Jeffrey R. Harring

University of Maryland, College Park | UMD, UMCP, University of Maryland College Park · Department of Human Development and Quantitative Methodology

A Monte Carlo simulation was performed to compare methods for handling missing data in growth mixture models. The methods considered in the current study were (a) a fully Bayesian approach using a Gibbs sampler, (b) full information maximum likelihood using the expectation–maximization algorithm, (c) multiple imputation, (d) a two-stage multiple im...

Preknowledge cheating jeopardizes the validity of inferences based on test results. Many methods have been developed to detect preknowledge cheating by jointly analyzing item responses and response times. Gaze fixations, an essential eye-tracker measure, can be utilized to help detect aberrant testing behavior with improved accuracy beyond using pr...

Educational researchers continue to debate the relative contribution of individual and environmental factors to learning. Concomitant with the proliferation of longitudinal educational testing following students and schools over time, recent research has shown that nonlinear mixed effect models can be parameterized to directly estimate quantities m...

Recently, joint models of item response data and response times have been proposed to better assess and understand test takers’ learning processes. This article demonstrates how biometric information such as gaze fixation counts obtained from an eye-tracking machine can be integrated into the measurement model. The proposed joint modeling framework...

Growth mixture models (GMMs) are a popular method to identify latent classes of growth trajectories. One shortcoming of GMMs is nonconvergence, which often leads researchers to apply covariance equality constraints to simplify estimation, though this may be a dubious assumption. Alternative model specifications have been proposed to reduce nonconve...

Sensitivity analyses encompass a broad set of post-analytic techniques that are characterized as measuring the potential impact of any factor that has an effect on some output variables of a model. This research focuses on the utility of the simulated annealing algorithm to automatically identify path configurations and parameter values of omitted...

Writing is a critical dimension of literacy that is grounded in language and intimately connected to reading. However, instruction to support writing remains understudied, particularly among bilingual students. The purpose of this study was to examine the effects of the CLAVES intervention specifically on argument writing. The CLAVES intervention i...

Measuring change in an educational or psychological construct over time is often achieved by repeatedly administering the same items to the same examinees over time and fitting a second-order latent growth curve model. However, latent growth modeling with full information maximum likelihood (FIML) estimation becomes computationally challenging when...

Studies using structural equation modeling (SEM) to evaluate theories against observed data rely on multiple sources of evidence to support a proposed model, such as fit indices, variance explained, and comparison of alternative models. Additional evidence can be obtained by evaluating the model results’ sensitivity to an omitted confounder. The ph...

Growth mixture models (GMMs) are a popular method to identify latent classes of growth trajectories. One shortcoming of GMMs is nonconvergence, which often leads researchers to apply covariance equality constraints to simplify estimation. This approach is criticized because it introduces a dubious homoskedasticity assumption across classes. Alterna...

Purpose Many studies have found a correlation between overall usage rates of nonmainstream forms and reading scores, but less is known about which dialect differences are most predictive. Here, we consider different methods of characterizing African American English use from existing assessments and examine which methods best predict literacy achie...

Growth mixture models (GMMs) are a popular method to uncover heterogeneity in growth trajectories. Harnessing the power of GMMs in applications is difficult given the prevalence of nonconvergence when fitting GMMs to empirical data. GMMs are rooted in the random effect tradition and nonconvergence often leads researchers to modify their intended mo...

Simulation studies involving mixture models inevitably aggregate parameter estimates and other output across numerous replications. A primary issue that arises in these methodological investigations is label switching. The current study compares several label switching corrections that are commonly used when dealing with mixture models. A growth mi...

Many approaches have been proposed to jointly analyze item responses and response times to understand behavioral differences between normally- and aberrantly-behaved test-takers. Biometric information, such as data from eye trackers, can be utilized to better identify these deviant testing behaviors in addition to more conventional data types. Give...

In this digital ITEMS module, Dr. Jeffrey Harring and Ms. Tessa Johnson introduce the linear mixed effects (LME) model as a flexible general framework for simultaneously modeling continuous repeated measures data with a scientifically defensible function that adequately summarizes both individual change as well as the average response. The module b...

