Latent variables should remain as such
Evidence from a Monte Carlo study
Bibliographic Data
| ID | 10124331 |
|---|---|
| Authors | Karina Navarro (0000-0002-2370-6909, University of Chile, corresponding author) |
| Year | 2019 |
| Volume | 146 |
| Issue | 4 |
| Pages | 417-442 |
| Publication date | 2019-04-22 |
| Peer Reviewed | Yes |
| Open Access | No |
| Type | ARTICLE |
| Venue | The Journal of General Psychology (JOURNAL) |
| Journal identifiers | ISSN: 0022-1309 • E-ISSN: 1940-0888 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/00221309.2019.1596064 |
| PMID | 31008695 |
| OpenAlex | W2940926386 |
| Language | EN |
| Citations received | 3 |
| References cited | 40 |
Use of subject scores as manifest variables to assess the relationship between latent variables produces attenuated estimates. This has been demonstrated for raw scores from classical test theory (CTT) and factor scores derived from factor analysis. Conclusions on scores have not been sufficiently extended to item response theory (IRT) theta estimates, which are still recommended for estimation of relationships between latent variables. This is because IRT estimates appear to have preferable properties compared to CTT, while structural equation modeling (SEM) is often advised as an alternative to scores for estimation of the relationship between latent variables. The present research evaluates the consequences of using subject scores as manifest variables in regression models to test the relationship between latent variables. Raw scores and three methods for obtaining theta estimates were used and compared to latent variable SEM modeling. A Monte Carlo study was designed by manipulating sample size, number of items, type of test, and magnitude of the correlation between latent variables. Results show that, despite the advantage of IRT models in other areas, estimates of the relationship between latent variables are always more accurate when SEM models are used. Recommendations are offered for applied researchers
Econometrics · Factor analysis · Item response theory · Latent class model · Latent variable · Latent variable model · Monte Carlo method · Psychometrics · Raw data · Raw score · Regression analysis · Sample (material · Sample size determination · Statistics · Structural equation modeling · Variables · Advanced Statistical Modeling Techniques · Diverse Approaches in Healthcare and Education Studies · Mathematics · Psychometric Methodologies and Testing
Item Response Theory
Statistical Approaches to Measurement Invariance
Item Response Theory
Multicollinearity and Measurement Error in Structural Equation Models
The new rules of measurement.
Estimation of IRT graded response models
Contributions to Factor Analysis of Dichotomous Variables
Computing and evaluating factor scores.
Mirt
Regression Among Factor Scores
On the Relationship between iTem Response Theory and Factor Analysis of Discretized Variables
Structural Equations with Latent Variables
A Monte Carlo Comparison of Item and Person Statistics Based on Item Response Theory versus Classical Test Theory
Item Response Theory and Classical Test Theory
Using IRT Trait Estimates Versus Summated Scores in Predicting Outcomes
Hypothesis Testing Using Factor Score Regression
Reexamining Nonlinear Structural Equation Modeling Procedures
Robustness Studies in Covariance Structure Modeling
Statistical Theories of Mental Test Scores
The trade-off between accuracy and precision in latent variable models of mediation processes
Effects of statistical models and items difficulties on making trait-level inferences
Developing Multidimensional Likert Scales Using Item Factor Analysis
| Unique citing works | 3 |
|---|---|
| Citations per year | 1 |
| Citation span | 2023 - 2026 (4) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 3 |