Multivariate Behavioral Research
Dados do Periódico
| Tipo | JOURNAL |
|---|---|
| Editora | Informa (GB) |
| ISSN | 0027-3171 / 1532-7906 |
| Scopus | 12711 |
| Wikidata | Q6935130 |
| OpenAlex | S64250036 |
| MAG | 64250036 |
| Site | https://www.tandfonline.com/toc/hmbr20/current |
| Total de publicações | 2.224 |
| Período coberto | 1966 - 2026 |
| País | US |
| Idioma | EN |
| Indexação | Scopus |
| Citada por | 890 |
| Fator de impacto | 1.589 |
| SJR | 2.017 (Q1) |
| SNIP | 1.76 |
| CiteScore | 5.8 |
| Índice h | 2 |
| Índice i10 | 1 |
| Citações em políticas (Overton) | 1 |
| Participação feminina na autoria | 36.7% |
This journal focuses on multivariate statistical methods in behavioral research. Its highly quantitative and methodological scope places it as a broader social science journal (psychology/statistics) with only loose intersection with social anthropology
Arts and Humanities (miscellaneous) · Experimental and Cognitive Psychology · Medicine (miscellaneous) · Statistics and Probability · Advanced Causal Inference Techniques · Advanced Statistical Methods and Models · Advanced Statistical Modeling Techniques · Bayesian Methods and Mixture Models · Bayesian Modeling and Causal Inference
Handling Missing Data in Intensive Longitudinal Data with Mixed Missing Mechanisms
Intensive longitudinal studies (ILS) are particularly prone to high levels of missing data compared to cross-sectional or traditional panel designs. Missingness may arise concurrently from the data collection process (MCAR, MAR, or MNAR) and from the handling of unequal measurement intervals (often treated as MAR), resulting in mixed missing mechanisms. Despite their prevalence in applied research, little is known about how missing-data handling …
Bayesian Machine Learning Tools for Alcohol Use Disorder Research
Alcohol use disorder (AUD) research faces significant challenges in capturing individual heterogeneity and complex temporal patterns in drinking behaviors. Standard statistical methods fail to account for within-person variability and between-person differences, while existing machine learning algorithms are not designed for hierarchical, longitudinal data structures common in AUD research. We developed a comprehensive R package implementing 30 B…
A Unified Framework for Jointly modelling Response Times and Item Position Effects in Computer-Based Learning Assessments
typically overlook variations in speed and ability within individuals. Instead, they often treat these as residual variances, missing the dynamic changes in individual performance throughout a test. Additionally, the influence of item position and the ordinal nature of response accuracy remain underexplored. This paper introduces a comprehensive modelling framework that integrates item responses, response times, and item position to better unders…
A Modularized Higher-Order Diagnostic Classification Model for Clustered Attribute Hierarchies
Recognizing that complex networks of skills typically exhibit hierarchical and modular organization, this article presents a Modularized Higher-Order Diagnostic Classification Model (MHO-DCM) designed to capture hierarchical relationships among attributes organized into clustered subdomains. Central to the proposed method is a representation of attribute hierarchies in which attributes are grouped into cognitively coherent subgraphs nested within…
Exploring the Use of Multiple Imputation for Handling Missing Covariates in Meta-Regression with Dependent Effect Sizes
Meta-analysts frequently encounter missing covariate values, which can complicate valid estimation of meta-regression models. In practice, missing data are managed often through ad hoc deletion approaches, which can reduce the validity of statistical inferences. More advanced missing data handling approaches such as multiple imputation (MI) remain underutilized, particularly in meta-analyses with dependent effect sizes within studies. This study …
Classic or Computational Graph? A Comparison of SEM Estimation Frameworks
Structural equation modeling (SEM) has traditionally relied on a narrow form of estimation—herein referred to as classic SEM—which uses analytic derivatives of an objective function and quasi-Newto
On the Consequences of Model Misspecification in Longitudinal Missing Data Analysis
Longitudinal studies are widely used in the social and behavioral sciences to investigate intraindividual change over time and interindividual differences in change. Because data are collected repe
Fair and Robust Estimation of Heterogeneous Treatment Effects for Optimal Policies in Multilevel Studies
Recently, there have been growing efforts in developing fair algorithms for treatment effect estimation and optimal treatment recommendations to mitigate discriminatory biases against disadvantaged groups. While most of this work has focused on addressing discrimination due to individual-level sensitive variables (e.g., race/ethnicity), it overlooks the broader impact of societal structures and cultural norms (e.g., structural racism) beyond the …
How to Use Residual Dynamic Structural Equation Modeling to Study Individual Differences and Intraindividual Variability in Experimental Factorial Designs
