A5025801659- Statistical Methods and Bayesian Inference
- Advanced Statistical Methods and Models
- Mental Health Research Topics
- Complex Network Analysis Techniques
- Statistical Methods and Inference
- Bayesian Modeling and Causal Inference
- Statistical Methods in Clinical Trials
- Opinion Dynamics and Social Influence
- Optimal Experimental Design Methods
- Advanced Statistical Modeling Techniques
- Psychometric Methodologies and Testing
- Forecasting Techniques and Applications
- Bayesian Methods and Mixture Models
- Advanced Causal Inference Techniques
- Data Analysis with R
- Gaussian Processes and Bayesian Inference
- Spatial and Panel Data Analysis
- Statistical Distribution Estimation and Applications
- Sensory Analysis and Statistical Methods
- Economic and Environmental Valuation
- Job Satisfaction and Organizational Behavior
- Genetic and phenotypic traits in livestock
- Social Capital and Networks
- Advanced Text Analysis Techniques
- Computational Drug Discovery Methods
Tilburg University
2016-2025
Arq Psychotrauma Expert Group
2019-2024
Ghent University Hospital
2020
East China Normal University
2020
Expertise Center Vocational Education
2019-2020
University of Puerto Rico at Río Piedras
2019-2020
Utrecht University
2008-2020
University of California, Davis
2019-2020
McGill University
2020
University of Liverpool
2018
Learning about hypothesis evaluation using the Bayes factor could enhance psychological research. In contrast to null-hypothesis significance testing it renders evidence in favor of each hypotheses under consideration (it can be used quantify support for null-hypothesis) instead a dichotomous reject/do-not-reject decision; straightforwardly multiple without having bother proper manner account testing; and allows continuous reevaluation after additional data have been collected (Bayesian...
Bayesian structural equation modeling (BSEM) has recently gained popularity because it enables researchers to fit complex models and solve some of the issues often encountered in classical maximum likelihood estimation, such as nonconvergence inadmissible solutions. An important component any analysis is prior distribution unknown model parameters. Often, rely on default priors, which are constructed an automatic fashion without requiring substantive information. However, can have a serious...
Informative hypotheses are increasingly being used in psychological sciences because they adequately capture researchers’ theories and expectations. In the Bayesian framework, evaluation of informative often makes use default Bayes factors such as fractional factor. This paper approximates adjusts factor that it can be to evaluate general statistical models. a fraction parameter must specified which controls amount information data for specifying an implicit prior. The remaining is testing...
The effects of gender stereotype threat on mathematical test performance in the classroom have been extensively studied several cultural contexts. Theory predicts that lowers girls' mathematics tests, while leaving boys' math unaffected. We conducted a large-scale experiment Dutch high schools (N = 2064) to study generalizability effect. In this registered report, we set out replicate overall effect among female school students and four core theoretical moderators, namely domain...
Several criteria from the optimal design literature are examined for use with item selection in multidimensional adaptive testing. In particular, it is what appropriate testing which all abilities intentional, some should be considered as a nuisance, or interest of composite abilities. Both theoretical analyses and studies simulated data this paper suggest that A-optimality D-optimality lead to most accurate estimates when former slightly outperforming latter. The criterion E-optimality...
This paper discusses a Fortran 90 program referred to as BIEMS (Bayesian inequality and equality constrained model selection) that can be used for calculating Bayes factors of multivariate normal linear models with and/or constraints between the parameters versus containing no constraints, which is unconstrained model. The prior under conjugate expected-constrained posterior proportional truncated in space. results appropriately balance fit complexity broad class models. When set represents...
The R package BGGM provides tools for making Bayesian inference in Gaussian graphical models (GGM).The methods are organized around two general approaches inference: (1
Gaussian graphical models are commonly used to characterize conditional independence structures (i.e., networks) of psychological constructs.Recently attention has shifted from estimating single networks those various sub-populations.The focus is primarily detect di erences or demonstrate replicability.We introduce two novel Bayesian methods for comparing that explicitly address these aims.The rst based on the posterior predictive distribution, with Kullback-Leibler divergence as discrepancy...
There have been considerable methodological developments of Bayes factors for hypothesis testing in the social and behavioral sciences, related fields. This development is due to flexibility factor multiple hypotheses simultaneously, ability test complex involving equality as well order constraints on parameters interest, interpretability outcome weight evidence provided by data support competing scientific theories. The available software tools Bayesian are still limited however. In this...
Bayesian network models offer a large degree of flexibility for modeling dependence among observables (item outcome variables) from the same task, which may be dependent. This article explores four design patterns locally dependent observations: (a) no context—ignores observables; (b) compensatory context—introduces latent variable, context, to model task-specific knowledge and use combine this with relevant proficiencies; (c) inhibitor an (threshold) (d) cascading—models each observable as...
Bayesian evaluation of inequality constrained hypotheses enables researchers to investigate their expectations with respect the structure among model parameters. This article proposes an approximate Bayes procedure that can be used for selection best a set based on factor in very general class statistical models. The software package BIG is provided such psychologists use approach proposed analysis own data. To illustrate and BIG, we evaluate path logistic regression model. Two simulation...
The matrix-F distribution is presented as prior for covariance matrices an alternative to the conjugate inverted Wishart distribution. A special case of univariate F a variance parameter equivalent half-t standard deviation, which becoming increasingly popular in Bayesian literature. can be conveniently modeled mixture or inverse distributions, allows straightforward implementation Gibbs sampler. By mixing matrix multivariate normal with distribution, horseshoe type obtained useful modeling...
Mixed-effects models are becoming common in psychological science. Although they have many desirable features, there is still untapped potential. It customary to view homogeneous variance as an assumption satisfy. We argue move beyond that perspective, and modeling within-person opportunity gain a richer understanding of processes. The technique do so based on the mixed-effects location scale model can simultaneously estimate submodels both mean (location) (scale). develop framework goes...
This Teacher’s Corner paper introduces Bayesian evaluation of informative hypotheses for structural equation models, using the free open-source R packages bain, hypothesis testing, and lavaan, a widely used SEM package. The introduction provides brief non-technical explanation hypotheses, statistical underpinnings evaluation, bain algorithm. Three tutorial examples demonstrate in context common types models: 1) confirmatory factor analysis, 2) latent variable regression, 3) multiple group...
Researchers often have expectations about the research outcomes in regard to inequality constraints between, e.g., group means.Consider example of researchers who investigated effects inducing a negative emotional state aggressive boys.It was expected that highly boys would, on average, score higher responses toward other peers than moderately boys, would turn nonaggressive boys.In most cases, null hypothesis testing is used evaluate such hypotheses.We show, however, hypotheses formulated...
The intraclass correlation plays a central role in modeling hierarchically structured data, such as educational panel or group-randomized trial data. It represents relevant information concerning the between-group and within-group variation. Methods for Bayesian hypothesis tests are proposed to improve decision making hierarchical data analysis assess grouping effect across different group categories. Estimation testing methods coefficient under marginal framework where random effects...
Several issues are discussed when testing inequality constrained hypotheses using a Bayesian approach. First, the complexity (or size) of parameter spaces can be ignored. This is case posterior probability that constraints hypothesis hold, Bayes factors based on non‐informative improper priors, and partial priors. Second, factor may not invariant for linear one‐to‐one transformations data. observed balanced priors which centred boundary space with diagonal covariance structure. Third,...