Bayesian structural equation modeling: A more flexible representation of substantive theory
The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Abstract
This article proposes a new approach to factor analysis and structural equation modeling using Bayesian analysis. The new approach replaces parameter specifications of exact zeros with approximate zeros based on informative, small-variance priors. It is argued that this produces an analysis that better reflects substantive theories. The proposed Bayesian approach is particularly beneficial in applications where parameters are added to a conventional model such that a nonidentified model is obtained if maximum-likelihood estimation is applied. This approach is useful for measurement aspects of latent variable modeling, such as with confirmatory factor analysis, and the measurement part of structural equation modeling. Two application areas are studied, cross-loadings and residual correlations in confirmatory factor analysis. An example using a full structural equation model is also presented, showing an efficient way to find model misspecification. The approach encompasses 3 elements: model testing using posterior predictive checking, model estimation, and model modification. Monte Carlo simulations and real data are analyzed using Mplus. The real-data analyses use data from Holzinger and Swineford's (1939) classic mental abilities study, Big Five personality factor data from a British survey, and science achievement data from the National Educational Longitudinal Study of 1988.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This traditional approach depends on the unrealistic assumptions of zero cross-loadings [30] and limits the researchers’ ability to investigate cross-loadings and residual covariance parameters [31].”
Citations
Cites
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Alternative Ways of Assessing Model Fit
Browne, M. W., & Cudeck, R. (1992) · Sociological Methods & Research · doi:10.1177/0049124192021002005 · Cited by 27,200 · cited 1×
“BSEM with its adjoining posterior predictive p value model test is similar in spirit to the frequentist conceptualization of close fit (M. W. Browne & Cudeck, 1993).”
ResultInference from iterative simulation using multiple sequences
Gelman, A., & Rubin, D. B. (1992) · Statistical Science · doi:10.1214/ss/1177011136 · Cited by 16,627 · cited 1×
“(A8) (Appendix continues) Convergence is determined using the Gelman–Rubin convergence diagnostic (Gelman & Rubin, 1992; Gelman et al., 2004).”
MethodTesting Structural Equation Models.
Clogg, C. C., Bollen, K. A., & Long, J. S. (1995) · Social Forces · doi:10.2307/2580595 · Cited by 8,211
Markov Chain Monte Carlo in Practice
(1995) · Chapman & Hall/CRC eBooks · doi:10.1201/b14835 · Cited by 7,757
(2010) · Cited by 7,034
Analysis of Incomplete Multivariate Data
Booth, D. E. (2000) · Technometrics · doi:10.1080/00401706.2000.10486013 · Cited by 5,627 · cited 1×
“Schafer (1997) gave a statistical discussion from a missing data and multiple imputation perspective, whereas Enders (2010) gave an applied discussion of these same topics.”
BackgroundIntroduction to Statistical Mediation Analysis
MacKinnon, D. P. (2012) · doi:10.4324/9780203809556 · Cited by 5,618 · cited 1×
“An example is an indirect effect a b in a mediation model (MacKinnon, 2008).”
BackgroundHarman, H. H. (1960) · Cited by 5,148
Exploratory Structural Equation Modeling
Asparouhov, T., & Muthén, B. (2009) · Structural Equation Modeling: A Multidisciplinary Journal · doi:10.1080/10705510903008204 · Cited by 2,665
Self-citation
Cited by
Items 101–200 of 1,001
Essential Validation Criteria for Rigorous Covariance‐Based Structural Equation Modelling
Gaskin, J. E., Lowry, P. B., Rosengren, W., & Fife, P. C. (2025) · Information Systems Journal · doi:10.1111/isj.12598 · Cited by 130
“Bayesian estimation is an alternative approach to handle imbalances and provide richer insights when group sizes vary widely (Muthén and Asparouhov 2012).”
Elsworth, G. R., Beauchamp, A., & Osborne, R. H. (2016) · BMC Health Services Research · doi:10.1186/s12913-016-1754-2 · Cited by 105
Zhang, X., Shi, Y., Li, T., Guan, Y., & Cui, X. (2023) · Information Systems Frontiers · doi:10.1007/s10796-023-10425-2 · Cited by 127
“Following the criterion that a PPP-value around 0.5 indicates an excellent-fitting model, the value of 0.44 implies the good performance of the model (Muthen & Asparouhov, 2012).”
InfluentialOnline news, civic awareness, and engagement in civic and political life
Boulianne, S. (2015) · New Media & Society · doi:10.1177/1461444815616222 · Cited by 128
“The coefficients are deemed credible at these levels as long as the upper and lower boundaries do not include the value of zero (Muthen and Asparouhov, 2012).”