This article demonstrates the application of residual dynamic structural equation modeling (RDSEM) for analyzing custom contrasts in experimental factorial designs. Previous applications of RDSEM have often focused on ecological momentary assessment and daily diary data. However, RDSEM was explicitly developed for intensive longitudinal data more generally, including settings with very short time intervals between observations. Beyond these types…
Automatic Mediation Analysis Under Measurement Error Via Bayesian Machine Learning
This paper considers the problem of causal mediation analysis (CMA) when the outcome, mediator, or both are modeled as latent variables that are measured with error from multiple indicators. Traditional structural equation modeling approaches rely on restrictive parametric assumptions and struggle to capture nonlinear relationships or interactions among covariates, outcomes, and mediators; additionally, accounting for measurement error is difficu…
A State Space Model of Daily Dynamics with Moderation Effects from Qualitative Text Data
The last two decades have seen a dramatic increase in using intensive longitudinal data to capture psychological processes. Intensive longitudinal data allow researchers to study intraindividual change and variability. Multiple modeling approaches have been developed to examine these dynamics in a process as it unfolds over time. What is often not considered in these models are factors that can influence the dynamics of the given process. In this…
Multivariate Location-Scale Models for Meta-Analysis
Often, primary studies that are pooled in a meta-analysis provide information on several outcomes of interest. Multivariate meta-analysis allows to analyze these outcomes simultaneously and model their relationship, and in addition can be more efficient than separate, univariate meta-analyses. However, standard multivariate meta-analysis models typically assume that the between-study variances and correlations are constant across studies. While i…
The Effects of Data Preprocessing Choices on Behavioral RCT Outcomes
Seemingly routine data-preprocessing choices can exert outsized influence on the conclusions drawn from randomized controlled trials (RCTs), particularly in behavioral science where data are noisy, skewed and replete with outliers. We demonstrate this influence with two fully specified multiverse analyses on simulated RCT data. Each analysis spans 180 analytical pathways, produced by crossing 36 preprocessing pipelines that vary outlier handling,…
Neural Network Analysis of Psychological Data
Artificial neural networks (ANN) have attracted increasing attention in the field of psychology. With the availability of software programs, the wide application of ANN becomes possible. However, without a firm understanding of the basics of the ANN, issues can easily arise. This article presents a step-by-step guide for implementing a feed-forward neural network (FNN) on a psychological data set to illustrate the critical steps in building, esti…
Multilevel Metamodels
Metamodels, or the regression analysis of Monte Carlo simulation results, provide a powerful tool to summarize simulation findings. However, an underutilized approach is the multilevel metamodel (MLMM) that accounts for the dependent data structure that arises from fitting multiple models to the same simulated data set. In this study, we articulate the theoretical rationale for the MLMM and illustrate how it can improve the interpretability of si…
Demystifying Posterior Distributions
Bayesian statistics have gained significant traction across various fields over the past few decades. Bayesian statistics textbooks often provide both code and the analytical forms of parameters for simple models. However, they often omit the process of deriving posterior distributions or limit it to basic univariate examples focused on the mean and variance. Additionally, these resources frequently assume a strong background in linear algebra an…
Sample Size Determination for Optimal and Sub-Optimal Designs in Simplified Parametric Test Norming
Norms play a critical role in high-stakes individual assessments (e.g., diagnosing intellectual disabilities), where precision and stability are essential. To reduce fluctuations in norms due to sampling, normative studies must be based on sufficiently large and well-designed samples. This paper provides formulas, applicable to any sample composition, for determining the required sample size for normative studies under the simplified parametric n…
Detecting Transition Points in the Slope-Intercept Relation in Linear Latent Growth Models
In a linear latent growth model parameterized by intercept (α) and slope (β) factors, those factors' relation is often of interest. The model typically captures this through their covariance parameter, which inherently assumes linearity in their relation. However, this assumption may not always hold. For instance, α and β might be unrelated below a certain threshold along the α-axis but show a meaningful relation above it. That is, even though in…
Calculating and Interpreting Maximal Reliability in Bifactor Models