Piecewise latent growth models (LGMs) for linear-linear processes have been well-documented and studied in recent years. However, in the latent growth modeling literature, advancements to other functional forms as well as to multiple changepoints or knots have been nearly non-existent. This manuscript deals with three extensions. The first is to a...

Guided by emotional security theory, we explored how child and context-related factors were associated with heterogeneity in young foster children’s organized patterns of fear response to distress. Results from group-based trajectory modeling used to analyze observational data from a fear-eliciting task showed that children from our sample (mean ag...

Longitudinal time use data afford the opportunity to study within- and between-individual differences, but can present challenges in data analysis. Often the response set includes a large number of zeros representing those who did not engage in the target behavior. Coupled with this is a continuous measure of time use for those who did engage. The...

Researchers require methods for evaluating whether statistical results are credible and thus, worthy of interpretation. An examination of fungible parameters estimates is a method in which the veracity of inferences can be strengthened or weakened by quantifying the level of support for individual parameter estimates as measured by the likelihood f...

Growth mixture models (GMMs) are prevalent for modeling unknown population heterogeneity via distinct latent classes. However, GMMs are riddled with convergence issues, often requiring researchers to atheoretically alter the model with cross-class constraints simply to obtain convergence. We discuss how within-class random effects in GMMs exacerbat...

Growth mixture models (GMMs) are prevalent for modeling unknown population heterogeneity via distinct latent classes. However, GMMs are riddled with convergence issues, often requiring researchers to atheoretically alter the model with cross-class constraints to obtain convergence. We discuss how within-class random effects in GMMs exacerbate conve...

Respondent attrition is a common problem in national longitudinal panel surveys. To make full use of the data, weights are provided to account for attrition. Weight adjustments are based on sampling design information and data from the base year; information from subsequent waves is typically not utilized. Alternative methods to address bias from n...

Data mining methods have drawn considerable attention across diverse scientific fields. However, few applications could be found in the areas of psychological and educational measurement, and particularly pertinent to this article, in test security research. In this study, various data mining methods for detecting cheating behaviors on large‐scale...

Students are expected to comprehend and produce increasingly complex texts in upper elementary school, and academic language and literacy skills are considered critical to meeting these expectations. Notions of academic language are also controversial and require careful deliberation when applied to traditionally minoritized populations, including...

In longitudinal/developmental studies, individual growth trajectories are sometimes bounded by a floor at the beginning of the observation period and/or a ceiling toward the end of the observation period (or vice versa), resulting in inherently nonlinear growth patterns. If the trajectories between the floor and ceiling are approximately linear, su...

With the development of technology-enhanced learning platforms, eye tracking biometric indicators can be recorded simultaneously with students item responses. In the current study, visual fixation, an essential eye tracking indicator, is modeled to reflect the degree of test engagement when a test taker solves a set of test questions. Three negativ...

Data mining methods have drawn considerable attention across diverse scientific fields. However, few applications could be found in the areas of psychological and educational measurement, and particularly pertinent to this article, in test security research. In this study, various data mining methods for detecting cheating behaviors on large-scale...

Computer-based testing (CBT) is becoming increasingly popular in assessing test-takers latent abilities and making inferences regarding their cognitive processes. In addition to collecting item responses, an important benefit of using CBT is that response times (RTs) can also be recorded and used in subsequent analyses. To better understand the str...

Objective: In the present research, we examined the effect of getting a new teacher on consistency in students' personality measures, including trait and social cognitive constructs. Method: To test the effect of this kind of situational transition, we analyzed two large longitudinal samples (N = 5,628; N = 2,458) with quasi-experimental study d...

Nonlinear mixed-effects models are models in which one or more coefficients of the growth model enter in a nonlinear manner, such as appearing in the exponent of the growth function. In their applications, the within-individual residuals are often assumed to be independent with constant variance across time, an assumption that implies that the assu...

