The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
The Performance of ML, GLS, and WLS Estimation in Structural Equation Modeling Under Conditions of Misspecification and Nonnormality
Abstract
This simulation study demonstrates how the choice of estimation method affects indexes of fit and parameter bias for different sample sizes when nested models vary in terms of specification error and the data demonstrate different levels of kurtosis. Using a fully crossed design, data were generated for 11 conditions of peakedness, 3 conditions of misspecification, and 5 different sample sizes. Three estimation methods (maximum likelihood [ML], generalized least squares [GLS], and weighted least squares [WLS]) were compared in terms of overall fit and the discrepancy between estimated parameter values and the true parameter values used to generate the data. Consistent with earlier findings, the results show that ML compared to GLS under conditions of misspecification provides more realistic indexes of overall fit and less biased parameter values for paths that overlap with the true model. However, despite recommendations found in the literature that WLS should be used when data are not normally distributed, we find that WLS under no conditions was preferable to the 2 other estimation procedures in terms of parameter bias and fit. In fact, only for large sample sizes (N = 1,000 and 2,000) and mildly misspecified models did WLS provide estimates and fit indexes close to the ones obtained for ML and GLS. For wrongly specified models WLS tended to give unreliable estimates and over-optimistic values of fit.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
Alternative Ways of Assessing Model Fit
Browne, M. W., & Cudeck, R. (1992) · Sociological Methods & Research · doi:10.1177/0049124192021002005 · Cited by 27,200
Structural Equations with Latent Variables.
Clogg, C. C., & Bollen, K. A. (1991) · Contemporary Sociology · doi:10.2307/2072165 · Cited by 17,442
Structural Equations with Latent Variables
Bollen, K. A. (1989) · Wiley series in probability and statistics · doi:10.1002/9781118619179 · Cited by 17,277
(1993) · Medical Entomology and Zoology · Cited by 7,690
Structural model evaluation and modification: An interval estimation approach
Steiger, J. H. (1990) · Multivariate Behavioral Research · doi:10.1207/s15327906mbr2502_4 · Cited by 7,408
Curran, P. J., West, S. G., & Finch, J. F. (1996) · Psychological Methods · doi:10.1037/1082-989x.1.1.16 · Cited by 5,512
LISREL 7 : a guide to the program and applications
Jöreskog, K. G., & Sörbom, D. (1989) · Medical Entomology and Zoology · Cited by 4,297
Evaluation of goodness-of-fit indices for structural equation models.
Mulaik, S. A., James, L. R., Van Alstine, J., & Bennett, N. (1989) · Psychological Bulletin · doi:10.1037//0033-2909.105.3.430 · Cited by 2,923
Cited by
lavaan : An R Package for Structural Equation Modeling
Rosseel, Y. (2012) · Journal of Statistical Software · doi:10.18637/jss.v048.i02 · Cited by 27,955
When to Use and How to Report the Results of PLS-SEM
Hair, J. F., Risher, J. J., Sarstedt, M., & Ringle, C. M. (2019) · European Business Review · doi:10.1108/ebr-11-2018-0203 · Cited by 27,541
“Scholars have noted that maximum likelihood estimation with CB-SEM is robust against violations of normality (Chou et al., 1991; Olsson et al., 2000), although it may require much larger sample sizes (Boomsma and Hoogland, 2001).”
BackgroundSchermelleh-Engel, K., Moosbrugger, H., & Müller, H. (2003) · Department of Psychology - University of Koblenz-Landau · doi:10.23668/psycharchives.12784 · Cited by 8,975
Partial least squares structural equation modeling
Sarstedt, M., Ringle, C. M., & Hair, J. F. (2017) · Handbook of Market Research · doi:10.1007/978-3-319-05542-8_15-1 · Cited by 3,285
Structural equations modeling: Fit Indices, sample size, and advanced topics
Iacobucci, D. (2010) · Journal of Consumer Psychology · doi:10.1016/j.jcps.2009.09.003 · Cited by 2,263
Partial Least Squares Structural Equation Modeling
Sarstedt, M., Ringle, C. M., & Hair, J. F. (2022) · Handbook of Market Research · doi:10.1007/978-3-319-57413-4_15 · Cited by 1,483
Ryu, K., Lee, H., & Gon Kim, W. (2012) · International Journal of Contemporary Hospitality Management · doi:10.1108/09596111211206141 · Cited by 1,254
Partial Least Squares Structural Equation Modeling
Sarstedt, M., Ringle, C. M., & Hair, J. F. (2021) · Handbook of Market Research · doi:10.1007/978-3-319-05542-8_15-2 · Cited by 876
A Comparison of Diagonal Weighted Least Squares Robust Estimation Techniques for Ordinal Data
DiStefano, C., & Morgan, G. B. (2014) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2014.915373 · Cited by 705
The invisible addiction: Cell-phone activities and addiction among male and female college students
Roberts, J., Yaya, L., & Manolis, C. (2014) · Journal of Behavioral Addictions · doi:10.1556/jba.3.2014.015 · Cited by 711
Hsu, C.-L., & Lin, J. C.-C. (2015) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2014.11.003 · Cited by 662
“Moreover, under conditions of misspecification, ML provides more realistic indices of overall fit and less biased parameter values for paths that overlap with the true model as compared to GLS (Olsson et al. 2000).”
