In applied research across education, the social and behavioral sciences, and medicine, path models frequently incorporate both continuous and ordinal manifest variables to predict binary outcomes. This study employs Monte Carlo simulations to evaluate six estimators: robust maximum likelihood with probit and logit links (MLR-probit, MLR-logit), mean- and variance-adjusted weighted and unweighted least squares (WLSMV, ULSMV), and Bayesian methods with noninformative and weakly informative priors (Bayes-NI, Bayes-WI). Across various sample sizes, variable scales, and effect sizes, results show that WLSMV and Bayes-WI consistently achieve low bias and RMSE, particularly in small samples or when mediators have few categories. By contrast, categorical MLR approaches tended to yield unstable estimates for modest effects. These findings offer practical guidance for selecting estimators in mixed-scale path analyses and underscore their implications for robust inference.
BaronR. M.KennyD. A. (1986). The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51(6), 1173–1182.
3.
BentlerP. M. (1990). Comparative fit indexes in structural models. Psychological Bulletin, 107(2), 238–246.
4.
BentlerP. M. (1995). Eqs structural equations program manual. Multivariate Software.
5.
BíróÉ.VinczeF.MátyásG.KósaK. (2021). Recursive path model for health literacy: The effect of social support and geographical residence. Frontiers in Public Health, 9, 724995.
6.
BollenK. A. (1987). Total, direct, and indirect effects in structural equation models. Sociological Methodology, 17, 37–69.
7.
BollenK. A. (1989). Structural equations with latent variables. Wiley.
8.
BrowneM. W. (1984). Asymptotically distribution-free methods for the analysis of covariance structures. British Journal of Mathematical and Statistical Psychology, 37(1), 62–83.
9.
ChanM.-k.SharkeyJ. D.LawrieS. I.ArchD. A.Nylund-GibsonK. (2021). Elementary school teacher well-being and supportive measures amid covid-19: An exploratory study. School Psychology, 36(6), 533–545.
10.
CohenJ. (1988). Statistical power analysis for the behavioral sciences. Lawrence Erlbaum.
11.
ColdwellM. (2017). Exploring the influence of professional development on teacher careers: A path model approach. Teaching and Teacher Education, 61, 189–198.
12.
CurranP. J.WestS. G.FinchJ. F. (1996). The robustness of test statistics to nonnormality and specification error in confirmatory factor analysis. Psychological Methods, 1(1), 16–29.
13.
DepaoliS. (2014). The impact of inaccurate “informative” priors for growth parameters in Bayesian growth mixture modeling. Structural Equation Modeling: A Multidisciplinary Journal, 21(2), 239–252.
14.
EdehE.LiangX.CaoC. (2025). Probing beyond: The impact of model size and prior informativeness on Bayesian sem fit indices. Behavior Research Methods, 57(4), 1–25.
15.
FinchW. H.MillerJ. (2019). The use of incorrect informative priors in the estimation of mimic model parameters with small sample sizes. Structural Equation Modeling: A Multidisciplinary Journal, 26(4), 497–508.
16.
FinneyS. J.DiStefanoC. (2013). Non-normal and categorical data in structural equation modeling. In HancockG. R.MuellerR. O. (Eds.), Structural equation modeling: A second course (pp. 439–492). Information Age Publishing.
17.
FloraD. B.CurranP. J. (2004). An empirical evaluation of alternative methods of estimation for confirmatory factor analysis with ordinal data. Psychological Methods, 9(4), 466–491.
18.
FoldnesN.GrønnebergS. (2017). The asymptotic covariance matrix and its use in simulation studies. Structural Equation Modeling: A Multidisciplinary Journal, 24(6), 881–896.
19.
FoldnesN.GrønnebergS. (2019). On identification and non-normal simulation in ordinal covariance and item response models. Psychometrika, 84(4), 1000–1017.
20.
[Record #1377 is using a reference type undefined in this output style.]
21.
FoldnesN.GrønnebergS. (2020). Pernicious polychorics: The impact and detection of underlying non-normality. Structural Equation Modeling: A Multidisciplinary Journal, 27(4), 525–543.
22.
FoldnesN.GrønnebergS. (2022). The sensitivity of structural equation modeling with ordinal data to underlying non-normality and observed distributional forms. Psychological Methods, 27(4), 541–567.
23.
GelmanA.MengX. L.SternH. (1996). Posterior predictive assessment of model fitness via realized discrepancies. Statistica Sinica, 6(4), 733–807.
24.
GelmanA.RubinD. B. (1992). Inference from iterative simulation using multiple sequences. Statistical Science, 7(4), 457–472.
25.
GemanS.GemanD. (1984). Stochastic relaxation, gibbs distributions, and the Bayesian restoration of images. IEE Transactions on Pattern Analysis and Machine Intelligence, 6(6), 721–741.
26.
GrønnebergS.FoldnesN. (2019). A problem with discretizing Vale–Maurelli in simulation studies. Psychometrika, 84(2), 554–561.
27.
GuidryJ. P.CarlyleK. E.PerrinP. B.LaRoseJ. G.RyanM.MessnerM. (2019). A path model of psychosocial constructs predicting future Zika vaccine uptake intent. Vaccine, 37(36), 5233–5241.
28.
HanS.EumK.KangH. S.KarstenK. (2022). Factors influencing academic self-efficacy among nursing students during covid-19: A path analysis. Journal of Transcultural Nursing, 33(2), 239–245.
29.
HoltmannJ.KochT.LochnerK.EidM. (2016). A comparison of ML, WLSMV, and Bayesian methods for multilevel structural equation models in small samples: A simulation study. Multivariate Behavioral Research, 51(5), 661–680.