In this software review, we provide a brief overview of four R functions to estimate nonlinear mixed-effects programs: nlme (linear and nonlinear mixed-effects model), nlmer (from the lme4 package, linear mixed-effects models using Eigen and S4), saemix (stochastic approximation expectation maximization), and brms (Bayesian regression models using...

The social integration hypothesis concerns one cause of survey nonresponse. Individuals who are more integrated in society will be more likely to respond to a survey, while individuals who are socially isolated will be less likely to participate. While much research has demonstrated support for the social integration hypothesis, the strength of the...

Preschool children’s use of decontextualized language, or talk about abstract topics beyond the here-and-now, is predictive of their kindergarten readiness and is associated with the frequency of parents’ own use of decontextualized language. Does a brief, parent-focused intervention conveying the importance of decontextualized language cause paren...

This study explored effects of Spanish oral language skills (vocabulary and syntax) on the development of English oral language skills (vocabulary, morphology, semantics, syntax) and reading comprehension among 156 bilingual Latino children in second through fifth grade whose first language was Spanish and whose second language was English. Using a...

Patients with heart failure (HF) experience multiple symptoms or symptom clusters. The purposes of this study were to (a) determine if distinct latent classes of HF symptoms could be identified, and (b) explore whether sociodemographic and clinical characteristics influenced symptom cluster membership. A total of 4,011 HF patients recruited from ou...

Guided by bio-ecological theory, this study aimed to: (1) identify heterogeneity in the developmental patterns of emotion regulation for maltreated preschool-aged children; (2) examine the role of gender, language, placement instability, cognitive stimulation, and emotional support on patterns of stability and change of emotion regulation over time...

Extreme and non-extreme response styles (RSs) are prevalent in survey research using Likert-type scales. Their effects on measurement invariance (MI) in the context of confirmatory factor analysis are systematically investigated here via a Monte Carlo simulation study. Using the parameter estimates obtained from analyzing a 2007 Trends in Internati...

Nonlinear mixed-effects (NLME) models are used when analyzing continuous repeated measures data taken on each of a number of individuals where the focus is on characteristics of complex, nonlinear individual change. Challenges with fitting NLME models and interpreting analytic results have been well documented in the statistical literature. However...

Multiple criteria have been proposed to aid in deciding how many latent classes to extract in growth mixture models; however, studies are just beginning to investigate the performance of these criteria under non-ideal conditions. We review these previous studies and conduct a simulation study to address the performance of fit criteria under two pre...

Recent years have seen an explosion of empirical longitudinal research. The importance that practitioners are placing on longitudinal designs and analyses signals a critical shift toward methods that enable a better understanding of developmental processes thought to underlie many human attributes and behaviors. To keep up with the convergence of c...

Model-based clustering methods, commonly referred to as finite mixture modeling, have been applied to a wide variety of cross-sectional and longitudinal data to account for heterogeneity in population characteristics. In this article, we elucidate 2 such approaches: growth mixture modeling and latent profile analysis. Both techniques are illustrate...

Nonlinear random coefficient models (NRCMs) for continuous longitudinal data are often used for examining individual behaviors that display nonlinear patterns of development (or growth) over time in measured variables. As an extension of this model, this study considers the finite mixture of NRCMs that combine features of NRCMs with the idea of fin...

External misspecification, the omission of key variables from a structural model, can fundamentally alter the inferences one makes without such variables present. This article presents two strategies for dealing with omitted variables, the first a fixed parameter approach incorporating the omitted variable into the model as a phantom variable where...

To date, small sample problems with latent growth models (LGMs) have not received the amount of attention in the literature as related mixed effects models (MEMs). Although many models can be interchangeably framed as a LGM or a MEM, LGMs uniquely provide criteria to assess global data-model fit. However, previous studies have demonstrated poor sma...

Researchers continue to be interested in efficient, accurate methods of estimating coefficients of covariates in mixture modeling. Including covariates related to the latent class analysis not only may improve the ability of the mixture model to clearly differentiate between subjects but also makes interpretation of latent group membership more mea...