MethodInfluentialPerceptual measures of performance: fact or fiction?
Ketokivi, M. A., & Schroeder, R. G. (2004) · Journal of Operations Management · doi:10.1016/j.jom.2002.07.001 · Cited by 604
Kim, S., Vandenabeele, W., Wright, B. E., Andersen, L. B., Cerase, F. P., Christensen, R. K., Desmarais, C., Koumenta, M., Leisink, P., Liu, B., et al. (2013) · Journal of Public Administration Research and Theory · doi:10.1093/jopart/mus027 · Cited by 587
Developmental cognitive neuroscience using latent change score models: A tutorial and applications
Kievit, R. A., Brandmaier, A. M., Ziegler, G., van Harmelen, A.-L., de Mooij, S. M. M., Moutoussis, M., Goodyer, I. M., Bullmore, E., Jones, P. B., Fonagy, P., et al. (2018) · Developmental Cognitive Neuroscience · doi:10.1016/j.dcn.2017.11.007 · Cited by 516
Recent Advances in Causal Modeling Methods for Organizational and Management Research
Williams, L. (2003) · Journal of Management · doi:10.1016/s0149-2063(03)00084-9 · Cited by 490
Factorial and Construct Validity of the Italian Positive and Negative Affect Schedule (PANAS)
Terracciano, A., McCrae, R. R., & Costa, P. T., Jr. (2003) · European Journal of Psychological Assessment · doi:10.1027//1015-5759.19.2.131 · Cited by 476
The role of atmospheric cues in online impulse-buying behavior.
Floh, A., & Madlberger, M. (2013) · Electronic Commerce Research and Applications · doi:10.1016/j.elerap.2013.06.001 · Cited by 460
Hsu, C.-L., & Lin, J. C.-C. (2016) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2016.04.012 · Cited by 439
Gross, M. J., & Brown, G. (2008) · Tourism Management · doi:10.1016/j.tourman.2008.02.009 · Cited by 433
Hsu, C.-L., & Lin, J. C.-C. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2016.04.023 · Cited by 413
Vamvaka, V., Stoforos, C., Palaskas, T., & Botsaris, C. (2020) · Journal of Innovation and Entrepreneurship · doi:10.1186/s13731-020-0112-0 · Cited by 392
de Winter, J. C. F., & Dodou, D. (2012) · Journal of Applied Statistics · doi:10.1080/02664763.2011.610445 · Cited by 385
Using Confirmatory Factor Analysis for Construct Validation: An Empirical Review
DiStefano, C., & Hess, B. (2005) · Journal of Psychoeducational Assessment · doi:10.1177/073428290502300303 · Cited by 384
Bandalos, D. L. (2014) · Structural Equation Modeling: A Multidisciplinary Journal · doi:10.1080/10705511.2014.859510 · Cited by 381
“As these researchers stated, “It [the WLS estimator] not only allows peaked data, but actually appears to reward the researcher for using nonnormal data” (Olsson et al., 2000, p. 578) by yielding values of fit indexes for misspecified models that became more optimal as nonnormality increased.”