30.
HuangY.-M.ShiyanbolaO. O.ChanH.-Y. (2018). A path model linking health literacy, medication self-efficacy, medication adherence, and glycemic control. Patient Education and Counseling, 101(11), 1906–1913.
31.
HuberP. J. (1967, June21–July18). The behavior of maximum likelihood estimates under nonstandard conditions [Conference session]. Fifth Berkeley symposium on mathematical statistics and probability, volume 1: Statistics, pp. 221–233.
32.
JobstL. J.AuerswaldM.MoshagenM. (2022). The effect of latent and error non-normality on corrections to the test statistic in structural equation modeling. Behavior Research Methods, 54(5), 2351–2363.
KlauthB. (2023). Evaluating the performance of estimators in SEM and IRT with ordinal variables. Western Michigan University.
35.
LaiE. Y.ShihS.HuangY. T.WangS. (2020, May15). A mediation analysis for a nonrare dichotomous outcome with sequentially ordered multiple mediators. Statistics in Medicine, 39(10), 1415–1428. https://doi.org/10.1002/sim.8485
36.
LeeS. Y. (2007). Bayesian estimation of structural equation models. In LeeS. Y. (Ed.), Structural equation modeling: A Bayesian approach (pp. 67–109). Wiley.
37.
LeiP.-W.ShiverdeckerL. K. (2020). Performance of estimators for confirmatory factor analysis of ordinal variables with missing data. Structural Equation Modeling: A Multidisciplinary Journal, 27(4), 584–601.
38.
LiC.-H. (2016). The performance of ML, DWLS, and ULS estimation with robust corrections in structural equation models with ordinal variables. Psychological Methods, 21(3), 369–387.
39.
LiC.-H. (2021). Statistical estimation of structural equation models with a mixture of continuous and categorical observed variables. Behavior Research Methods, 53(5), 2191–2213.
40.
LiangX.YangY. (2014). An evaluation of WLSMV and Bayesian methods for confirmatory factor analysis with categorical indicators. International Journal of Quantitative Research in Education, 2(1), 17–38.
41.
LiangX.YangY.CaoC. (2020). The performance of ESEM and BSEM in structural equation models with ordinal indicators. Structural Equation Modeling: A Multidisciplinary Journal, 27(6), 874–887. https://doi.org/10.1080/10705511.2020.1716770
42.
LingJ.RobbinsL. B.McCarthyV. L.SpeckB. J. (2015). Psychosocial determinants of physical activity in children attending afterschool programs: A path analysis. Nursing Research, 64(3), 190–199.
43.
MicceriT. (1989). The unicorn, the normal curve, and other improbable creatures. Psychological Bulletin, 105(1), 156–166.
44.
MuthénB. O. (1984). A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators. Psychometrika, 49(1), 115–132.
45.
MuthénB. O.AsparouhovT. (2012). Bayesian structural equation modeling: A more flexible representation of substantive theory. Psychological Methods, 17(3), 313–335.
NguyenT. Q.Webb-VargasY.KoningI. M.StuartE. A. (2016). Causal mediation analysis with a binary outcome and multiple continuous or ordinal mediators: Simulations and application to an alcohol intervention. Structural Equation Modeling: A Multidisciplinary Journal, 23(3), 368–383.
49.
OlssonU. H. (1979). Maximum likelihood estimation of the polychoric correlation coefficient. Psychometrika, 44(4), 443–460.
50.
R Core Team. (2022). R: A language and environment for statistical computing. R foundation for statistical computing, Vienna, Austria. http://www.R-project.org/
51.
RhemtullaM.Brosseau-LiardP. É.SavaleiV. (2012). When can categorical variables be treated as continuous? A comparison of robust continuous and categorical SEM estimation methods under suboptimal conditions. Psychological Methods, 17(3), 354–373.
52.
RosseelY. (2012). Lavaan: An R package for structural equation modeling and more. Journal of Statistical Software, 48(2), 1–36.
53.
SatorraA.BentlerP. M. (2001). A scaled difference chi-square test statistic for moment structure analysis. Psychometrika, 66(4), 507–514.
54.
StageF. K.CarterH. C.NoraA. (2004). Path analysis: An introduction and analysis of a decade of research. The Journal of Educational Research, 98(1), 5–13.
55.
SteigerJ. H.LindJ. C. (1980). Statistically based tests for the number of common factors [Paper presentation]. Annual meeting of the Psychometric Society, Iowa City, IA, United States.
56.
StreinerD. L. (2005). Finding our way: An introduction to path analysis. The Canadian Journal of Psychiatry, 50(2), 115–122.
57.
TuckerL. R.LewisC. (1973). A reliability coefficient for maximum likelihood factor analysis. Psychometrika, 38(1), 1–10.
WhiteH. (1980). A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica: Journal of the Econometric Society, 48(4), 817–838.
60.
WrightS. (1918). On the nature of size factors. Genetics, 3(4), 367–374.
61.
WrightS. (1921). Correlation and causation. Journal of Agricultural Research, 20(7), 557–585.
62.
YangY.LiangX. (2013). Confirmatory factor analysis under violations of distributional and structural assumptions. International Journal of Quantitative Research in Education, 1(1), 61–84.
63.
YuanK. H.BentlerP. M. (2000). Three likelihood-based methods for mean and covariance structure analysis with nonnormal missing data. Sociological Methodology, 30, 165–200.
64.
ZhangT. (2024). Relative performance of MLR, WLSMV, and Bayes estimators: An investigation using confirmatory factor analysis with ordinal data. University of South Carolina.
