The performance of unweighted least squares and regularized unweighted least squares in estimating factor loadings in structural equation modeling

Zulkifli, N.; Aimran, N.; Deni, S.

Growing Science » International Journal of Data and Network Science » The performance of unweighted least squares and regularized unweighted least squares in estimating factor loadings in structural equation modeling

Journals

IJDS Volumes

Volume 1 (8)
- Issue 1 (5)
- Issue 2 (3)

Volume 2 (12)
- Issue 1 (3)
- Issue 2 (3)
- Issue 3 (3)
- Issue 4 (3)

Volume 3 (27)
- Issue 1 (4)
- Issue 2 (9)
- Issue 3 (8)
- Issue 4 (6)

Volume 4 (37)
- Issue 1 (6)
- Issue 2 (15)
- Issue 3 (7)
- Issue 4 (9)

Volume 5 (86)
- Issue 1 (9)
- Issue 2 (11)
- Issue 3 (32)
- Issue 4 (34)

Volume 6 (163)
- Issue 1 (30)
- Issue 2 (33)
- Issue 3 (40)
- Issue 4 (60)

Volume 7 (200)
- Issue 1 (53)
- Issue 2 (46)
- Issue 3 (46)
- Issue 4 (55)

Volume 8 (243)
- Issue 1 (60)
- Issue 2 (61)
- Issue 3 (60)
- Issue 4 (62)

Keywords

Authors

Countries

International Journal of Data and Network Science

ISSN 2561-8156 (Online) - ISSN 2561-8148 (Print) Quarterly Publication Volume 7 Issue 3 pp. 1017-1024 , 2023

The performance of unweighted least squares and regularized unweighted least squares in estimating factor loadings in structural equation modeling Pages 1017-1024 Download PDF

Authors: Nurul Raudhah Zulkifli, Nazim Aimran, Sayang Mohd Deni

DOI: 10.5267/j.ijdns.2023.6.004

Keywords: Monte Carlo simulation, Regularization, Unweighted least square, Regularized unweighted least square

Abstract: In a confirmatory study, researchers are expected to employ the covariance-based structural equation modeling (CB-SEM). One of the key presumptions when utilizing CB-SEM is that the data is multivariate normal. Nevertheless, a perfect normal distribution is rarely observed in real-life data. To resolve this, the unweighted least square (ULS) is designed to specifically deal with non-normal data in SEM. However, ULS often yields improper solutions like negative, or boundary estimates of unique variances since it considers measurement errors in observed variables. The disturbance in SEM is reflected in unique variance, which is random error due to unreliability or measurement error and reliable variation in the item that indicates unknown latent causes. Consequently, this can generate bias in indicator loadings estimates. As an action to disentangle this issue, the present study proposes the implementation of regularization parameters by adding small positive values to the variance-covariance matrix. The ratio of bias to variance in a model can be improved to obtain the best estimation performance. Pro-Active Monte Carlo simulation was used to produce multivariate non-normal data with designated sample sizes and population characteristics. The data were analyzed using R Programming Environment by employing “psych”, “MASS”, “foreign”, “mvrnonnorm”, “purr”, and “semTools” packages with 1000 replications to produce multivariate non-normal data. Next, the “lavaan” package was used for SEM and regularized SEM analyses. The outcome of this study proves the capability of regularized ULS to improve parameter estimation.

How to cite this paper

 Zulkifli, N., Aimran, N & Deni, S. (2023). The performance of unweighted least squares and regularized unweighted least squares in estimating factor loadings in structural equation modeling.International Journal of Data and Network Science, 7(3), 1017-1024.