Confirmatory bifactor models have been widely applied to understand multidimensional constructs in different areas of psychology research. Maximal reliability captures how well an optimal linear composite (OLC) represents the target latent variable. In this article, we point out that researchers have been using an incorrect generalization of coefficient H, a maximal reliability coefficient developed for one-factor models, with bifactor models. We…
Moderating the Consequences of Longitudinal Change for Distal Outcomes
There has been a growing interest in using earlier change to predict downstream distal outcomes in development; however, prior work has mostly focused on estimating the unique effect of the different growth parameters (e.g., intercept and slope) rather than focusing on the trajectory as a whole. Here I lay out a distal outcome latent curve model with latent interactions which attempts to model the joint effect of growth parameters on these later …
On the Ratio Between Point-Polyserial and Polyserial Correlations for Non-Normal Bivariate Distributions
It is a well-known fact that for the bivariate normal distribution the ratio between the point-polyserial correlation (the linear correlation after one of the two variables is discretized into k categories with probabilities pi, i=1,...,k) and the polyserial correlation ρ (the linear correlation between the two normal components) remains constant with ρ, keeping the pi‘s fixed. If we move away from the bivariate normal distribution, by considerin…
Targeted Maximum Likelihood Estimation for Causal Inference With Observational Data—The Example of Private Tutoring
State-of-the-art causal inference methods for observational data promise to relax assumptions threatening valid causal inference. Targeted maximum likelihood estimation (TMLE), for example, is a template for constructing doubly robust, semiparametric, efficient substitution estimators, providing consistent estimates if the outcome or treatment model is correctly specified. Compared to standard approaches, it reduces the risk of misspecification b…
Correlated Residuals in Lagged-Effects Models
The appeal of lagged-effects models, like the first-order vector autoregressive (VAR(1)) model, is the interpretation of the lagged coefficients in terms of predictive-and possibly causal-relationships between variables over time. While the focus in VAR(1) applications has traditionally been on the strength and sign of the lagged relationships, there has been a growing interest in the residual relationships (i.e., the correlations between the inn…
Analyzing Count Data in Single Case Experimental Designs with Generalized Linear Mixed Models
Single-case experimental designs (SCEDs) involve repeated measurements of a small number of cases under different experimental conditions, offering valuable insights into treatment effects. However, challenges arise in the analysis of SCEDs when autocorrelation is present in the data. Recently, generalized linear mixed models (GLMMs) have emerged as a promising statistical approach for SCEDs with count outcomes. While prior research has demonstra…
Dynamic Fit Index Cutoffs for Time Series Network Models
In this study, we extend the dynamic fit index (DFI) developed by McNeish and Wolf to the context of time series analysis. DFI is a simulation-based method for deriving fit index cutoff values tailored to the specific model and data characteristics. Through simulations, we show that DFI cutoffs for detecting an omitted path in time series network models tend to be closer to exact fit than the popular benchmark values developed by Hu and Bentler. …
The Scree Test For The Number Of Factors
1966). The Scree Test For The Number Of Factors. Multivariate Behavioral Research: Vol. 1, No. 2, pp. 245-276
Confidence Intervals for the Probability of Superiority Effect Size Measure and the Area Under a Receiver Operating Characteristic Curve
It is good scientific practice to the report an appropriate estimate of effect size and a confidence interval (CI) to indicate the precision with which a population effect was estimated. For comparisons of 2 independent groups, a probability-based effect size estimator (A) that is equal to the area under a receiver operating characteristic curve and closely related to the popular Wilcoxon-Mann-Whitney nonparametric statistical tests has many appe…
An Exploration of Six Semantic Factors At First Grade
Six hypotheses in the semantic domain were developed for six-year-old children and implemented with a 23-test battery, which was administered to 100 Ss, IQ 60 to 154. Principal component factors were rotated by varimax, graphic, biquartimin and Procrustes processes, yielding essentially similar structure; interpretation was based on the graphic. Divergent semantic units (DMU) and systems (DMS) emerged clearly from other factors and each other, de…
The BC Try Computer System of Cluster And Factor Analysis
The structure and use of the BC TRY system in both variable and object analysis are described. The system of about 30 programs includes programs for data handling, intercorrelating data, communality estimation, factoring (cluster analysis, bifactor analysis, square root factoring, principal components, canonical factoring, alpha factoring, etc.), rotation, structure analysis, geo- metrical-graphical subsetting of factor spaces, factor and cluster…
