The Model Size Effect in SEM: Inflated Goodness-of-Fit Statistics Are Due to the Size of the Covariance Matrix

The size of a model has been shown to critically affect the goodness of approximation of the model fit statistic T to the asymptotic chi-square distribution in finite samples. It is not clear, however, whether this “model size effect” is a function of the number of manifest variables, the number of free parameters, or both. It is demonstrated by means of 2 Monte Carlo computer simulation studies that neither the number of free parameters to be estimated nor the model degrees of freedom systematically affect the T statistic when the number of manifest variables is held constant. Increasing the number of manifest variables, however, is associated with a severe bias. These results imply that model fit drastically depends on the size of the covariance matrix and that future studies involving goodness-of-fit statistics should always consider the number of manifest variables, but can safely neglect the influence of particular model specifications.     

Sample Size Requirements in Single- and Multiphase Growth Mixture Models: A Monte Carlo Simulation Study

Just as growth mixture models are useful with single-phase longitudinal data, multiphase growth mixture models can be used with multiple-phase longitudinal data. One of the practically important issues in single- and multiphase growth mixture models is the sample size requirements for accurate estimation. In a Monte Carlo simulation study, the sample sizes required for using these models are investigated under various theoretical and realistic conditions. In particular, the relationship between the sample size requirement and the number of indicator variables is examined, because the number of indicators can be relatively easily controlled by researchers in many multiphase data collection settings such as ecological momentary assessment. The findings not only provide tangible information about required sample sizes under various conditions to help researchers, but they also increase understanding of sample size requirements in single- and multiphase growth mixture models.     

The Impact of Sample Size and Other Factors When Estimating Multilevel Logistic Models

The design of research studies utilizing binary multilevel models must necessarily incorporate knowledge of multiple factors, including estimation method, variance component size, or number of predictors, in addition to sample sizes. This Monte Carlo study examined the performance of random effect binary outcome multilevel models under varying methods of estimation, level-1 and level-2 sample size, outcome prevalence, variance component sizes, and number of predictors using SAS software. Mean estimates of statistical power were influenced primarily by sample sizes at both levels. In addition, confidence interval coverage and width and the likelihood of nonpositive definite random effect covariance matrices were impacted by variance component size and estimation method. The interactions of these and other factors with various model performance outcomes are explored.     

Growth Curve Modeling to Studying Change: A Comparison of Approaches Using Longitudinal Dyadic Data With Distinguishable Dyads

Although methodology articles have increasingly emphasized the need to analyze data from two members of a dyad simultaneously, the most popular method in substantive applications is to examine dyad members separately. This might be due to the underappreciation of the extra information simultaneous modeling strategies can provide. Therefore, the goal of this study was to compare multiple growth curve modeling approaches for longitudinal dyadic data (LDD) in both structural equation modeling and multilevel modeling frameworks. Models separately assessing change over time for distinguishable dyad members are compared to simultaneous models fitted to LDD from both dyad members. Furthermore, we compared the simultaneous default versus dependent approaches (whether dyad pairs’ Level 1 [or unique] residuals are allowed to covary and differ in variance). Results indicated that estimates of variance and covariance components led to conflicting results. We recommend the simultaneous dependent approach for inferring differences in change over time within a dyad.     

Using Monte Carlo Normal Distributions to Evaluate Structural Models With Nonnormal Data

Statistical theories of goodness-of-fit tests in structural equation modeling are based on asymptotic distributions of test statistics. When the model includes a large number of variables or the population is not from a multivariate normal distribution, the asymptotic distributions do not approximate the distribution of the test statistics very well at small sample sizes. A variety of methods have been developed to improve the accuracy of hypothesis testing at small sample sizes. However, all these methods have their limitations, specially for nonnormal distributed data. We propose a Monte Carlo test that is able to control Type I error with more accuracy compared to existing approaches in both normal and nonnormally distributed data at small sample sizes. Extensive simulation studies show that the suggested Monte Carlo test has a more accurate observed significance level as compared to other tests with a reasonable power to reject misspecified models.     

