classic Lindisfarne Scribes problem, and the flexibility of the modeling approach through two new applications. The first involves a latent-mixture model to determine if individuals learn categories incrementally or in discrete stages. The second involves a hierarchical model of crowd-sourced predictions about the winner of the U.S. National Football League's Most Valuable Player for the 2016-2017 season.

show abstract

A tutorial on Bayes factor estimation with the product space method

Cited by 98 publications

References 53 publications

Nicotine deprivation, temporal discounting and choice consistency in heavy smokers

Nicotine deprivation, temporal discounting and choice consistency in heavy smokers

Bayesian inference for psychology, part III: Parameter estimation in nonstandard models

A simple and flexible Bayesian method for inferring step changes in cognition

Contact Info

Product

Resources

About