The Dimensionality Of The CPI Socialization Scale And An Empirically Derived Typology Among Delinquent And Nondelinquent Boys
The 64 items of the CPI So scale were cluster analyzed in a sample of 318 males into 3 main dimensions: C-1-Stable home and school adjustment versus waywardness and dissatisfaction with family; C-2-Optimism and trust in others versus dysphoria, distrust and alienation; C-3-Observation of convention versus asocial role and attitude. The initial sample was comprised of 84 school disciplinary problems (DP), 75 institutionalized delinquents (D), and …
The Equivalence Of Psychotic Syndromes Across Two Media
The study goal was to test the equivalence of ten dimensions of psychotic behavior across two measuring media. The data consisted of ratings of 814 newly admitted schizophrenics made in the interview and on the ward. The factored. A least squares solution of a hypothesis matrix yielded ten clear factors of which eight were defined both by ward and interview measures
Ecology And The Science Of Psychology
The discussion reviews significant, converging developments contributing to the ecologic trend in psychology as well as issues and difficulties that must eventually be resolved. The presentation is focused principally on implications of the ecologic emphasis on content and method in psychology
Year-By-Year Changes In Personality From Six To Eighteen Years
Teacher trait-ratings on 42 bipolar traits were obtained for 660 school children (26 boys and 26 girls from Kindergarten through Grade 12). The trait-ratings were transformed into factor scores on Cattell's 16 basic personality factors. Year-by-year cross-sectional analysis of the trait-ratings and factor scores yielded significant sex and age differences throughout the school age period
Dimensions Of Leadership In A Student Cooperative
Homans (1960) analyzed leadership phenomena in terms of four major constructs, activity, interaction, aentiment, and norm. The present study developed an instrument to represent three of Homans' constructs and tested propositions based on his theory of small group leadership. Fifteen subjects, five each at three leadership levels, were rated by close associates and also rated themselves. With one exception (norms) the propositions derived from Ho…
Fixed Effects Analysis of Variance by Regression Analysis
This paper is concerned with the solution of typical analysis of variance problems using general purpose multiple regression computer programs. Specific models, restrictions on the parameters for hypothesis testing, and computational aspects are discussed. It is argued that this approach has many pedagogical advantages over traditional procedures
Determination and Evaluation of Rate Measurements in the Analysis of Space Medical Data
Measures of rate of change and of rate of rate of change are developed for application to physiological and psychological data. Examples are given of the use of these measures with heart-rate data for comparisons within and between subjects. It is shown that the measures provide information over and above that offered by means and variances, and that the measures appropriately reflect the impact of external variables
The Development of Nonmetric Space Analysis
A Simplicial Design for the Analysis of Correlational Learning Data
The usual matrix of intercorrelations among trials in a study of the learning process produces a superdiagonal matrix with resulting factors which are uninteresting: viz, a factor for the early trials and a factor for the later trials; with perhaps also a factor for the middle trials. By introducing several independent measures of learning for each trial a more meaningful factor structure can be obtained
Three-Mode Factor Analysis Of Parker-Fleishman Complex Tracking Behavior Data
A combination method of analysis utilizing Tucker's generalized learning curves and three-mode factor analysis is tried out on intercorrelations published by Parker and Fleishman of several measures of performance at several stages of practice on a complex tracking task. The results indicated two measure factors, directional control and sideslip control; four stages of practice factors, very early, middle early, middle late, and very late; and se…
The Empirical Anchor Technique
A simple experimental technique is proposed for assessing the construct validity of factor titles. The technique involves writing items which are implicit titles of an emergent factor, adding these items to a cross-validation sample with the hypothesis that the items should load high on the given factor and low on other factors. The results of the cross-validation factor analysis would then give estimates of convergent and discriminant validity o…
Behavioral And Personality Expectations Associated With Status Positions
Two parallel studies explore whether status-positions may be character- ized by certain general behaviors and personality traits. Fifty-two status- positions, including selected ethnic, occupational, age, sex, and familial categories, were ranked and rated on twenty-eight personality and behavioral characteristics by substantial samples of college students. Analysis of these data indicated that some behavioral characteristics and personality trai…
Direction Of Measurement And Profile Similarity
