Bayesian Factor Analysis as a Variable-Selection Problem: Alternative Priors and Consequences

Factor analysis is a popular statistical technique for multivariate data analysis. Developments in the structural equation modeling framework have enabled the use of hybrid confirmatory/exploratory approaches in which factor-loading structures can be explored relatively flexibly within a confirmatory factor analysis (CFA) framework. Recently, Muthén & Asparouhov proposed a Bayesian structural equation modeling (BSEM) approach to explore the presence of cross loadings in CFA models. We show that the issue of determining factor-loading patterns may be formulated as a Bayesian variable selection problem in which Muthén and Asparouhov's approach can be regarded as a BSEM approach with ridge regression prior (BSEM-RP). We propose another Bayesian approach, denoted herein as the Bayesian structural equation modeling with spike-and-slab prior (BSEM-SSP), which serves as a one-stage alternative to the BSEM-RP. We review the theoretical advantages and disadvantages of both approaches and compare their empirical performance relative to two modification indices-based approaches and exploratory factor analysis with target rotation. A teacher stress scale data set is used to demonstrate our approach.     

Bayesian Hierarchical Classes Analysis

Hierarchical classes models are models for N-way N-mode data that represent the association among the N modes and simultaneously yield, for each mode, a hierarchical classification of its elements. In this paper we present a stochastic extension of the hierarchical classes model for two-way two-mode binary data. In line with the original model, the new probabilistic extension still represents both the association among the two modes and the hierarchical classifications. A fully Bayesian method for fitting the new model is presented and evaluated in a simulation study. Furthermore, we propose tools for model selection and model checking based on Bayes factors and posterior predictive checks. We illustrate the advantages of the new approach with applications in the domain of the psychology of choice and psychiatric diagnosis. Iwin Leenen is now at the Instituto Mexicano de Investigación de Familia y Población (IMIFAP), Mexico. The research reported in this paper was partially supported by the Spanish Ministerio de Educación y Ciencia (programa Ramón y Cajal) and by the Research Council of K.U.Leuven (PDM/99/037, GOA/2000/02, and GOA/2005/04). The authors are grateful to Johannes Berkhof for fruitful discussions.     

攻击性初中生的类别转变：潜在转变分析

研究采用潜在转变分析探讨了攻击性初中生的类别转变。276名初中参加了为期一年的短期纵向追踪研究,在一年中分两次报告了自己的攻击行为。用潜在转变模型分析了初二到初三时青少年的攻击类别转变,结果表明初中生有三种攻击模式。研究以潜在转变模型进一步探究了这三种攻击模式的变化,结果发现两种模式具有很强的稳定性,不同模式之间也有一定程度的转变。最后,研究探讨了攻击类别转变的影响因素,结果表明性别与友谊质量可以起到显著作用。针对实际意义,文章最后进行了讨论和总结。     

Power Analysis for the Likelihood-Ratio Test in Latent Markov Models: Shortcutting the Bootstrap p-Value-Based Method

The latent Markov (LM) model is a popular method for identifying distinct unobserved states and transitions between these states over time in longitudinally observed responses. The bootstrap likelihood-ratio (BLR) test yields the most rigorous test for determining the number of latent states, yet little is known about power analysis for this test. Power could be computed as the proportion of the bootstrap p values (PBP) for which the null hypothesis is rejected. This requires performing the full bootstrap procedure for a large number of samples generated from the model under the alternative hypothesis, which is computationally infeasible in most situations. This article presents a computationally feasible shortcut method for power computation for the BLR test. The shortcut method involves the following simple steps: (1) obtaining the parameters of the model under the null hypothesis, (2) constructing the empirical distributions of the likelihood ratio under the null and alternative hypotheses via Monte Carlo simulations, and (3) using these empirical distributions to compute the power. We evaluate the performance of the shortcut method by comparing it to the PBP method and, moreover, show how the shortcut method can be used for sample-size determination.     

Bayesian inference for finite mixtures of generalized linear models with random effects

We present an hierarchical Bayes approach to modeling parameter heterogeneity in generalized linear models. The model assumes that there are relevant subpopulations and that within each subpopulation the individual-level regression coefficients have a multivariate normal distribution. However, class membership is not known a priori, so the heterogeneity in the regression coefficients becomes a finite mixture of normal distributions. This approach combines the flexibility of semiparametric, latent class models that assume common parameters for each sub-population and the parsimony of random effects models that assume normal distributions for the regression parameters. The number of subpopulations is selected to maximize the posterior probability of the model being true. Simulations are presented which document the performance of the methodology for synthetic data with known heterogeneity and number of sub-populations. An application is presented concerning preferences for various aspects of personal computers.     

