Related references
Note: Only part of the references are listed.
Article
Statistics & Probability
Roy Levy et al.
Summary: This study provides a coherent approach to Bayesian analysis of multilevel models in the presence of missing data, covering the main aspects of the models and missingness.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Psychology, Multidisciplinary
Julia M. Haaf et al.
Summary: The primary goal of conducting a meta-analysis is to estimate the true effect size across a collection of studies. However, when the analyzed studies have qualitatively different results, the average effect may be a product of different mechanisms and therefore uninterpretable. To address this issue, it is important to determine whether all studies show an effect in the same expected direction. This can be achieved by using a model with multiple ordinal constraints and comparing it to alternative models. If the ordinal constraints hold, it suggests the existence of an underlying mechanism that explains the results from all studies, making the average effects interpretable.
PSYCHOLOGICAL METHODS
(2023)
Article
Psychology, Multidisciplinary
Esther Ulitzsch et al.
Summary: This study compares the performance of different solutions for small sample structural equation modeling (SEM) and evaluates the potential and boundaries of different parameterizations and constraints for improving estimation quality and stabilizing parameter estimates. Simulation results show that Bayesian methods outperform constrained maximum likelihood estimation and fixed reliability single indicator approaches in terms of accuracy of parameter estimates under conditions with low reliabilities, and perform comparably under high reliabilities. Both constrained maximum likelihood and Bayesian methods exhibit acceptable Type I error rates, while fixed reliability single indicator approaches are prone to severe inflation of Type I error rates. Stabilizing effects on Bayesian parameter estimates can be achieved even with mildly incorrect prior information. Additionally, an empirical example demonstrates the practical importance of carefully choosing the method of analysis for small sample SEM.
PSYCHOLOGICAL METHODS
(2023)
Review
Psychology, Multidisciplinary
Daniel W. Heck et al.
Summary: This article highlights the potential of the Bayes factor in psychological research and discusses six specific applications. It provides illustrative examples, key references, and software information. The article concludes with a discussion of the opportunities and pitfalls of Bayes factor applications and future research directions.
PSYCHOLOGICAL METHODS
(2023)
Article
Mathematics, Interdisciplinary Applications
Brian T. T. Keller et al.
Summary: A growing body of literature has focused on missing data methods that factorize the joint distribution into a part representing the analysis model of interest and a part representing the distributions of the incomplete predictors. This study explores the utility of these methods for multilevel models with interactive effects, using Monte Carlo computer simulations. The results suggest that these methods generally produce unbiased estimates and good coverage when the model's distributional assumptions are satisfied, but severe misspecifications from non-normal distributions can introduce biases.
MULTIVARIATE BEHAVIORAL RESEARCH
(2023)
Article
Mathematics, Interdisciplinary Applications
James Uanhoro
Summary: We propose a fully Bayesian approach for meta-analytic structural equation modeling based on hierarchical modeling of sample covariance matrices. This approach allows for flexible models, inclusion of moderators, investigation of global fit and local misspecification. Simulation studies demonstrate the validity of the Bayesian computation procedure for commonplace meta-analytic SEM applications. We provide diverse data analysis examples and accompanying R code to facilitate adoption and further study of the approach.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2023)
Article
Mathematics, Interdisciplinary Applications
David Kaplan et al.
Summary: The purpose of this paper is to demonstrate and evaluate the use of Bayesian dynamic borrowing in large-scale educational assessments. The results show that Bayesian dynamic borrowing performs well in cases with heterogeneous historical data compared to other methods, while it performs similarly to other methods in cases of homogeneous data.
Article
Education & Educational Research
Sally Paganin et al.
Summary: This article provides guidance on semiparametric IRT models and their implementation, emphasizing efficient sampling strategies and comparing inferential results between parametric and semiparametric models.