Effect of Sample Size Ratio and Model Misfit When Using the Difficulty Parameter Differences Procedure to Detect DIF

This study examined the effect of sample size ratio and model misfit on the Type I error rates and power of the Difficulty Parameter Differences procedure using Winsteps. A unidimensional 30-item test with responses from 130,000 examinees was simulated and four independent variables were manipulated: sample size ratio (20/100/250/500/1000); model fit/misfit (1 PL and 3PLc =. 15 models); impact (no difference/mean differences/variance differences/mean and variance differences); and percentage of items with uniform and nonuniform DIF (0%/10%/20%). In general, the results indicate the importance of ensuring model fit to achieve greater control of Type I error and adequate statistical power. The manipulated variables produced inflated Type I error rates, which were well controlled when a measure of DIF magnitude was applied. Sample size ratio also had an effect on the power of the procedure. The paper discusses the practical implications of these results.     

Revisiting the Model Size Effect in Structural Equation Modeling

Fitting a large structural equation modeling (SEM) model with moderate to small sample sizes results in an inflated Type I error rate for the likelihood ratio test statistic under the chi-square reference distribution, known as the model size effect. In this article, we show that the number of observed variables (p) and the number of free parameters (q) have unique effects on the Type I error rate of the likelihood ratio test statistic. In addition, the effects of p and q cannot be fully explained using degrees of freedom (df). We also evaluated the performance of 4 correctional methods for the model size effect, including Bartlett’s (1950), Swain’s (1975), and Yuan’s (2005) corrected statistics, and Yuan, Tian, and Yanagihara’s (2015) empirically corrected statistic. We found that Yuan et al.’s (2015) empirically corrected statistic generally yields the best performance in controlling the Type I error rate when fitting large SEM models.     

On Fitting a Multivariate Two-Part Latent Growth Model

The purpose of this study was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete substantive measurement theory. Three Monte Carlo studies were performed based on the ratio of the number of observed variables to the number of underlying factors. Within each study, communality, sample size, and the number of targets were manipulated. Outcomes included a measure of congruence and a measure of variability with regard to the rotated pattern matrix. The magnitude of the main effect for the influence of the number of targets on congruence and variability ranged from moderate to large. The magnitude of the interaction between the number of targets and level of communality ranged from small to moderate with regard to congruence and variability. Consistent with theoretical expectations, the minimum number of targets to specify to be reasonably assured of obtaining an accurate solution varied across study conditions.     

Inference and Interval Estimation Methods for Indirect Effects With Latent Variable Models

Although much is known about the performance of recent methods for inference and interval estimation for indirect or mediated effects with observed variables, little is known about their performance in latent variable models. This article presents an extensive Monte Carlo study of 11 different leading or popular methods adapted to structural equation models with latent variables. Manipulated variables included sample size, number of indicators per latent variable, internal consistency per set of indicators, and 16 different path combinations between latent variables. Results indicate that some popular or previously recommended methods, such as the bias-corrected bootstrap and asymptotic standard errors had poorly calibrated Type I error and coverage rates in some conditions. Likelihood-based confidence intervals, the distribution of the product method, and the percentile bootstrap emerged as leading methods for both interval estimation and inference, whereas joint significance tests and the partial posterior method performed well for inference.     

Comparing Squared Multiple Correlation Coefficients Using Structural Equation Modeling

In social science research, a common topic in multiple regression analysis is to compare the squared multiple correlation coefficients in different populations. Existing methods based on asymptotic theories (Olkin & Finn, 1995) and bootstrapping (Chan, 2009) are available but these can only handle a 2-group comparison. Another method based on structural equation modeling (SEM) has been proposed recently. However, this method has three disadvantages. First, it requires the user to explicitly specify the sample R² as a function in terms of the basic SEM model parameters, which is sometimes troublesome and error prone. Second, it requires the specification of nonlinear constraints, which is not available in some popular SEM software programs. Third, it is for a 2-group comparison primarily. In this article, a 2-stage SEM method is proposed as an alternative. Unlike all other existing methods, the proposed method is simple to use, and it does not require any specific programming features such as the specification of nonlinear constraints. More important, the method allows a simultaneous comparison of 3 or more groups. A real example is given to illustrate the proposed method using EQS, a popular SEM software program.     