Bayesian adaptive estimation: The next dimension

We propose a new psychometric model for two-dimensional stimuli, such as color differences, based on parameterizing the threshold of a one-dimensional psychometric function as an ellipse. The Ψ Bayesian adaptive estimation method applied to this model yields trials that vary in multiple stimulus dimensions simultaneously. Simulations indicate that this new procedure can be much more efficient than the more conventional procedure of estimating the psychometric function on one-dimensional lines independently, requiring only one-fourth or less the number of trials for equivalent performance in typical situations. In a real psychophysical experiment with a yes-no task, as few as 22 trials per estimated threshold ellipse were enough to consistently demonstrate certain color appearance phenomena. We discuss the practical implications of the multidimensional adaptation. In order to make the application of the model practical, we present two significantly faster algorithms for running the Ψ method: a discretized algorithm utilizing the Fast Fourier Transform for better scaling with the sampling rates and a Monte Carlo particle filter algorithm that should be able to scale into even more dimensions.     

Bayesian estimation of a multilevel IRT model using gibbs sampling

In this article, a two-level regression model is imposed on the ability parameters in an item response theory (IRT) model. The advantage of using latent rather than observed scores as dependent variables of a multilevel model is that it offers the possibility of separating the influence of item difficulty and ability level and modeling response variation and measurement error. Another advantage is that, contrary to observed scores, latent scores are test-independent, which offers the possibility of using results from different tests in one analysis where the parameters of the IRT model and the multilevel model can be concurrently estimated. The two-parameter normal ogive model is used for the IRT measurement model. It will be shown that the parameters of the two-parameter normal ogive model and the multilevel model can be estimated in a Bayesian framework using Gibbs sampling. Examples using simulated and real data are given.     

Flexible Bayesian modelling in dichotomous item response theory using mixtures of skewed item curves

Most item response theory (IRT) models for dichotomous responses are based on probit or logit link functions which assume a symmetric relationship between the probability of a correct response and the latent traits of individuals taking a test. This assumption restricts the use of those models to the case in which all items behave symmetrically. On the other hand, asymmetric models proposed in the literature impose that all the items in a test behave asymmetrically. This assumption is inappropriate for great majority of tests which are, in general, composed of both symmetric and asymmetric items. Furthermore, a straightforward extension of the existing models in the literature would require a prior selection of the items' symmetry/asymmetry status. This paper proposes a Bayesian IRT model that accounts for symmetric and asymmetric items in a flexible but parsimonious way. That is achieved by assigning a finite mixture prior to the skewness parameter, with one of the mixture components being a point mass at zero. This allows for analyses under both model selection and model averaging approaches. Asymmetric item curves are designed through the centred skew normal distribution, which has a particularly appealing parametrization in terms of parameter interpretation and computational efficiency. An efficient Markov chain Monte Carlo algorithm is proposed to perform Bayesian inference and its performance is investigated in some simulated examples. Finally, the proposed methodology is applied to a data set from a large-scale educational exam in Brazil.     

K-means、潜在类别模型和混合Rasch模型的比较

基于模拟研究比较了K-means方法、潜在类别模型和混合Rasch模型在二分外显变量情境下的聚类效果.结果表明：（1）潜在类别数量、变量数量、样本量、样本平衡和变量间相关对K-means方法、潜在类别模型和混合Rasch模型的分类准确性均有影响且因素间的交互作用存在;（2）除了在2个潜在类别的样本不平衡条件下K-means方法表现较差外,在其他条件下与潜在类别模型和混合Rasch模型的表现相当;（3）混合Rasch模型的分类一致性在2个潜在类别的情境下要好于潜在类别模型,但是在4个潜在类别的情境下要差于潜在类别模型.     

Using MCMC chain outputs to efficiently estimate Bayes factors

One of the most important methodological problems in psychological research is assessing the reasonableness of null models, which typically constrain a parameter to a specific value such as zero. Bayes factor has been recently advocated in the statistical and psychological literature as a principled means of measuring the evidence in data for various models, including those where parameters are set to specific values. Yet, it is rarely adopted in substantive research, perhaps because of the difficulties in computation. Fortunately, for this problem, the Savage–Dickey density ratio (Dickey & Lientz, 1970) provides a conceptually simple approach to computing Bayes factor. Here, we review methods for computing the Savage–Dickey density ratio, and highlight an improved method, originally suggested by Gelfand and Smith (1990) and advocated by Chib (1995), that outperforms those currently discussed in the psychological literature. The improved method is based on conditional quantities, which may be integrated by Markov chain Monte Carlo sampling to estimate Bayes factors. These conditional quantities efficiently utilize all the information in the MCMC chains, leading to accurate estimation of Bayes factors. We demonstrate the method by computing Bayes factors in one-sample and one-way designs, and show how it may be implemented in WinBUGS.     