BackgroundMethodInfluentialAldrup, K., Klusmann, U., Lüdtke, O., Göllner, R., & Trautwein, U. (2018) · Journal of Educational Psychology · doi:10.1037/edu0000256 · Cited by 109
Jacobson, N. C., Lord, K. A., & Newman, M. G. (2017) · Journal of Affective Disorders · doi:10.1016/j.jad.2017.01.011 · Cited by 99
Byrne, B. M., & van de Vijver, F. J. R. (2017) · Psicothema · doi:10.7334/psicothema2017.178 · Cited by 117
“In addition, both van de Schoot et al. (2013) and Muthén and Asparouhov (2012) present example applications of BSEM.”
InfluentialA multilevel investigation of predictors and outcomes of shared leadership
Klasmeier, K. N., & Rowold, J. (2020) · Journal of Organizational Behavior · doi:10.1002/job.2477 · Cited by 120
The dark side of creativity: Coworker envy and ostracism as a response to employee creativity
Breidenthal, A. P., Liu, D., Bai, Y., & Mao, Y. (2020) · Organizational Behavior and Human Decision Processes · doi:10.1016/j.obhdp.2020.08.001 · Cited by 119
Maschi, T. M., Viola, D., Morgen, K., & Koskinen, L. (2013) · Journal of Crime and Justice · doi:10.1080/0735648x.2013.808853 · Cited by 107
“A simple path analysis (See Figure 1), an extension of regression modeling using structural equations (see Kline 2010 or Muthén and Asparouhov 2012 for detailed reviews of structural equation modeling theory and practice), will test the directional and theoretical relationship between trauma,…”
MethodGucciardi, D. F., & Jackson, B. (2013) · Journal of science and medicine in sport · doi:10.1016/j.jsams.2013.11.011 · Cited by 119
Falkenström, F., Hatcher, R. L., & Holmqvist, R. (2015) · Assessment · doi:10.1177/1073191114552472 · Cited by 96
“With BSEM usually only one respecification needs to be done (see also B. O. Muthén and Asparouhov, 2012, for more details).”
BackgroundMethodInfluentialCausal mediation analysis for longitudinal data with exogenous exposure
Bind, M., VanderWeele, T. J., Coull, B. A., & Schwartz, J. D. (2015) · Biostatistics · doi:10.1093/biostatistics/kxv029 · Cited by 121
“For instance, Yuan and MacKinnon (2009) introduced Bayesian multilevel models with random intercepts and slopes, Muthen and Asparouhov (2012) proposed a Bayesian Structural Equation Modeling approach, and Nuijten and others (2014) recently proposed a mediation test using Bayes factors to examine…”
When the going gets tough: Mental toughness and its relationship with behavioural perseverance
Gucciardi, D. F., Peeling, P., Ducker, K. J., & DAWSON, B. T. (2014) · Journal of science and medicine in sport · doi:10.1016/j.jsams.2014.12.005 · Cited by 103
Teacher well-being in the classroom: A micro-longitudinal study
Li, P., Mayer, D., & Malmberg, L. (2022) · Teaching and Teacher Education · doi:10.1016/j.tate.2022.103720 · Cited by 114
A Comparison of CFA, ESEM, and BSEM in Test Structure Analysis
Xiao, Y., Liu, H., & Hau, K. (2019) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2018.1562928 · Cited by 103
“A Comparison of CFA, ESEM, and BSEM in Test Structure Analysis Yue Xiao,1 Hongyun Liu,1 and Kit-Tai Hau2 1Beijing Normal University 2The Chinese University of Hong Kong Minor cross-loadings on non-targeted factors are often found in psychological or other instruments.”
BackgroundMethodInfluentialThe handbook of multilevel theory, measurement, and analysis.
(2019) · American Psychological Association eBooks · doi:10.1037/0000115-000 · Cited by 96
Mansolf, M. A., & Reise, S. P. (2016) · Multivariate Behavioral Research · doi:10.1080/00273171.2016.1215898 · Cited by 101
Racial differences in institutional trust and COVID-19 vaccine hesitancy and refusal
Bagasra, A. B., Doan, S. C., & Allen, C. T. (2021) · BMC Public Health · doi:10.1186/s12889-021-12195-5 · Cited by 95
“90, suggest a poor model fit with data [34].”
BackgroundEvaluating Sensitivity of Parameters of Interest to Measurement Invariance in Latent Variable Models
Oberski, D. L. (2013) · Political Analysis · doi:10.1093/pan/mpt014 · Cited by 108
Golay, P., Reverte, I., Rossier, J., Favez, N., & Lecerf, T. (2013) · Psychological Assessment · doi:10.1037/a0030676 · Cited by 94
“The method used here closely draws on the approach described by Muthén and Asparouhov (2012). This paragraph does not provide a detailed overviewed of BSEM estimation.”