BackgroundResultRobitzsch, A. (2020) · Frontiers in Education · doi:10.3389/feduc.2020.589965 · Cited by 379
Beyond top‐down and bottom‐up work redesign: Customizing job content through idiosyncratic deals
Hornung, S., Rousseau, D. M., Glaser, J., Angerer, P., & Weigl, M. (2010) · Journal of Organizational Behavior · doi:10.1002/job.625 · Cited by 372
Balducci, C., Fraccaroli, F., & Schaufeli, W. B. (2010) · European Journal of Psychological Assessment · doi:10.1027/1015-5759/a000020 · Cited by 353
Usakli, A., & Kucukergin, K. G. (2018) · International Journal of Contemporary Hospitality Management · doi:10.1108/ijchm-11-2017-0753 · Cited by 323
Karwowski, M., Lebuda, I., Wisniewska, E., & Gralewski, J. (2013) · The Journal of Creative Behavior · doi:10.1002/jocb.32 · Cited by 310
Bryan, C. J., Bryan, A. O., Anestis, M. D., Anestis, J. C., Green, B. A., Etienne, N., Morrow, C. E., & Ray-Sannerud, B. (2016) · Assessment · doi:10.1177/1073191115590855 · Cited by 279
Meier, A., Reinecke, L., & Meltzer, C. E. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2016.06.011 · Cited by 277
Macabasco-O’Connell, A., DeWalt, D. A., Broucksou, K. A., Hawk, V., Baker, D. W., Schillinger, D., Ruo, B., Bibbins-Domingo, K., Holmes, G. M., Erman, B., et al. (2011) · Journal of General Internal Medicine · doi:10.1007/s11606-011-1668-y · Cited by 268
Kelley, K., & Pornprasertmanit, S. (2016) · Psychological Methods · doi:10.1037/a0040086 · Cited by 259
Sideridis, G., Simos, P., Papanicolaou, A., & Fletcher, J. (2014) · Educational and Psychological Measurement · doi:10.1177/0013164414525397 · Cited by 246
“Methods related to SEM have been proposed by Price et al. (2009) making use of Bayesian methods or Chen et al.”
MethodDigitalizing procurement: The impact of data analytics on supply chain performance
Hallikas, J., Immonen, M., & Brax, S. (2021) · Supply Chain Management: An International Journal · doi:10.1108/scm-05-2020-0201 · Cited by 218
Hong, S.-I., Hasche, L., & Bowland, S. (2009) · The Gerontologist · doi:10.1093/geront/gnp006 · Cited by 218
Shen, C.-X., Liu, R.-D., & Wang, D. (2013) · Computers in Human Behavior · doi:10.1016/j.chb.2012.08.004 · Cited by 148
Ali, A. M., Hori, H., Kim, Y., & Kunugi, H. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.799769 · Cited by 122
Dombrowski, S. C., Canivez, G. L., Watkins, M. W., & Alexander Beaujean, A. (2015) · Intelligence · doi:10.1016/j.intell.2015.10.009 · Cited by 105
Conradt, M., Cavanagh, M., Franklin, J., & Rief, W. (2006) · Journal of Psychosomatic Research · doi:10.1016/j.jpsychores.2005.07.003 · Cited by 104
The impact of barriers and benefits of e-procurement on its adoption decision: An empirical analysis
Toktaş-Palut, P., Baylav, E., Teoman, S., & Altunbey, M. (2014) · International Journal of Production Economics · doi:10.1016/j.ijpe.2014.07.017 · Cited by 86
A Factor Analytic Study of the Cross-Cultural Adaptability Inventory
Davis, S. L., & Finney, S. J. (2006) · Educational and Psychological Measurement · doi:10.1177/0013164405278571 · Cited by 80
Lin, J., Klatt, L.-I., McCracken, L. M., & Baumeister, H. (2018) · PAIN · doi:10.1097/j.pain.0000000000001134 · Cited by 76
Xu, K., Shen, G. Q., Liu, G., & Martek, I. (2019) · Sustainability · doi:10.3390/su11020491 · Cited by 64
“Maximum Likelihood (MI) is widely used to achieve more accurate parameter values when the sample size is less than 2000 [57].”
MethodFactor structure and internal consistency of a Swedish version of the pain catastrophizing scale
Kemani, M. K., Grimby‐Ekman, A., Lundgren, J., Sullivan, M., & Lundberg, M. (2019) · Acta Anaesthesiologica Scandinavica · doi:10.1111/aas.13246 · Cited by 43
Faija, C. L., Reeves, D., Heal, C., & Wells, A. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2020.01064 · Cited by 15
“The MCQ-30 item scores demonstrated considerable skew, for which the ML approach has been shown to outperform other methods in overall fit and parameter estimates, including when data is ordinal (Olsson et al., 2000).”
MethodPersuasibility and the Self – Investigating Heterogeneity among Consumers
Koller, M., Floh, A., Zauner, A., & Rusch, T. (2013) · Australasian Marketing Journal · doi:10.1016/j.ausmj.2013.02.004 · Cited by 7
“Following Olsson et al. (2000), we used robust maximum likelihood estimation for further analysis.”
Method
Metadata
- Authors
- Olsson, U. H., Foss, T., Troye, S. V., & Howell, R. D.
- Venue
- Structural Equation Modeling: A Multidisciplinary Journal
- Publisher
- Informa UK Limited
- Published
- 2000-10
- Volume
- 7
- Issue
- 4
- Pages
- 557-595
- ISSN
- 1070-5511 (ISSN-L)
- 1532-8007
- OpenAlex
- W2024218294
- Cited by
- 648
- References
- 31
- FWCI
- 11.71
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.