Nonlinear models are effective tools for the analysis of longitudinal data. These models provide a flexible means for describing data that follow complex forms of change. Exponential and logistic functions that include a parameter to represent an asymptote, for instance, are useful for describing responses that tend to level off with time. There ar...

A Monte Carlo simulation is employed to investigate the performance of five estimation methods of nonlinear mixed effects models in terms of parameter recovery and efficiency of both regression coefficients and variance/covariance parameters under varying levels of data sparseness and model misspecification.

The present study investigated language skills and reading comprehension with English monolingual and Spanish–English bilingual children in grades 2–5. Of the 377 children in the sample, 207 were English monolingual and 170 were Spanish–English bilingual. Data were collected within a cohort-sequential design for two academic years in the fall and s...

Several studies have stressed the importance of simultaneously estimating interaction and quadratic effects in multiple regression analyses, even if theory only suggests an interaction effect should be present. Specifically, past studies suggested that failing to simultaneously include quadratic effects when testing for interaction effects could re...

Latent curve models have become a popular approach to the analysis of longitudinal data. At the individual level the model expresses an individual's response as a linear combination of what are called `basis functions' that are common to all members of a population and weights that may vary among individuals. This paper uses differential calculus t...

The purpose of this study was to explore relationships between language variables and writing outcomes with linguistically diverse students in grades 3–5. The participants were 197 children from three schools in one district in the mid-Atlantic United States. We assessed students’ vocabulary knowledge and morphological and syntactical skill as well...

In this correlational study, we analyzed data from 71 Spanish-English biliterate students in grades 3 (n=21), 4 (n=23), and 5 (n=27) with the goal of investigating the applicability of the Simple View of Reading (Gough & Tunmer, 1986; Hoover & Gough, 1990) in English and in Spanish for this population. The simple view posits that decoding (the abil...

This study extends previous research on the long-term connections between motivation constructs in expectancy-value theory and achievement outcomes. Using growth mixture modelling, we examined trajectories of change for 421 students from 4th grade through college in their self-concept of ability (SCA) in math, interest in math, and perceived import...

Latent interaction models have motivated a great deal of methodological research, mainly in the area of estimating such models. Product-indicator methods have been shown to be competitive with other methods of estimation in terms of parameter bias and standard error accuracy, and their continued popularity in empirical studies is due, in part, to t...

Two classes of methods properly account for clustering of data: design-based methods and model-based methods. Estimates from both methods have been shown to be approximately equal with large samples. However, both classes are known to produce biased standard error estimates with small samples. This paper compares the bias of standard errors and sta...

The authors performed a Monte Carlo simulation to empirically investigate the robustness and power of 4 methods in testing mean differences for 2 independent groups under conditions in which 2 populations may not demonstrate the same pattern of nonnormality. The approaches considered were the t test, Wilcoxon rank-sum test, Welch-James test with tr...

Hipp and Bauer (2006) investigated the issues of singularities and local maximum 3 solutions within growth mixture models (GMMs) and made recommendations regarding 4 the use of multiple starting values. Building on their work, this simulation study 5 investigates the feasibility of estimating GMMs within Mplus as measured by 6 convergence to proper...

Physical activity in infancy is essential for early brain development. Development in the early years is the most rapid at any time during life. Monitoring functional movement skills of infants and toddlers frequently (3-week intervals) and quickly (minutes) produces information on whether development is on track or in need of intervention. To meet...

The primary aim of this study was to explore the relationship between teachers' instruction and students’ vocabulary and comprehension in grades 3–5. The secondary aim of this study was to investigate whether this relationship differed for English monolingual and Spanish–English bilingual students. To meet these aims, we observed and recorded readi...

Nonlinear mixed-effects (NLME) models remain popular among practitioners for analyzing continuous repeated measures data taken on each of a number of individuals when interest centers on characterizing individual-specific change. Within this framework, variation and correlation among the repeated measurements may be partitioned into interindividual...