Recently, Tellegen (1965), in his discussion of the influence of direction of measurement on the analysis of test characteristics, pointed out that similar problems can exist in the assessment of profile similarity. This paper reports two empirical analyses which demonstrate that the correlations between personality test profiles are meaningfully affected by decisions concerning direction of measurement. Reflection of scales in a profile can alte…
Three Factor Analyses Of Electromyographic Data Under Varying Conditions
Electromyographic scores for seven muscles, systolic and diastolic blood pressure, heart rate, and galvanic skin resistance were obtained on 20 male and 24 female psychiatric clinic out-patients during three experimental conditions: rest, white noise, and psychological stress. Subjects also received 6 psychiatric ratings representing their response to the psychological stress. These ratings were included in all three score matrices. A principal c…
The Perceived Structure Of Social Attitudes And Personality
This study examined the relationships between attitudes inferred from behavior and attitudes implied by item content. 60 subjects judged the similarity between all possible pairs of 18 attitude items and 6 person descriptions designed to reflect three hypothesized dimensions of authoritarian ideology. These interstimulus similarity judgments were subjected t o a multidimensional scaling analysis. Results supported the hypotheses that (a) subsets …
Predicting Individual Differences By Cluster Analysis
Prediction of individual differences by cluster analysis procedures is described for the case of Holzinger's 24-variable problem and the case of MMPI item-clusters. Comparisons are made between univariate, multiple regression, and person-cluster predictions. The best prediction is from person- clusters, whose score patterns are objectively isolated by BC TRY Computer System programs. The role of chance is objectively assessed by program 4CAST and…
Predicting Group Differences In Cluster Analysis
Prediction of group differences by cluster analysis procedures is described for the case of neighborhoods (tracts) of a metropolitan area. Social areas of homogeneous neighborhoods are isolated by objective "O-analysis" procedures of the BC TRY Computer System. The predictor attributes are pre-war demographic features from which high predictions both of demographic and voting-attitudes are made up to 15 years, despite the social disruptions of a …
Multivariate Analysis Of A Rehabilitation System
Cross-validation of previously published findings regarding the structure of rehabilitation data yields substantial evidence that this structure is stable and quite definitive. Tentative data are presented regarding relation- ships between intelligence and personality on the one hand, and rehabilitation outcomes on the other. It appears that intelligence is more related to short- run outcomes; personality more related to long-run outcomes
The Reliability And Consistency Of Complex Personality Judgements
Two separate tasks were used to investigate the ability of subjects to make reliable and consistent judgments of similarities among personalities. Ten social categories for which each subject specified persons known to him- self were used as concepts. Test-retest reliabilities were obtained for an 8 point similarity-dissimilarity scale and inconsistency was measured by the intransitive relations appearing in a triadic judgment test. Reliabilities…
Group Based Pattern Analysis Of The Single Individual
This paper shows how the personality structure of a single individual can be statistically: analyzed into its component types (or factors) as these are reflected in responses which he has in common with a sample of subjects (chosen to be representative of a universe to which the single subject belongs). A further development expands the method to show how patterns can be selected in an effort to differentiate categories of individuals in a fashio…
Nonmetric Factor Analysis
(1967). Nonmetric Factor Analysis: A Rank Reducing Alternative To Linear Factor Analysis. Multivariate Behavioral Research: Vol. 2, No. 4, pp. 485-505
Methods Factors In Multitrait-Multimethod Matrices
When traits are measured by the same method (or at the same time) the intertrait correlations are higher than when the intertrait correlation is across methods. An empirical investigation of the nature of such method factors is reported, in which the method factors seem to operate in a multiplicative rather than additive way, or in which larger method loadings are associated with larger trait loadings. An implicit-theory-of-personality explanatio…
The Effect Of Shifts In Fixed-Interval Schedules On Acquisition, Extinction, Spontaneous Recovery, And Reacquisition
Using both multivariate and univariate statistical tests, the effect of two opposite patterns of primary reinforcement schedules upon the acquisition, extinction, spontaneous recovery and reacquisition of bar pressing was determined. Two control and two experimental groups, each consisting of eight Ss, formed the standard 2x2 factorial design for the experiment. The main effects were (a) effect of primary reinforcement (experimental vs. control g…