MethodYu, S., Deng, Y., Yu, H., & Liu, X. (2018) · Current Psychology · doi:10.1007/s12144-018-0007-4 · Cited by 94
Addressing Methodological Challenges in Culture-Comparative Research
Fischer, R. D., & Poortinga, Y. H. (2018) · Journal of Cross-Cultural Psychology · doi:10.1177/0022022117738086 · Cited by 117
“Thus, Bayesian analysis amounts to an update of prior beliefs in the light of new evidence, using Bayes’s theorem (Muthén & Asparouhov, 2012), whereas the traditional testing of the null hypothesis is neutral on the prior evidence and only relies on the evidence of the data observed in the study at…”
MethodStevenson, B. L., Dvorak, R. D., Kramer, M. P., Peterson, R. S., Dunn, M. E., Leary, A. V., & Pinto, D. A. (2019) · Journal of Abnormal Psychology · doi:10.1037/abn0000472 · Cited by 92
The Comparability of Measurements of Attitudes toward Immigration in the European Social Survey
Davidov, E., Cieciuch, J., Meuleman, B., Schmidt, P., Algesheimer, R., & Hausherr, M. (2015) · Public Opinion Quarterly · doi:10.1093/poq/nfv008 · Cited by 107
Understanding child disadvantage from a social determinants perspective
Goldfeld, S. R., O’Connor, M., Cloney, D., Gray, S. A. O., Redmond, G., Badland, H. M., Williams, K. J., Mensah, F. K., Woolfenden, S. R., Kvalsvig, A., et al. (2017) · Journal of Epidemiology & Community Health · doi:10.1136/jech-2017-209036 · Cited by 91
“30 The optimal model was determined to be that with the PPC estimate closest to zero (ie, the least deviance from data simulated from the theoretical covariance structure) that also did not overlap with the credibility interval of a more parsimonious model.”
BackgroundLacko, D., Čeněk, J., Točík, J., Avsec, A., Đorđević, V., Genc, A., Haka, F., Šakotić-Kurbalija, J., Mohorić, T., Neziri, I., et al. (2022) · Cross-Cultural Research · doi:10.1177/10693971211068971 · Cited by 105
“…(AwC, Marsh et al., 2018), item response theory for DIF identification (IRT; Kim and Yoon, 2011), Bayesian structural equation modeling (BSEM; Muthén and Asparouhov, 2012), exploratory structural equation modeling (ESEM; Asparouhov and Muthén, 2009), multi-group factor analysis alignment…”
MethodUnrestricted factor analysis: A powerful alternative to confirmatory factor analysis
Steenkamp, J. E. M., & Maydeu‐Olivares, A. (2022) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-022-00888-1 · Cited by 98
“Some research has started to compare the performance of Bayesian Structural Equation Modeling (BSEM: Muthén & Asparouhov, 2012) with SEM and ESEM (e.g., Guo et al., 2019) but much more research is needed before we know under which conditions a frequentist versus a Bayesian approach is preferable.”
BackgroundKroencke, L., Harari, G. M., Back, M. D., & Wagner, J. (2023) · Journal of Personality and Social Psychology · doi:10.1037/pspp0000422 · Cited by 105
R-squared change in structural equation models with latent variables and missing data
Hayes, T. (2021) · Behavior Research Methods · doi:10.3758/s13428-020-01532-y · Cited by 92
An introduction to using Bayesian linear regression with clinical data
Baldwin, S. A., & Larson, M. J. (2017) · Behaviour Research and Therapy · doi:10.1016/j.brat.2016.12.016 · Cited by 96
de Beer, L. T., & Bianchi, R. (2019) · European Journal of Psychological Assessment · doi:10.1027/1015-5759/a000392 · Cited by 76
Jensen, S. N., Ivarsson, A., Fallby, J., Dankers, S., & Elbe, A. (2018) · Psychology of sport and exercise · doi:10.1016/j.psychsport.2018.02.008 · Cited by 88
McMahon, T. P., & Naragon‐Gainey, K. (2018) · Clinical Psychological Science · doi:10.1177/2167702618807408 · Cited by 90
Can we improve how we screen applicants for initial teacher education?