Given the increase of bilingual students in the K-12 public school system, understanding reading comprehension performance, especially among this population, has been a major focal point in the research literature. This study explores the nature of reading comprehension among a sample of 123 Spanish–English bilingual elementary students. We add to...

Latent growth curve models with piecewise functions are flexible and useful analytic models for investigating individual behaviors that exhibit distinct phases of development in observed variables. As an extension of this framework, this study considers a piecewise linear-linear latent growth mixture model (LGMM) for describing segmented change of...

Latent growth curve models with piecewise functions for continuous repeated measures data have become increasingly popular and versatile tools for investigating individual behavior that exhibits distinct phases of development in observed variables. As an extension of this framework, this research study considers a piecewise function for describing...

Spline (or piecewise) regression models have been used in the past to account for patterns in observed data that exhibit distinct phases. The changepoint or knot marking the shift from one phase to the other, in many applications, is an unknown parameter to be estimated. As an extension of this framework, this research considers modeling the relati...

The present study investigated the role of vocabulary depth in reading comprehension among a diverse sample of monolingual and bilingual children in grades 2–4. Vocabulary depth was defined as including morphological awareness, awareness of semantic relations, and syntactic awareness. Two hundred ninety-four children from 3 schools in a Mid-Atlanti...

A rapidly expanding arena for item response theory (IRT) is in attitudinal and health-outcomes survey applications, often with polytomous items. In particular, there is interest in computer adaptive testing (CAT). Meeting model assumptions is necessary to realize the benefits of IRT in this setting, however. Although initial investigations of local...

Two Monte Carlo simulations were performed to compare methods for estimating and testing hypotheses of quadratic effects in latent variable regression models. The methods considered in the current study were (a) a 2-stage moderated regression approach using latent variable scores, (b) an unconstrained product indicator approach, (c) a latent modera...

A conditionally linear mixed effects model is an appropriate framework for investigating nonlinear change in a continuous latent variable that is repeatedly measured over time. The efficacy of the model is that it allows parameters that enter the specified nonlinear time-response function to be stochastic, whereas those parameters that enter in a n...

Background: Most individuals diagnosed with schizophrenia or other psychotic disorders are treated in the community mental health system, funded primarily by Medicaid. While much attention has been devoted to developing and disseminating evidence-based practices, little research has investigated the outcomes for consumers of the community mental he...

The Simple View of Reading (SVR) suggests that the components of reading comprehension are decoding and linguistic comprehension. Given research that suggests that fluency is a separate construct from decoding and linguistic comprehension in fourth grade, the aim of this study was to examine the role of fluency in the SVR model. Analyses of data fr...

Monte Carlo simulations in statistics are computer experiments involving random sampling from known probability distributions to study properties of statistical methods. As the relations among variables become increasingly complex, the method of generating data under imposed model and distributional conditions becomes progressively more complicated...

Fisher's correlation transformation is commonly used to draw inferences regarding the reliability of tests comprised of dichotomous or polytomous items. It is illustrated theoretically and empirically that omitting test length and difficulty results in inflated Type I error. An empirically unbiased correction is introduced within the transformation...

Previous research investigating children with Developmental Coordination Disorder (DCD) has consistently reported increased intra- and inter-individual variability during motor skill performance. Statistically characterizing this variability is not only critical for the analysis and interpretation of behavioral data, but also may facilitate our und...

Recent research has demonstrated that adaptation to a visuomotor distortion systematically influenced movements to auditory targets in adults and typically developing (TD) children, suggesting that the adaptation of spatial-to-motor transformations for reaching movements is multisensory (i.e., generalizable across sensory modalities). The multisens...

Conventional methods and analyses view measurement error as random. A scenario is presented where a variable was measured with systematic error. Mixture models with systematic parameter constraints were used to test hypotheses in the context of general linear models; this accommodated the heterogeneity arising due to systematic measurement error.

There has been a growing concern in higher education about our failure to produce scientifically trained workers and scientifically literate citizens. Active-learning and research-oriented activities are posited as ways to give students a deeper understanding of science. We report on an undergraduate teaching assistant (UTA) experience and suggest...