S5E20 Local fit…Because Global Fit Measures Suck!


In this week’s episode Greg and Patrick discuss the assessment of global vs. local model fit and they argue that although global measures of fit can be useful, carefully assessing local fit may be of much greater importance in practice. Along the way the also discuss cheap beach house rentals, misplaced sand dunes, Mrs. Lincoln, the child catcher, hushpuppies, cockroach feces, academia as community theater, spikes and smoodges, opening paragraphs, dark and stormy nights, sharp rusty knives, dream teams, DAGs as religion, No Daggity, burly moles, Western Kansas, good bones, and computer defaults.

Related Episodes

  • S4E10: Test Driving Model Identification
  • S3E08: Statistical Degrees of Freedom…An Intimate Stranger
  • S2E24: The Equivalent Models Problem
  • S1E14: Model Fit & The Curse of the Black Pearl
  • S1E06: Model Modification and Whac-a-Mole

Suggested Readings

Chen, F., Curran, P. J., Bollen, K. A., Kirby, J., & Paxton, P. (2008). An empirical evaluation of the use of fixed cutoff points in RMSEA test statistic in structural equation models. Sociological Methods & Research36, 462-494.

Hu, L. T., & Bentler, P. M. (1999). Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives. Structural Equation Modeling: A Multidisciplinary Journal6, 1-55.

Lance, C. E., Beck, S. S., Fan, Y., & Carter, N. T. (2016). A taxonomy of path-related goodness-of-fit indices and recommended criterion values. Psychological Methods, 21, 388–404.

MacCallum, R. (1986). Specification searches in covariance structure modeling. Psychological Bulletin100, 107.

MacCallum, R. C., Roznowski, M., & Necowitz, L. B. (1992). Model modifications in covariance structure analysis: the problem of capitalization on chance. Psychological Bulletin111, 490.

McNeish, D., & Wolf, M. G. (2023). Dynamic fit index cutoffs for confirmatory factor analysis models. Psychological Methods28, 61.

Textor, J., Van der Zander, B., Gilthorpe, M. S., Liśkiewicz, M., & Ellison, G. T. (2016). Robust causal inference using directed acyclic graphs: the R package ‘dagitty’. International journal of epidemiology45, 1887-1894.

Thoemmes, F., Rosseel, Y., & Textor, J. (2018). Local fit evaluation of structural equation models using graphical criteria. Psychological Methods23, 27.



join our
email list

Scroll to Top