JOURNAL OF EDUCATIONAL AND BEHAVIORAL STATISTICS
(2023)
Article
Psychology, Educational
James Ohisei Uanhoro
Summary: Accounting for model misspecification is a key challenge in Bayesian structural equation modeling. We propose a Bayesian approach that incorporates the degree of misspecification as a parameter, allowing for comparing different models fit to the same data. By estimating the misspecification parameter simultaneously with structural parameters, the resulting model provides more reliable inference compared to existing methods. The approach also estimates the residual covariance matrix, enabling diagnosis of misspecifications and updating of hypothesized models.
EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT
(2023)
Article
Statistics & Probability
Oludare Ariyo et al.
Summary: In the study of using vague priors for the covariance parameters of random effects, the marginal criteria outperform the conditional criteria, and joint and separation priors outperform the inverse-Wishart prior in all scenarios.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2022)
Article
Statistics & Probability
Albert Xingyi Man et al.
Summary: Exploratory factor analysis is widely used in various fields such as psychology, finance, genomics, neuroscience, and economics. This study introduces a new Bayesian sampling algorithm that efficiently explores the multimodal posterior surface and addresses issues with traditional approaches.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Psychology, Multidisciplinary
Brooke E. Magnus et al.
Summary: Zero responses and their equivalents are common on measures of psychopathology, especially in community samples, resulting in high levels of zero inflation. Researchers propose a multidimensional zero-inflated graded response model (MZI-GRM) to better capture zero inflation on questionnaires by including correlated latent variables representing susceptibility and severity, showing better fit than existing models on capturing zero inflation across items.
PSYCHOLOGICAL METHODS
(2022)
Article
Mathematics, Interdisciplinary Applications
Esther Ulitzsch et al.
Summary: Careless and insufficient effort responding (C/IER) poses a threat to data quality and validity of inferences drawn from questionnaire data. A model-based approach is presented to detect various manifestations of C/IER by utilizing response time information and theoretical considerations. The approach considers individual differences in response behavior, allows for variations in attentiveness, and deals with different response patterns arising from C/IER.
Article
Mathematics, Interdisciplinary Applications
Haiyan Liu et al.
Summary: The study compared the impact of different priors on model complexity and DIC, revealing that SS priors led to larger pD and smaller DIC compared to IW priors. Additionally, the DIC was found to better detect model misspecification under SS priors compared to IW priors.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2022)
Article
Mathematics, Interdisciplinary Applications
Camiel van Zundert et al.
Summary: Bayesian mediation analysis requires specifying a prior for the covariance matrix of the variables involved. This paper introduces separation strategy priors and a Prior Predictive Check, providing guidelines for optimal prior specification based on researcher's prior knowledge encoding preferences.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2022)
Article
Computer Science, Interdisciplinary Applications
Jose Roberto Silva dos Santos et al.
Summary: Large-scale longitudinal studies in education often face challenges in imposing experimental conditions, requiring a flexible statistical model to account for unobserved heterogeneity and the nature of observational assessment data. Proposed longitudinal item response theory models utilize skewed multivariate normal distributions to monitor performance growth, addressing unexplained heterogeneity through structured covariance patterns and skew-normal latent variable distributions. A hybrid MCMC approach is developed for parameter estimation and model comparison, with simulation results showing good parameter recovery.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2022)
Article
Psychology, Multidisciplinary
Kenneth A. Bollen et al.
Summary: Psychologists often use latent variable models to represent concepts that are difficult to directly measure, and scaling indicators are commonly used in model building. However, the choice of scaling indicators is often overlooked, leading to potential inaccuracies in the results. This article proposes a set of criteria and diagnostic tools to assist researchers in making informed decisions about scaling indicators.
PSYCHOLOGICAL METHODS
(2022)
Article
Psychology, Multidisciplinary
Philippe Rast et al.
Summary: Research on individual variation has gained more attention recently. This study presents a new model parameterization based on GARCH models to explore the potential usefulness of these models in research on within-person variability. The pdBEKK and DCC models provide better explanations for within-person variance and offer more accurate psychological interpretations. However, these models require a large amount of data to detect significant parameters.
PSYCHOLOGICAL METHODS
(2022)
Article
Psychology, Mathematical
Benjamin Graves et al.