Neglect the Structure of Multitrait-Multimethod Data at Your Peril: Implications for Associations With External Variables

In 1959, Campbell and Fiske introduced the use of multitrait–multimethod (MTMM) matrices in psychology, and for the past 4 decades confirmatory factor analysis (CFA) has commonly been used to analyze MTMM data. However, researchers do not always fit CFA models when MTMM data are available; when CFA modeling is used, multiple models are available that have attendant strengths and weaknesses. In this article, we used a Monte Carlo simulation to investigate the drawbacks of either using CFA models that fail to match the data-generating model or completely ignore the MTMM structure of data when the research goal is to uncover associations between trait constructs and external variables. We then used data from the National Institute of Child Health and Human Development Study of Early Child Care and Youth Development to illustrate the substantive implications of fitting models that partially or completely ignore MTMM data structures. Results from analyses of both simulated and empirical data show noticeable biases when the MTMM data structure is partially or completely neglected.     

Linking Academic Entitlement and Student Incivility Using Latent Means Modeling

Academic entitlement has been theoretically linked with uncivil student behavior; however, this relationship has not been tested. To address this gap in the literature, the authors used latent means modeling to estimate the relationship between the Academic Entitlement Questionnaire and uncivil student behavior. The authors gathered scores on the questionnaire from 2 samples of students: civil/compliant and uncivil/noncompliant. Measurement invariance was established for the Academic Entitlement Questionnaire, providing additional validity evidence for the scale and allowing for the estimation of the latent mean difference in academic entitlement. As predicted, noncompliant students were significantly higher in academic entitlement than were compliant students. These results empirically link academic entitlement and student incivility, further supporting that academic entitlement is an important construct in academia and should receive increased attention from educators.     

Bayesian Model Averaging Over Directed Acyclic Graphs With Implications for the Predictive Performance of Structural Equation Models

This article examines Bayesian model averaging as a means of addressing predictive performance in Bayesian structural equation models. The current approach to addressing the problem of model uncertainty lies in the method of Bayesian model averaging. We expand the work of Madigan and his colleagues by considering a structural equation model as a special case of a directed acyclic graph. We then provide an algorithm that searches the model space for submodels and obtains a weighted average of the submodels using posterior model probabilities as weights. Our simulation study provides a frequentist evaluation of our Bayesian model averaging approach and indicates that when the true model is known, Bayesian model averaging does not yield necessarily better predictive performance compared to nonaveraged models. However, our case study using data from an international large-scale assessment reveals that the model-averaged submodels provide better posterior predictive performance compared to the initially specified model.     

Cross-Validation of a Model of Intrinsic Motivation With Students Enrolled in High School Elective Courses

The purpose of this study was to cross-validate a model of relationships among social-contextual factors, individual differences, and intrinsic motivation in adolescent students enrolled in required courses (E. Ferrer-Caja & M. R. Weiss, 2000) with an independent sample of students taking elective courses. Female and male high school students (N = 219) completed measures of motivational climate, teaching style, perceived competence, self-determination, goal orientation, and intrinsic motivation. Motivated behavior was assessed by teachers who rated the students on effort and persistence in class activities. First, the authors used structural equation modeling to examine model invariance between the original and the new samples, which yielded a lack of equivalence. Next, the authors examined several alternative theory-based models using the elective sample. The results indicated that the data were best represented by a model that separated social-contextual factors, individual factors, intrinsic motivation, and motivated behaviors. The strongest predictors of intrinsic motivation were task-goal orientation and perceived competence. These results are discussed from both theoretical and methodological perspectives.     