Klassen, R. M., Kim, L. E., Rushby, J. V., & Bardach, L. (2019) · Teaching and Teacher Education · doi:10.1016/j.tate.2019.102949 · Cited by 94
Resilience and Vulnerability to the Psychological Harm From Flooding: The Role of Social Cohesion
Greene, G., Paranjothy, S., & Palmer, S. R. (2015) · American Journal of Public Health · doi:10.2105/ajph.2015.302709 · Cited by 84
Keech, J. J., Cole, K., Hagger, M. S., & Hamilton, K. (2020) · Psychology and Health · doi:10.1080/08870446.2020.1743841 · Cited by 93
Multiple Group Alignment for Exploratory and Structural Equation Models
Asparouhov, T., & Muthén, B. (2022) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2022.2127100 · Cited by 84
Self-citationLeón, J., Medina-Garrido, E., & Alonso, J. L. N. (2017) · Frontiers in Psychology · doi:10.3389/fpsyg.2017.00895 · Cited by 90
“Therefore, to purify the scale (Hair et al., 2010, p. 666), we relied on information from parallel analysis (Horn, 1965; Hayton et al., 2004), exploratory structural equation modeling (ESEM; Asparouhov and Muthén, 2009), and Bayesian structural equation modeling (BSEM; Muthén and Asparouhov, 2012).”
MethodSchmiege, S. J., Masyn, K. E., & Bryan, A. D. (2017) · Organizational Research Methods · doi:10.1177/1094428117747689 · Cited by 83
“Although these models did not converge in our example, we suspect we might have encountered greater success had we approximated the equivalence constraints using Bayesian methods (e.g., B. O. Muthén & Asparouhov, 2012).”
MethodSchwarz, G., Newman, A., Yu, J., & Michaels, V. (2021) · The International Journal of Human Resource Management · doi:10.1080/09585192.2021.1962388 · Cited by 92
“Therefore, a 1-1-1 mediation model with a Level-2 moderator was specified using robust maximum likelihood (MLR) estimation (Muthén & Asparouhov, 2012).”
MethodLühr, M., Pavlova, M. K., & Luhmann, M. (2021) · Journal of Happiness Studies · doi:10.1007/s10902-021-00480-4 · Cited by 85
“We used Bayesian estimation with noninformative priors because maximum likelihood estimation was computationally infeasible with our large sample size (Muthén & Asparouhov, 2012).”
MethodDavidov, E., Muthén, B., & Schmidt, P. (2018) · Sociological Methods & Research · doi:10.1177/0049124118789708 · Cited by 85
“…field of multiple-group alignment optimization (Asparouhov and Muthén 2013) using a component loss function (Jennrich 2006) and Bayesian statistics (Muthén and Asparouhov 2012; van der Schoot et al. 2013) provide new tools for assessing MI and imposing exact or more relaxed (approximate) forms…”
MethodSelf-citationZercher, F., Schmidt, P., Cieciuch, J., & Davidov, E. (2015) · Frontiers in Psychology · doi:10.3389/fpsyg.2015.00733 · Cited by 73
“According to Muthén and Asparouhov (2012) and van de Schoot et al. (2013), the CI should contain zero.”
BackgroundMethodInfluentialAn alternative to post hoc model modification in confirmatory factor analysis: The Bayesian lasso.
Pan, J., Ip, E. H., & Dubé, L. (2017) · Psychological Methods · doi:10.1037/met0000112 · Cited by 82
“As discussed in Muthén and Asparouhov (2012), the PP p-value is akin to a model fit index.”
InfluentialStatistical power of latent growth curve models to detect quadratic growth
Diallo, T. M. O., Morin, A. J. S., & Parker, P. D. (2013) · Behavior Research Methods · doi:10.3758/s13428-013-0395-1 · Cited by 90
Baldwin, S. A., Fellingham, G. W., & Baldwin, A. S. (2016) · Health Psychology · doi:10.1037/hea0000292 · Cited by 82
Do People Know What They’re Like in the Moment?
Sun, J., & Vazire, S. (2019) · Psychological Science · doi:10.1177/0956797618818476 · Cited by 87
“Because of the computational demands of these models, we used the Bayes estimator in Mplus (B. O. Muthén & Asparouhov, 2012), with the default set of diffuse (i.e., noninformative) priors.”
MethodTofighi, D., & Kelley, K. (2019) · Multivariate Behavioral Research · doi:10.1080/00273171.2019.1618545 · Cited by 85
“These methods include two variations of Bayesian credible interval (Muth en & Asparouhov, 2012; Yuan & MacKinnon, 2009), one with flat priors (Bayes-Flat; noninformative, uninformative) and one with weakly informative (Bayes-Weak) priors for regression coefficients (note that this is the default…”
MethodPensgaard, A. M., Ivarsson, A., Nilstad, A., Solstad, B. E., & Steffen, K. (2018) · BMJ Open Sport & Exercise Medicine · doi:10.1136/bmjsem-2017-000317 · Cited by 79
“A potential scale reduction factor around 1 was considered as evidence of convergence.(31) Model fit of the models was assessed using the posterior predictive P value and the 95% CI.”