Refrences

Afthanorhan, A., Awang, Z., Aimran, N., & Arifin, J. (2021). An Extensive Comparison Between CBSEM and Consistent PLS-SEM On Producing the Estimates of Construct Correlation in Applied Research. In Journal of Physics: Conference Series (Vol. 1874, No. 1, p. 012083). IOP Publishing.
Aimran, A. N., Ahmad, S., Afthanorhan, A., & Awang, Z. (2017). The development of comparative bias index. AIP Conference Proceedings, 1870.
Ainur, A. K., Sayang, M. D., Jannoo, Z., & Yap, B. W. (2017). Sample Size and Non-Normality Effects on Goodness of Fit Measures in Structural Equation Models. Pertanika Journal of Science & Technology, 25(2).
Arruda, E. H., & Bentler, P. M. (2017). A Regularized GLS for Structural Equation Modeling. Structural Equation Modeling, 24(5), 657–665.
Arruda, E. H. (2017). Applications of Regularization to SEM: Shrinking Eigenvalues to Improve Stability of Covariance Matrices. University of California, Los Angeles.
Awang, Z. (2023). SEM Made Simple 2.0: A Gentle Approach to Learning Structural Equation Modeling. MPWS Rich Publication, Bangi.
Bickel, P. J., & Li, B. (2006). Regularization in statistics. TEST: Sociedad de Estadísticae Investigación Operativa, 15, 271-344.
Forero, C. G., Maydeu-Olivares, A., & Gallardo-Pujol, D. (2009). Factor analysis with ordinal indicators: A Monte Carlo study comparing DWLS and ULS estimation. Structural Equation Modeling, 16(4), 625-641.
Henseler, J., & Chin, W. W. (2010). A comparison of approaches for the analysis of interaction effects between latent variables using partial least squares path modeling. Structural equation modeling, 17(1), 82-109.
Jacobucci, R., Brandmaier, A. M., & Kievit, R. A. (2019). A Practical Guide to Variable Selection in Structural Equation Modeling by Using Regularized Multiple-Indicators, Multiple-Causes Models. Advances in Methods and Practices in Psychological Science, 2(1), 55–76.
Jacobucci, R., Grimm, K. J., & McArdle, J. J. (2016). Regularized Structural Equation Modeling. Structural Equation Modeling, 23(4), 555–566.
Jung, S. (2013). Structural equation modeling with small sample sizes using two-stage ridge least-squares estimation. Behavior Research Methods, 45(1), 75–81.
Jung, S., & Takane, Y. (2008). Regularized common factor analysis. New trends in psychometrics, 141-149.
Kline, R. B. (2016). Principles and practice of structural equation modeling. Guilford publications.
McDonald, R. P., & Bollen, K. A. (1990). Structural Equations with Latent Variables. In Journal of the American Statistical Association, 85(412).
Mindrila, D. (2010). Maximum likelihood (ML) and diagonally weighted least squares (DWLS) estimation procedures: A comparison of estimation bias with ordinal and multivariate non-normal data. International Journal of Digital Society, 1(1), 60-66.
Pavlov, G., Shi, D., & Maydeu-Olivares, A. (2020). Chi-square Difference Tests for Comparing Nested Models: An Evaluation with Non-normal Data. Structural Equation Modeling, 27(6), 908–917.
R Core Team. (2018). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing.
Rosseel, Y. (2012). lavaan: An R package for structural equation modeling. Journal of Statistical Software, 48, 1-36.
Schermelleh-Engel, K., Moosbrugger, H., & Müller, H. (2003). Evaluating the fit of structural equation models: Tests of significance and descriptive goodness-of-fit measures. Methods of psychological research online, 8(2), 23-74.
Vale, C. D., & Maurelli, V. A. (1983). Simulating multivariate nonnormal distributions. Psychometrika, 48(3), 465–471.
Yuan, K. H., & Bentler, P. M. (2017). Improving the convergence rate and speed of Fisher- scoring algorithm: Ridge and anti-ridge methods in structural equation modeling. Annals of the Institute of Statistical Mathematics, 69, 1-27.
Yuan, K. H., & Chan, W. (2016). Structural equation modeling with unknown population distributions: Ridge Generalized Least Squares. Structural Equation Modeling: A Multidisciplinary Journal, 23, 163-179.
Zulkifli, R., Aimran, N., Deni, S. M., & Badarisam, F. N. (2022). A comparative study on the performance of maximum likelihood, generalized least square, scale-free least square, partial least square and consistent partial least square estimators in structural equation modeling. International Journal of Data and Network Science, 6(2), 391–400.