Summary: In this study, it is demonstrated that Bayesian model comparison metrics can systematically change depending on the constraints used, leading to the introduction of principled methods for setting the scale of latent variables to stabilize model comparison metrics. These methods involve placing priors on ratios of factor loadings and using effect coding.
BEHAVIOR RESEARCH METHODS
(2022)
Article
Mathematics, Interdisciplinary Applications
Milica Miocevic et al.
Summary: In the field of mediation analysis, Bayesian methods with informative priors can have different effects on statistical properties compared to frequentist methods, depending on sample size and the level of accuracy in the priors. It was found that the impact of inaccurate priors for loadings could be mitigated by reducing the informativeness of the prior, while this was not always the case for structural paths. The consequences of using informative priors varied depending on the inferential goals of the analysis, with inaccurate priors being more detrimental for accurately estimating the mediated effect.
MULTIVARIATE BEHAVIORAL RESEARCH
(2021)
Article
Mathematics, Interdisciplinary Applications
Steffen Zitzmann et al.
Summary: In small samples, the key criterion for Bayesian approaches is not bias but variability, and they can provide more accurate estimates than Maximum Likelihood methods.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2021)
Article
Mathematics, Interdisciplinary Applications
Sarah Depaoli et al.
Summary: The study found that Bayesian model averaging (BMA) is a reliable alternative to traditional model comparison and selection methods. The simulation study demonstrated that BMA can effectively compare and select models through both Bayesian and frequentist frameworks.
MULTIVARIATE BEHAVIORAL RESEARCH
(2021)
Article
Mathematics, Interdisciplinary Applications
Sara van Erp et al.
Summary: Bayesian estimation of multilevel structural equation models has advantages in terms of sample size requirements and computational feasibility, but careful specification of the prior distribution, especially for random effects variance parameters, is necessary. The paper investigates alternative, more robust prior distributions for the doubly latent categorical multilevel model, highlighting the importance of constructing reasonable priors for multiple random effects variance parameters in MLSEMs. Although the robust priors outperform the traditional inverse-Gamma prior, consideration of hyperparameters is still crucial.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2021)
Article
Computer Science, Interdisciplinary Applications
Edgar C. Merkle et al.
Summary: This paper describes a general, efficient approach to Bayesian SEM estimation in Stan, contrasting it with previous implementations in R package blavaan. Practical comparisons under multiple scenarios show that the new approach is clearly better, and discussions on possible extensions to other models of interest to psychometricians are provided.
JOURNAL OF STATISTICAL SOFTWARE
(2021)
Article
Computer Science, Interdisciplinary Applications
Paul-Christian Buerkner
Summary: Item response theory (IRT) is often implemented in the human sciences using R packages like brms and the probabilistic programming language Stan. These tools allow for the specification and fitting of Bayesian IRT models with various response distributions and parameter configurations, making it easy to extract posterior distributions and evaluate model fit.
JOURNAL OF STATISTICAL SOFTWARE
(2021)
Article
Mathematics, Interdisciplinary Applications
Riddhi Pratim Ghosh et al.
Summary: Estimation of correlation matrices is challenging due to positive-definiteness constraint and high-dimensionality. Reparameterizing Cholesky factors of correlation matrices in terms of angles has become popular, but has not been used in Bayesian estimation perhaps due to lack of clear statistical relevance. In this paper, angles are shown to be the inverse cosine of semi-partial correlations for longitudinal data, allowing for meaningful selection and shrinkage priors. Our method effectively deals with the positive-definiteness constraint and outperforms other methods based on partial autocorrelations in simulation.
Article
Psychology, Multidisciplinary
Oliver Luedtke et al.
Summary: The article discusses different Bayesian estimators for stabilizing parameter estimates in confirmatory factor analysis models, with simulation studies showing that the EAP method produces more accurate estimates of latent correlations and outperforms other Bayesian estimators in terms of root mean squared error. It is recommended to use the four-parameter beta distribution as a prior distribution to improve the stability of parameter estimates.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Psychology, Multidisciplinary
Michael J. Zyphur et al.