MethodGao, H., Tian, H., Zhang, Z., & Xia, X. (2022) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2022.153288 · Cited by 83
Barnett, L. M., Mazzoli, E., Bowe, S. J., Lander, N., & Salmon, J. (2022) · Psychology of sport and exercise · doi:10.1016/j.psychsport.2022.102164 · Cited by 83
Effects of supervisor bottom-line mentality on subordinate unethical pro-organizational behavior
Zhang, Y., He, B., Huang, Q., & Xie, J. (2020) · Journal of Managerial Psychology · doi:10.1108/jmp-11-2018-0492 · Cited by 85
Fu, Y., Wen, Z., & Wang, Y. (2021) · Educational and Psychological Measurement · doi:10.1177/00131644211008953 · Cited by 89
“One of the advantages of ESEM is that small cross-loadings do not need to be eliminated from the model (Muthén & Asparouhov, 2012).”
BackgroundCho, S., & Kang, H. (2016) · Environment and Behavior · doi:10.1177/0013916516631801 · Cited by 85
“To overcome these computational problems, recent studies have suggested that Bayesian procedures offer a more flexible and efficient alternative for complex multilevel models (Depaoli & Clifton, 2015; Lee, 2007; Marsh et al., 2009; Muthén & Asparouhov, 2012).”
BackgroundDembo, R., Briones-Robinson, R., Barrett, K. L. V., Winters, K. C., Schmeidler, J., Ungaro, R. A., Karas, L. M., Belenko, S. R., & Gulledge, L. M. (2011) · Journal of Emotional and Behavioral Disorders · doi:10.1177/1063426611421006 · Cited by 76
Residual Structural Equation Models
Asparouhov, T., & Muthén, B. (2022) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2022.2074422 · Cited by 79
“The second approach is given in Figure 10, where the factors ft correspond to the measurement errors eit and the hat variables Ŷt correspond to factors fit in equation (27).”
BackgroundSelf-citationPotential‐based achievement goals
Elliot, A., Murayama, K., Kobeisy, A., & Lichtenfeld, S. (2015) · British Journal of Educational Psychology · doi:10.1111/bjep.12051 · Cited by 73
“Because the approach-avoidance model had a negative variance when tested with the maximum-likelihood approach, we also conducted a Bayesian factor analysis to supplement the initial analysis (Muthen & Asparouhov, 2012).”
Papastathopoulos, A., Ahmad, S. Z., Sabri, N. A., & Kaminakis, K. (2019) · Journal of Travel Research · doi:10.1177/0047287519874131 · Cited by 78
“B. Muthén and Asparouhov (2012) demonstrated an approach to model specification and estimation in SEM by focusing on long-standing issues and limitations in conventional SEM, providing significant benefits for empirical application.”
BackgroundSmit, R., Dober, H., Hess, K., Bachmann, P., & Birri, T. (2022) · Research in Mathematics Education · doi:10.1080/14794802.2022.2062780 · Cited by 84
“Bayesian analysis is an attractive alterna-tivetomaximumlikelihoodestimation,especiallyforsmallsamplesizesandmulti-levelvari-able models with random e ff ects (Muthén, 2010; Muthén & Asparouhov, 2012).”
MethodSingle-Level and Multilevel Mediation Analysis
Tofighi, D., & Thoemmes, F. J. (2013) · The Journal of Early Adolescence · doi:10.1177/0272431613511331 · Cited by 88
“For Mplus implementation of the Bayesian approach, see B. O. Muthén and Asparouhov (2012).”
MethodCunningham, N. R., Lynch-Jordan, A. M., Barnett, K. A., Peugh, J., Sil, S., Goldschneider, K. R., & Kashikar‐Zuck, S. (2014) · Journal of Pediatric Gastroenterology and Nutrition · doi:10.1097/mpg.0000000000000529 · Cited by 80
“20 (Muthén & Muthén, Los Angeles, CA) for correlational analysis and for constructing mediation models (32).”
