Multivariate non-normal distributions and their effects on statistical power and measures of fit in structural equation modeling
Erstveröffentlichung
2023-03-21Authors
Jobst, Lisa Jasmin Désirée
Referee
Moshagen, MortenKlein, Andreas
Stadnitski, Tatjana
Dissertation
Faculties
Fakultät für Ingenieurwissenschaften, Informatik und PsychologieInstitutions
Institut für Psychologie und PädagogikAbstract
The dissertation investigates the effects of multivariate non-normal data on measures of fit and statistical power in structural equation modeling. Different non-normality conditions were generated by means of Monte Carlo simulations considering various estimation methods and corrections to the likelihood-ratio model test statistic. Furthermore, the dissertation provides important insights regarding the simultaneous effect of multivariate non-normality and missing data. The results show that the multivariate distribution has an effect on measures of fit as well as on statistical power in finite samples.
Date created
2022
Cumulative dissertation containing articles
• Jobst, L. J., Bader, M., & Moshagen, M. (2021). A tutorial on assessing statistical power and determining sample size for structural equation models. Psychological Methods. Advance online publication. https://doi.org/10.1037/met0000423
• Jobst, L. J., Auerswald, M., & Moshagen, M. (2021). The effect of latent and error non-normality on measures of fit in structural equation modeling. Educational and Psychological Measurement. Advance online publication. https://doi.org/10.1177/00131644211046201
• Jobst, L. J., Auerswald, M., & Moshagen, M. (2022). The effect of latent and error non-normality on corrections to the test statistic in structural equation modeling. Behavior Research Methods. Advance online publication. https://doi.org/10.3758/s13428-021-01729-9
• Jobst, L. J., Heine, C., Auerswald, M., & Moshagen, M. (2021). Effects of multivariate non-normality and missing data on the root mean square error of approximation. Structural Equation Modeling: A Multidisciplinary Journal, 28(6), 851–858. https://doi.org/10.1080/10705511.2021.1933987
• Jobst, L. J., Auerswald, M., & Moshagen, M. (2021). The effect of latent and error non-normality on measures of fit in structural equation modeling. Educational and Psychological Measurement. Advance online publication. https://doi.org/10.1177/00131644211046201
• Jobst, L. J., Auerswald, M., & Moshagen, M. (2022). The effect of latent and error non-normality on corrections to the test statistic in structural equation modeling. Behavior Research Methods. Advance online publication. https://doi.org/10.3758/s13428-021-01729-9
• Jobst, L. J., Heine, C., Auerswald, M., & Moshagen, M. (2021). Effects of multivariate non-normality and missing data on the root mean square error of approximation. Structural Equation Modeling: A Multidisciplinary Journal, 28(6), 851–858. https://doi.org/10.1080/10705511.2021.1933987
Subject headings
[GND]: Strukturgleichungsmodell | Multivariate Analyse[LCSH]: Structural equation modeling | Multivariate analysis | Statistical hypothesis testing
[Free subject headings]: Non-normal multivariate data | Source of non-normality | Statistical power
[DDC subject group]: DDC 150 / Psychology | DDC 310 / General statistics
Metadata
Show full item recordDOI & citation
Please use this identifier to cite or link to this item: http://dx.doi.org/10.18725/OPARU-47813
Jobst, Lisa Jasmin Désirée (2023): Multivariate non-normal distributions and their effects on statistical power and measures of fit in structural equation modeling. Open Access Repositorium der Universität Ulm und Technischen Hochschule Ulm. Dissertation. http://dx.doi.org/10.18725/OPARU-47813
Citation formatter >