Stochastic search item selection for factor analytic models

In this paper we implement a Markov chain Monte Carlo algorithm based on the stochastic search variable selection method of George and McCulloch (1993) for identifying promising subsets of manifest variables (items) for factor analysis models. The suggested algorithm is constructed by embedding in the usual factor analysis model a normal mixture prior for the model loadings with latent indicators used to identify not only which manifest variables should be included in the model but also how each manifest variable is associated with each factor. We further extend the suggested algorithm to allow for factor selection. We also develop a detailed procedure for the specification of the prior parameters values based on the practical significance of factor loadings using ideas from the original work of George and McCulloch (1993). A straightforward Gibbs sampler is used to simulate from the joint posterior distribution of all unknown parameters and the subset of variables with the highest posterior probability is selected. The proposed method is illustrated using real and simulated data sets.     

Approximately counting and sampling knowledge states

Approximately counting and sampling knowledge states from a knowledge space is a problem that is of interest for both applied and theoretical reasons. However, many knowledge spaces used in practice are far too large for standard statistical counting and estimation techniques to be useful. Thus, in this work we use an alternative technique for counting and sampling knowledge states from a knowledge space. This technique is based on a procedure variously known as subset simulation, the Holmes–Diaconis–Ross method, or multilevel splitting. We make extensive use of Markov chain Monte Carlo methods and, in particular, Gibbs sampling, and we analyse and test the accuracy of our results in numerical experiments.     

Bayesian PTSD-Trajectory Analysis with Informed Priors Based on a Systematic Literature Search and Expert Elicitation

There is a recent increase in interest of Bayesian analysis. However, little effort has been made thus far to directly incorporate background knowledge via the prior distribution into the analyses. This process might be especially useful in the context of latent growth mixture modeling when one or more of the latent groups are expected to be relatively small due to what we refer to as limited data. We argue that the use of Bayesian statistics has great advantages in limited data situations, but only if background knowledge can be incorporated into the analysis via prior distributions. We highlight these advantages through a data set including patients with burn injuries and analyze trajectories of posttraumatic stress symptoms using the Bayesian framework following the steps of the WAMBS-checklist. In the included example, we illustrate how to obtain background information using previous literature based on a systematic literature search and by using expert knowledge. Finally, we show how to translate this knowledge into prior distributions and we illustrate the importance of conducting a prior sensitivity analysis. Although our example is from the trauma field, the techniques we illustrate can be applied to any field.     

Examining Patterns of Political, Social Service, and Collaborative Involvement of Religious Congregations: A Latent Class and Transition Analysis

This investigation examines typologies of congregations based on patterns of congregational political and social service activities and collaborative partners. Based on a latent class analysis of a national random sample of 2,153 congregations, results indicated four distinct types of congregations with unique patterns of political, social service, and collaborative partnerships labeled: (a) Active, (b) Not Active, (c) Social Service Not Political, and (d) Political Not Social Service. Moreover, congregational characteristics such as religious tradition and clergy characteristics predicted membership in certain types. A latent transition analysis using an additional 262 congregations revealed distinct patterns of how congregations changed types across a nine year period. Results showed both congregational continuity (e.g., Not Active congregations remained Not Active) and change (e.g., Active congregations were likely to change type membership). This study advances congregational research by examining congregational types, what predicts certain types, and how congregations change types across time. Implications for future research and partnership with religious congregations also are discussed.     

Extending exploratory diagnostic classification models: Inferring the effect of covariates

Diagnostic models provide a statistical framework for designing formative assessments by classifying student knowledge profiles according to a collection of fine-grained attributes. The context and ecosystem in which students learn may play an important role in skill mastery, and it is therefore important to develop methods for incorporating student covariates into diagnostic models. Including covariates may provide researchers and practitioners with the ability to evaluate novel interventions or understand the role of background knowledge in attribute mastery. Existing research is designed to include covariates in confirmatory diagnostic models, which are also known as restricted latent class models. We propose new methods for including covariates in exploratory RLCMs that jointly infer the latent structure and evaluate the role of covariates on performance and skill mastery. We present a novel Bayesian formulation and report a Markov chain Monte Carlo algorithm using a Metropolis-within-Gibbs algorithm for approximating the model parameter posterior distribution. We report Monte Carlo simulation evidence regarding the accuracy of our new methods and present results from an application that examines the role of student background knowledge on the mastery of a probability data set.     