BackgroundThe Effect of Customer Empowerment on Adherence to Expert Advice
Camacho, N., de Jong, M., & Stremersch, S. (2014) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2014.03.004 · Cited by 86
Socially Desirable Responding: Enhancement and Denial in 20 Countries
He, J., van de Vijver, F. J. R., Espinosa, A. D. C. D., Abubakar, A. A., Dimitrova, R., Adams, B. G., Aydinli, A., Atitsogbe, K. A., Alonso‐Arbiol, I., Bobowik, M., et al. (2014) · Cross-Cultural Research · doi:10.1177/1069397114552781 · Cited by 77
“…constraints in multigroup confirmatory factor analysis (i.e., invariance of loadings and intercepts) may be overly restrictive and that we need to allow for psychologically inconsequential variation in these parameters, as done in Bayesian Structural Equation Modeling (Muthen & Asparouhov, 2012).”
Forms and Functions of Aggression in Early Childhood
Evans, S. C., Frazer, A. L., Blossom, J. B., & Fite, P. J. (2018) · Journal of Clinical Child & Adolescent Psychology · doi:10.1080/15374416.2018.1485104 · Cited by 76
“…estimation utilizes the Markov Chain Monte Carlo algorithm to sequentially estimate posterior values accounting for each preceding estimate until changes are ignorable, producing estimates similar to maximum likelihood robust estimation (MLR; Muthén & Asparouhov, 2012; Zyphur & Oswald, 2015).”
BackgroundMethodInvariance analyses in large-scale studies
van de Vijver, F. J. R., Avvisati, F., Davidov, E., Eid, M., Fox, J., Donné, N. L., Lek, K., Meuleman, B., Paccagnella, M., & van de Schoot, R. (2019) · OECD education working papers · doi:10.1787/254738dd-en · Cited by 90
Zitzmann, S., Lüdtke, O., Robitzsch, A., & Hecht, M. (2020) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2020.1752216 · Cited by 73
“…scholars have pointed out the potential of Bayesian approaches for estimating latent variable models; for example, in terms of greater flexibility in modeling (e.g., Lüdtke et al., 2013; Muthén & Asparouhov, 2012) or fewer estimation problems (e.g., Depaoli & Clifton, 2015; Hox et al., 2012).”
BackgroundSmith, D., Harvey, P. W., Lawn, S., Harris, M., & Battersby, M. (2016) · Quality of Life Research · doi:10.1007/s11136-016-1368-5 · Cited by 75
“Also, whilst early studies have suggested that departures from the multivariate normal assumption do not appear to have a major effect on the p value, further research is still required [46].”
BackgroundMethodInfluentialRevised scoring and improved reliability for the Communication Patterns Questionnaire.
Crenshaw, A. O., Christensen, A., Baucom, D. H., Epstein, N. B., & Baucom, B. (2016) · Psychological Assessment · doi:10.1037/pas0000385 · Cited by 73
“However, the posterior predictive p does appear sensitive to sample size, though the extent of its sensitivity to sample size does not yet appear fully resolved (see B. Muthén & Asparouhov, 2012).”
InfluentialHatcher, R. L., Lindqvist, K., & Falkenström, F. (2020) · Psychotherapy Research · doi:10.1080/10503307.2019.1677964 · Cited by 72
“Using Markov Chain Monte Carlo estimation (a simulation-based technique), Muthén and Asparouhov (2012) showed that it is possible to estimate residual covariances and cross-loadings using zero-mean, small variance “priors” (for more information, see online Supplemental Material).”
MethodTwo-Level Dynamic Structural Equation Models with Small Samples
McNeish, D. (2019) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2019.1578657 · Cited by 78
“With maximum likelihood estimation, models with many random effects can make estimation quite difficult or even impossible given the use of the joint distribution (Asparouhov et al., 2018; Muthén & Asparouhov, 2012).”
BackgroundMethodRajbhandari, S., Devkota, N., Khanal, G., Mahato, S., & Paudel, U. R. (2022) · Heliyon · doi:10.1016/j.heliyon.2022.e08919 · Cited by 92
Niven, A. G., & Markland, D. A. (2015) · Psychology of sport and exercise · doi:10.1016/j.psychsport.2015.11.004 · Cited by 84
“Finally, for comparison purposes, we briefly report the results of ML-CFA analyses using the robust ML estimator and with exact zero cross-loadings and correlated residuals centred around zero (Muthén & Asparouhov, 2012).”
InfluentialScherer, R., Jansen, M., Nilsen, T., Areepattamannil, S., & Marsh, H. W. (2016) · PLoS ONE · doi:10.1371/journal.pone.0150829 · Cited by 84
“Another reason for this lack of comparability may lie in too strict assumptions on item-factor links that neglected potential overlaps between the factors of teachers’ self-efficacy [16].”
