A Relative Normed Effect-Size Difference Index for Determining the Number of Common Factors in Exploratory Solutions

Article Psychology, Multidisciplinary

We Need to Change How We Compute RMSEA for Nested Model Comparisons in Structural Equation Modeling

Victoria Savalei et al.

Summary: Comparison of nested models in structural equation modeling (SEM) often involves the use of fit indices and chi-square difference tests. This article argues that comparing RMSEA values by simply taking their difference is problematic and suggests the use of RMSEA(D) associated with the chi-square difference test instead. The authors highlight the need to modify current practices, especially in the assessment of measurement invariance.

PSYCHOLOGICAL METHODS (2023)

Add to Collection

Article Psychology, Educational

On Effect Size Measures for Nested Measurement Models

Tenko Raykov et al.

Summary: This article discusses a class of effect size indices that evaluate the differences between two nested confirmatory factor analysis models in terms of fit to observed variables. These indices quantify the impact of parameter restrictions on the initially considered model and are independent of sample size. The described indices measure the changes in linear combinations of the proportions of explained variance in the manifest variables as a result of introducing constraints. They are not influenced by the statistical significance of these restrictions. The discussed effect size measures can be easily estimated using popular software and their application is illustrated with numerical examples.

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT (2022)

Add to Collection

Article Psychology, Mathematical

SOLOMON: a method for splitting a sample into equivalent subsamples in factor analysis

Urbano Lorenzo-Seva

Summary: Exploratory factor analysis and confirmatory factor analysis are two important consecutive steps in the overall analysis process. Researchers split a single sample into two halves using a random split method to conduct the analysis. This paper introduces a new method of splitting samples for factor analysis, which has been tested in simulation studies and real datasets.

BEHAVIOR RESEARCH METHODS (2022)

Add to Collection

Article Psychology, Educational

Examining Multidimensional Measuring Instruments for Proximity to Unidimensional Structure Using Latent Variable Modeling

Tenko Raykov et al.

Summary: This article discusses a procedure for testing proximity to unidimensionality for multicomponent measuring instruments with multidimensional structure. Developed within the framework of latent variable modeling, the method allows one to estimate a variance proportion-based index that indicates proximity to unidimensional structure. It can be applied in educational, behavioral, and social research to evaluate whether a more general structure scale, test, or measuring instrument could be considered as associated with an approximately unidimensional latent structure for certain empirical purposes.

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT (2021)

Add to Collection

Article Psychology, Educational

Model Selection and Average Proportion Explained Variance in Exploratory Factor Analysis

Tenko Raykov et al.

Summary: This paper discusses a procedure for evaluating the average R-squared index for a given set of observed variables in an exploratory factor analysis model, which can serve as an effective tool in model selection. The method is developed within the framework of exploratory structural equation modeling and is easy to apply with popular statistical software. The outlined procedure is demonstrated using a numerical example.

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT (2021)

Add to Collection

Article Social Sciences, Mathematical Methods

MSA: The Forgotten Index for Identifying Inappropriate Items Before Computing Exploratory Item Factor Analysis

Urbano Lorenzo-Seva et al.

Summary: Kaiser's single-variable measure of sampling adequacy (MSA) is a useful index for item selection, but is currently underutilized. The proposal discusses the foundation and rationale of MSA from a modern FA perspective, incorporates the index into a robust approach, and implements the proposal in various statistical programs. The use and advantages of MSA are illustrated through an empirical example in personality measurement.

METHODOLOGY-EUROPEAN JOURNAL OF RESEARCH METHODS FOR THE BEHAVIORAL AND SOCIAL SCIENCES (2021)

Add to Collection

Article Mathematics, Interdisciplinary Applications