Bayesian Evaluation of Inequality-Constrained Hypotheses in SEM Models Using Mplus

Researchers in the behavioral and social sciences often have expectations that can be expressed in the form of inequality constraints among the parameters of a structural equation model resulting in an informative hypothesis. The questions they would like an answer to are “Is the hypothesis Correct” or “Is the hypothesis incorrect?” We demonstrate a Bayesian approach to compare an inequality-constrained hypothesis with its complement in an SEM framework. The method is introduced and its utility is illustrated by means of an example. Furthermore, the influence of the specification of the prior distribution is examined. Finally, it is shown how the approach proposed can be implemented using Mplus.     

A Model of Homework's Influence on the Performance Evaluations of Elementary School Students

This study was the first to test a model of the influence of homework on classroom performance using a sample of elementary school students. A total of 28 teachers in Grades 2 and 4 took part in the study, along with 428 students and parents. The authors used structural equation modeling to examine relationships among variables. Student norms were positively related to the elimination of distractions from homework by parents. Positive student norms, higher student ability, and positive parent attitudes toward homework were all related to greater parent facilitation. Student's attitude toward homework was unrelated to home and community factors but was related positively to parent attitudes toward homework. Classroom grades were unrelated to student's attitude toward homework but were predicted by how much homework the student completed (even after the use of homework in grading was controlled), by student ability, and by the amount of parent facilitation. More generally, parent facilitation was an important mediator of the relation between student norms, student ability, and parent attitudes toward homework, and the outcome of classroom grades.     

Sensitivity of SEM Fit Indexes With Respect to Violations of Uncorrelated Errors

This simulation study investigated the sensitivity of commonly used cutoff values for global-model-fit indexes, with regard to different degrees of violations of the assumption of uncorrelated errors in confirmatory factor analysis. It is shown that the global-model-fit indexes fell short in identifying weak to strong model misspecifications under both different degrees of correlated error terms, and various simulation conditions. On the basis of an example misspecification search, it is argued that global model testing must be supplemented by this procedure. Implications for the use of structural equation modeling are discussed.     

Exploratory and Confirmatory Factor Analysis of the School Level Environment Questionnaire (SLEQ)

The purpose of the present study was to validate an existing school environment instrument, the School Level Environment Questionnaire (SLEQ). The SLEQ consists of 56 items, with seven items in each of eight scales. One thousand, one hundred and six (1106) teachers in 59 elementary schools in a southwestern USA public school district completed the instrument. An exploratory factor analysis was undertaken for a random sample of half of the completed surveys. Using principal axis factoring with oblique rotation, this analysis suggested that 13 items should be dropped and that the remaining 43 items could best be represented by seven rather than eight factors. A confirmatory factor analysis was run with the other half of the original sample using structural equation modeling. Examination of the fit indices indicated that the model came close to fitting the data, with goodness-of-fit (GOF) coefficients just below recommended levels. A second model was then run with two of the seven factors, with their associated items removed. That left five factors with 35 items. Model fit was improved. A third model was tried, using the same five factors with 35 items but with correlated residuals between some of the items within a factor. This model seemed to fit the data well, with GOF coefficients in recommended ranges. These results led to a refined, more parsimonious version of the SLEQ that was then used in a larger study. Future research is needed to see if this model would fit other samples in different elementary schools and in secondary schools both in the USA and in other countries. This revised version was published online in July 2006 with corrections to the Cover Date.     

The Effect of Scale Referent on Tests of Mean Structure Parameters

Structured means analysis is a very useful approach for testing hypotheses about population means on latent constructs. In such models, a z test is most commonly used for testing the statistical significance of the relevant parameter estimates or of the differences between parameter estimates, where a z value is computed based on the asymptotic standard error estimate associated with the parameter of interest. In the current article, a series of population analyses demonstrate that the z tests for latent mean structure parameters or, more directly, the standard error estimates upon which those z tests are based are, not invariant to how factors are scaled. As such, circumstances exist in which latent mean inference is compromised solely as a result of scaling decisions. This problem is illustrated in the context of between-subjects (i.e., multisample) latent means models and within-subjects latent means models. Recommendations for practice are also offered.