Investigating the performance of exploratory graph analysis and traditional techniques to identify the number of latent factors: A simulation and tutorial - PubMed
Investigating the performance of exploratory graph analysis and traditional techniques to identify the number of latent factors: A simulation and tutorial
Hudson Golino et al. Psychol Methods. 2020 Jun.
Abstract
Exploratory graph analysis (EGA) is a new technique that was recently proposed within the framework of network psychometrics to estimate the number of factors underlying multivariate data. Unlike other methods, EGA produces a visual guide-network plot-that not only indicates the number of dimensions to retain, but also which items cluster together and their level of association. Although previous studies have found EGA to be superior to traditional methods, they are limited in the conditions considered. These issues are addressed through an extensive simulation study that incorporates a wide range of plausible structures that may be found in practice, including continuous and dichotomous data, and unidimensional and multidimensional structures. Additionally, two new EGA techniques are presented: one that extends EGA to also deal with unidimensional structures, and the other based on the triangulated maximally filtered graph approach (EGAtmfg). Both EGA techniques are compared with 5 widely used factor analytic techniques. Overall, EGA and EGAtmfg are found to perform as well as the most accurate traditional method, parallel analysis, and to produce the best large-sample properties of all the methods evaluated. To facilitate the use and application of EGA, we present a straightforward R tutorial on how to apply and interpret EGA, using scores from a well-known psychological instrument: the Marlowe-Crowne Social Desirability Scale. (PsycInfo Database Record (c) 2020 APA, all rights reserved).
Figures

Effect Size - Multidimensional Structures

Simulated five factor model with loadings of .70 and 5,000 observations with interfactor correlation of .70 (top) and zero (bottom). The left side shows the population correlation matrix plotted as a network of zero-order correlations, while the left side shows the EGA estimation of the population correlation matrix. Nodes represent variables, edges represent correlations, and the node colors indicates the simulated factors.

New EGA algorithm for unidimensional and multidimensional structures

A depiction of a network tetrahedron (left) and a tetrahedron drawn so that no edges are crossing (right)

A depiction of how TMFG constructs a network. Starting with the tetrahedron, the node with the largest sum to three other nodes in the network is added (top left). This process continues until all nodes are included in the network.

Accuracy per sample size, factor loadings and number of variables (NVAR) for unidimensional factors with continuous (A) and dichotomous (B) data.

Mean Absolute Error (MAE) per sample size, factor loadings and number of variables (NVAR) for unidimensional factors with continuous (A) and dichotomous (B) data.

Accuracy per sample size, factor loadings and number of variables (NVAR) for multidimensional factors with continuous (A) and dichotomous (B) data.

Boxplot comparing the percentage of correct estimates between EGA, PApaf and PApca in multidimensional structures with dichotomous data by interfactor correlation and factorloadings.

Mean Absolute Error (MAE) per sample size, factor loadings and interfactor correlation for unidimensional factors with continuous (A) and dichotomous (B) data.

EGA dimesional structure of the Social Desirability Scale.
Similar articles
-
Garcia-Pardina A, Abad FJ, Christensen AP, Golino H, Garrido LE. Garcia-Pardina A, et al. Behav Res Methods. 2024 Sep;56(6):6179-6197. doi: 10.3758/s13428-024-02348-w. Epub 2024 Feb 20. Behav Res Methods. 2024. PMID: 38379114
-
Exploring Estimation Procedures for Reducing Dimensionality in Psychological Network Modeling.
Shi D, Christensen AP, Day EA, Golino HF, Garrido LE. Shi D, et al. Multivariate Behav Res. 2024 Sep 16:1-27. doi: 10.1080/00273171.2024.2395941. Online ahead of print. Multivariate Behav Res. 2024. PMID: 39279587
-
Brandenburg N, Papenberg M. Brandenburg N, et al. Psychol Methods. 2024 Feb;29(1):21-47. doi: 10.1037/met0000527. Epub 2022 Aug 4. Psychol Methods. 2024. PMID: 35925729
-
Marsh HW, Morin AJ, Parker PD, Kaur G. Marsh HW, et al. Annu Rev Clin Psychol. 2014;10:85-110. doi: 10.1146/annurev-clinpsy-032813-153700. Epub 2013 Dec 2. Annu Rev Clin Psychol. 2014. PMID: 24313568 Review.
-
Brothers A, Chui H, Diehl M. Brothers A, et al. Gerontologist. 2014 Dec;54(6):1075-88. doi: 10.1093/geront/gnu076. Epub 2014 Jul 25. Gerontologist. 2014. PMID: 25063938 Free PMC article. Review.
Cited by
-
Rozgonjuk D, Sindermann C, Elhai JD, Christensen AP, Montag C. Rozgonjuk D, et al. J Behav Addict. 2020 Aug 13;9(3):686-697. doi: 10.1556/2006.2020.00036. Print 2020 Oct 12. J Behav Addict. 2020. PMID: 32986606 Free PMC article.
-
Kozlowski MB, Antovich D, Karalunas SL, Nigg JT. Kozlowski MB, et al. Psychol Assess. 2022 Dec;34(12):1081-1092. doi: 10.1037/pas0001180. Epub 2022 Sep 29. Psychol Assess. 2022. PMID: 36174168 Free PMC article.
-
Sheykhangafshe FB, Farahani H, Watson P. Sheykhangafshe FB, et al. Front Psychol. 2024 Jul 3;15:1400340. doi: 10.3389/fpsyg.2024.1400340. eCollection 2024. Front Psychol. 2024. PMID: 39021647 Free PMC article.
-
Dal Santo F, García-Portilla MP, Fernández-Egea E, González-Blanco L, Sáiz PA, Giordano GM, Galderisi S, Bobes J. Dal Santo F, et al. Schizophrenia (Heidelb). 2024 Sep 30;10(1):81. doi: 10.1038/s41537-024-00499-5. Schizophrenia (Heidelb). 2024. PMID: 39349504 Free PMC article.
-
Pellegrini V. Pellegrini V. PLoS One. 2023 Jan 17;18(1):e0280285. doi: 10.1371/journal.pone.0280285. eCollection 2023. PLoS One. 2023. PMID: 36649283 Free PMC article.
References
-
- Anderson H, T.W. & Rubin. (1958). Statistical inference in factor analysis. In Proceedings of the 3rd berkeley symposium on mathematics, statistics, and probability (Vol. 5, pp. 111–150).
-
- Aust F, & Barth M (2018). papaja: Create APA manuscripts with R Markdown. Retrieved from https://github.com/crsh/papaja
-
- Barfuss W, Massara GP, Di Matteo T, & Aste T (2016). Parsimonious modeling with information filtering networks. Physical Review E, 94(6), 062306. - PubMed
-
- Beierl B, E. T. (2018). Is that measure really one-dimensional? Nuisance parameters can mask severe model misspecification when assessing factorial validity. Methodology, 14(4), 188–196.