BackgroundMethodInfluentialTamminen, K. A., Gaudreau, P., McEwen, C. E., & Crocker, P. R. E. (2016) · Journal of Sport and Exercise Psychology · doi:10.1123/jsep.2015-0189 · Cited by 75
“Model convergence was closely followed using the potential scale reduction convergence criteria (PSR) with values lower than 1.10 taken as the indicator that convergence has been obtained (Muthén & Asparouhov, 2012).”
InfluentialPrem, R., Scheel, T., Weigelt, O., Hoffmann, K., & Korunka, C. (2018) · Frontiers in Psychology · doi:10.3389/fpsyg.2018.01087 · Cited by 95
Cross-cultural comparability of noncognitive constructs in TIMSS and PISA
He, J., Barrera-Pedemonte, F., & Buchholz, J. (2018) · Assessment in Education Principles Policy and Practice · doi:10.1080/0969594x.2018.1469467 · Cited by 80
“…strictness in parameter constraints to seek partial invariance (Byrne & van de Vijver, 2010) or approximate invariance (Asparouhov & Muthén, 2014; Muthén & Asparouhov, 2012) to tolerate trivial differences, Argentina (CAB) AustraliaCanada Chile Chinese Taipei Hong…”
BackgroundSpecifying Location-Scale Models for Heterogeneous Variances as Multilevel SEMs
McNeish, D. (2020) · Organizational Research Methods · doi:10.1177/1094428120913083 · Cited by 73
“Retaining the default prior distributions in Mplus yields results that are very close to maximum likelihood, especially at larger samples (Muthén & Asparouhov, 2012).”
MethodResultShuck, B., Zigarmi, D., & Owen, J. J. (2015) · European journal of training and development · doi:10.1108/ejtd-08-2014-0061 · Cited by 89
Assessing construct structural validity of epidemiological measurement tools: a seven-step roadmap
Reichenheim, M. E., Hökerberg, Y. H. M., & de Moraes, C. L. (2014) · Cadernos de Saúde Pública · doi:10.1590/0102-311x00143613 · Cited by 71
Bayesian Structural Equation Modeling in Sport and Exercise Psychology
Stenling, A., Ivarsson, A., Johnson, U., & Lindwall, M. (2015) · Journal of Sport and Exercise Psychology · doi:10.1123/jsep.2014-0330 · Cited by 82
“The rationale for posterior predictive model checking, such as the posterior predictive p value, is to investigate whether the replicated data that is generated by the model matches the observed data (e.g., Gelman et al., 2014a; Levy, 2011; Muthén & Asparouhov, 2012a; Zyphur & Oswald, 2015).”
BackgroundMethodResultInfluentialA review of some emergent quantitative analyses in sport and exercise psychology
Myers, N. D., Ntoumanis, N., Gunnell, K. E., Gucciardi, D. F., & Lee, S. (2017) · International Review of Sport and Exercise Psychology · doi:10.1080/1750984x.2017.1317356 · Cited by 71
“Bayesian structural equation modelling (BSEM; Muthén & Asparouhov, 2012) has a lot of similarities with ESEM, particularly when the target rotation is used (Marsh et al., 2014).”
BackgroundLatent Growth Curve Models for Biomarkers of the Stress Response
Felt, J. M., Depaoli, S. A., & Tiemensma, J. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00315 · Cited by 78
“For a more technical review of Bayesian estimation and how it applies to LVMs such as LGCMs, see Muthén and Asparouhov (2012) and Kaplan and Depaoli (2012).”
BackgroundOn identity and sport conduct of student-athletes: Considering athletic and academic contexts
Yukhymenko–Lescroart, M. A. (2017) · Psychology of sport and exercise · doi:10.1016/j.psychsport.2017.09.006 · Cited by 76
“The statistical significance of indirect associations was tested using Bayesian credible 2 intervals (Muthén & Asparouhov, 2012), which have no distributional assumptions.”
MethodBifactor Modelling and the Evaluation of Scale Scores
Reise, S. P., Bonifay, W. E., & Haviland, M. G. (2018) · Wiley eBooks · doi:10.1002/9781118489772.ch22 · Cited by 78
Yang, F., Wang, Y., Yang, C., Zhou, M., Shu, J., Fu, B., & Hu, H. (2019) · BMC Medical Education · doi:10.1186/s12909-019-1454-9 · Cited by 79
Trans-diagnostic measurement of impulsivity and compulsivity: A review of self-report tools
Hook, R. W., Grant, J. E., Ioannidis, K., Tiego, J., Yücel, M., Wilkinson, P. O., & Chamberlain, S. R. (2020) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2020.10.007 · Cited by 77
Doron, J., & Gaudreau, P. (2014) · Journal of Sport and Exercise Psychology · doi:10.1123/jsep.2013-0043 · Cited by 69
“Bayesian estimators are more flexible and efficient than traditional estimators (e.g., Muthén & Asparouhov, 2012) because they are more likely to converge and are less susceptible to provide untrustworthy parameter estimates (e.g., negative error variance).”