Application of the Within- and Between-Series Estimators to Non-normal Multiple-Baseline Data: Maximum Likelihood and Bayesian Approaches

In single-case research, multiple-baseline (MB) design provides the opportunity to estimate the treatment effect based on not only within-series comparisons of treatment phase to baseline phase observations, but also time-specific between-series comparisons of observations from those that have started treatment to those that are still in the baseline. For analyzing MB studies, two types of linear mixed modeling methods have been proposed: the within- and between-series models. In principle, those models were developed based on normality assumptions, however, normality may not always be found in practical settings. Therefore, this study aimed to investigate the robustness of the within- and between-series models when data were non-normal. A Monte Carlo study was conducted with four statistical approaches. The approaches were defined by the crossing of two analytic decisions: (a) whether to use a within- or between-series estimate of effect and (b) whether to use restricted maximum likelihood or Markov chain Monte Carlo estimations. The results showed the treatment effect estimates of the four approaches had minimal bias, that within-series estimates were more precise than between-series estimates, and that confidence interval coverage was frequently acceptable, but varied across conditions and methods of estimation. Applications and implications were discussed based on the findings.     

A Hierarchical Framework for Modeling Speed and Accuracy on Test Items

Current modeling of response times on test items has been strongly influenced by the paradigm of experimental reaction-time research in psychology. For instance, some of the models have a parameter structure that was chosen to represent a speed-accuracy tradeoff, while others equate speed directly with response time. Also, several response-time models seem to be unclear as to the level of parametrization they represent. A hierarchical framework for modeling speed and accuracy on test items is presented as an alternative to these models. The framework allows a “plug-and-play approach” with alternative choices of models for the response and response-time distributions as well as the distributions of their parameters. Bayesian treatment of the framework with Markov chain Monte Carlo (MCMC) computation facilitates the approach. Use of the framework is illustrated for the choice of a normal-ogive response model, a lognormal model for the response times, and multivariate normal models for their parameters with Gibbs sampling from the joint posterior distribution. This study received funding from the Law School Admission Council (LSAC). The opinions and conclusions contained in this paper are those of the author and do not necessarily reflect the policy and position of LSAC. The author is indebted to the American Institute of Certified Public Accountants for the data set in the empirical example and to Rinke H. Klein Entink for his computational assistance     

Describing Trajectories of Homeless Service Use in Hawai‘i Using Latent Class Growth Analysis

The State of Hawai‘i, like many other areas across the United States, has large numbers of individuals and families experiencing homelessness, many of whom seek support through statewide shelters and services. This study explored the diversity of ways in which individuals and families moved through Hawai‘i's homeless service system. Using administrative data, a cohort of new service users was tracked across time to trace the developmental trajectories of their homeless service use. The sample consisted of adults who had entered the service system for the first time in the fiscal year (FY) of 2010 (N = 4655). These individuals were then tracked through the end of FY 2014, as they used emergency shelter, transitional shelter, and outreach services. A latent class growth analysis was conducted and identified four distinct patterns of service use: low service use (n = 3966, 85.2%); typical transitional shelter use (n = 452, 9.7%); atypical transitional use (n = 127, 2.7%), and potential chronic service use (n = 110, 2.4%). Multinomial logistic regression models were then used to determine if select demographic, family, background experience (e.g., education, employment), or health variables were associated with class membership. The distinct profiles for class membership are discussed.     

Conditional estimation of exponential random graph models from snowball sampling designs

A complete survey of a network in a large population may be prohibitively difficult and costly. So it is important to estimate models for networks using data from various network sampling designs, such as link-tracing designs. We focus here on snowball sampling designs, designs in which the members of an initial sample of network members are asked to nominate their network partners, their network partners are then traced and asked to nominate their network partners, and so on. We assume an exponential random graph model (ERGM) of a particular parametric form and outline a conditional maximum likelihood estimation procedure for obtaining estimates of ERGM parameters. This procedure is intended to complement the likelihood approach developed by  Handcock and Gile (2010) by providing a practical means of estimation when the size of the complete network is unknown and/or the complete network is very large. We report the outcome of a simulation study with a known model designed to assess the impact of initial sample size, population size, and number of sampling waves on properties of the estimates. We conclude with a discussion of the potential applications and further developments of the approach.     

Bayesian factor analysis for multilevel binary observations

Multilevel covariance structure models have become increasingly popular in the psychometric literature in the past few years to account for population heterogeneity and complex study designs. We develop practical simulation based procedures for Bayesian inference of multilevel binary factor analysis models. We illustrate how Markov Chain Monte Carlo procedures such as Gibbs sampling and Metropolis-Hastings methods can be used to perform Bayesian inference, model checking and model comparison without the need for multidimensional numerical integration. We illustrate the proposed estimation methods using three simulation studies and an application involving student's achievement results in different areas of mathematics. The authors thank Ian Westbury, University of Illinois at Urbana Champaign for kindly providing the SIMS data for the application.