Summary: This article discusses the potential uses of Bayesian estimation in time-series and panel data models by incorporating prior probabilities in addition to observed data. By using informative shrinkage or small variance priors, the article highlights the benefits of increased model parsimony, stability of estimates, and improved out-of-sample predictions and interpretability. The use of priors also allows for estimating otherwise under-identified models and higher-order lagged effects in a more trustworthy manner than under maximum likelihood estimation.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Psychology
Wolf Vanpaemel
PSYCHOLOGICAL REVIEW
(2020)
Article
Mathematics, Interdisciplinary Applications
Artur Pokropek et al.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2020)
Article
Mathematics, Interdisciplinary Applications
Julia M. Haaf et al.
JOURNAL OF MATHEMATICAL PSYCHOLOGY
(2020)
Article
Psychology, Multidisciplinary
Mauricio Garnier-Villarreal et al.
PSYCHOLOGICAL METHODS
(2020)
Article
Computer Science, Interdisciplinary Applications
Quentin F. Gronau et al.
JOURNAL OF STATISTICAL SOFTWARE
(2020)
Article
Mathematics, Interdisciplinary Applications
Edgar C. Merkle et al.
Article
Mathematics, Interdisciplinary Applications
Daniel W. Heck
BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY
(2019)
Article
Psychology
Paul-Christian Buerkner et al.
ADVANCES IN METHODS AND PRACTICES IN PSYCHOLOGICAL SCIENCE
(2019)
Article
Mathematics, Interdisciplinary Applications
Tihomir Asparouhov et al.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2018)
Article
Computer Science, Interdisciplinary Applications
Edgar C. Merkle et al.
JOURNAL OF STATISTICAL SOFTWARE
(2018)
Article
Psychology, Multidisciplinary
Craig K. Enders et al.
PSYCHOLOGICAL METHODS
(2018)
Article
Psychology, Multidisciplinary
Herbert Hoijtink et al.
PSYCHOLOGICAL METHODS
(2018)
Article
Physics, Multidisciplinary
Andrew Gelman et al.
Article
Computer Science, Interdisciplinary Applications
Charles C. Driver et al.
JOURNAL OF STATISTICAL SOFTWARE
(2017)
Article
Mathematics, Interdisciplinary Applications
Sierra A. Bainter
MULTIVARIATE BEHAVIORAL RESEARCH
(2017)
Article
Mathematics, Interdisciplinary Applications
Elena A. Erosheva et al.
Article
Mathematical & Computational Biology
Sandra M. Hurtado Rua et al.
STATISTICS IN MEDICINE
(2015)
Article
Statistics & Probability
S. McKay Curtis
Journal of Statistical Software
(2015)
Article
Mathematical & Computational Biology
Yinghui Wei et al.
STATISTICS IN MEDICINE
(2013)
Article
Mathematics, Interdisciplinary Applications
Alan Huang et al.
Article
Psychology, Multidisciplinary
Rens van de Schoot et al.
FRONTIERS IN PSYCHOLOGY
(2013)
Article
Statistics & Probability
John W. Seaman et al.
AMERICAN STATISTICIAN
(2012)
Article
Mathematics, Interdisciplinary Applications
Carel F. W. Peeters
Article
Psychology
Eric-Jan Wagenmakers et al.
COGNITIVE PSYCHOLOGY
(2010)
Article
Statistics & Probability
Joyee Ghosh et al.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2009)
Article
Statistics & Probability
Daniel Lewandowski et al.
JOURNAL OF MULTIVARIATE ANALYSIS
(2009)
Article
Statistics & Probability
Mohsen Pourahmadi et al.
JOURNAL OF MULTIVARIATE ANALYSIS
(2007)
Article
Statistics & Probability
Harry Joe
JOURNAL OF MULTIVARIATE ANALYSIS
(2006)
Article
Mathematics, Interdisciplinary Applications
TD Little et al.
STRUCTURAL EQUATION MODELING-A MULTIDISCIPLINARY JOURNAL
(2006)