BackgroundKuiper, J. R., Stapleton, H. M., Wills-Karp, M. A., Wang, X., Burd, I. D., & Buckley, J. P. (2020) · Environmental Health · doi:10.1186/s12940-020-00610-0 · Cited by 69
Acceptability of Family Violence: Underlying Ties Between Intimate Partner Violence and Child Abuse
Gracia, E., Rodriguez, C. M., Martín-Fernández, M., & Lila, M. (2017) · Journal of Interpersonal Violence · doi:10.1177/0886260517707310 · Cited by 76
“Bayesian structural equation modeling (BSEM) is an emergent and promising CFA framework that offers several advantages over the classical maximum likelihood estimation (B. Muthén & Asparouhov, 2012).”
BackgroundStreet, K. E. S., Malmberg, L., & Stylianides, G. J. (2022) · Educational Studies in Mathematics · doi:10.1007/s10649-022-10165-1 · Cited by 75
“Bayesian statistics are suitable for models with complex between-level variance parameters such as ours (Muthén & Asparouhov, 2012; Zitzmann et al., 2016).”
MethodInfluentialA Bayesian Approach for Estimating Multilevel Latent Contextual Models
Zitzmann, S., Lüdtke, O., Robitzsch, A., & Marsh, H. W. (2016) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2016.1207179 · Cited by 68
“For each model and model parameter, the PSR was 1 and the MCMCSEPSD ratio was well below .05, indicating that WinBUGS approximated the posterior distributions very well (see Hoff, 2009; B. O. Muthén & Asparouhov, 2012; see also Cho & Bottge, 2015).”
BackgroundMethodInfluentialGuo, J., Marsh, H. W., Parker, P. D., Dicke, T., Lüdtke, O., & Diallo, T. (2019) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2018.1554999 · Cited by 66
“Exploratory SEM (ESEM) is claimed to provide an optimal compromise between EFA and CFA/SEM.”
BackgroundMethodResultInfluentialHøglend, P. A., & Hagtvet, K. A. (2019) · Journal of Consulting and Clinical Psychology · doi:10.1037/ccp0000381 · Cited by 66
Meaning in Life and Coping With Everyday Stressors
Ward, S. J., Womick, J., Titova, L., & King, L. (2022) · Personality and Social Psychology Bulletin · doi:10.1177/01461672211068910 · Cited by 72
“Models used Bayes’ estimation (to account for the non-normality of indirect effects) with latent mean-centered predictors (Muthén & Asparouhov, 2012).”
MethodBayesian Probability and Statistics in Management Research: A New Horizon
Zyphur, M. J., & Oswald, F. L. (2012) · Journal of Management · doi:10.1177/0149206312463183 · Cited by 65
Bayesian Factor Analysis as a Variable-Selection Problem: Alternative Priors and Consequences
Lu, Z., Chow, S., & Loken, E. (2016) · Multivariate Behavioral Research · doi:10.1080/00273171.2016.1168279 · Cited by 71
“By comparison, Muthén and Asparouhov (2012) and Asparouhov, Muthén, and Morin (2015) suggested running BSEM-RP multiple times by using several prior variances in the range of [0.001, 0.1] for sensitivity checking and selecting the appropriate prior variances through subjective selection with two…”
BackgroundMethodResultInfluentialDiagnosis of Calcific Tendonitis of the Rotator Cuff by Using Susceptibility-weighted MR Imaging
Nörenberg, D., Ebersberger, H. U., Walter, T., Ockert, B., Knobloch, G., Diederichs, G., Hamm, B., & Makowski, M. R. (2015) · Radiology · doi:10.1148/radiol.2015150034 · Cited by 66
Gosse, C., Parmentier, M., & Reybroeck, M. V. (2021) · Frontiers in Psychology · doi:10.3389/fpsyg.2021.685681 · Cited by 67
“When conducting Bayesian analysis, researchers are strongly invited to examine the sensitivity of their results to alternative prior distributional specifications and parameter autocorrelations with alternative thinning parameters (Muthén and Asparouhov, 2012).”
BackgroundMethodInfluentialBujacz, A., Vittersø, J., Huta, V., & Kaczmarek, L. D. (2014) · Frontiers in Psychology · doi:10.3389/fpsyg.2014.00984 · Cited by 75
“Including small priors for cross-loadings (or residual covariances which is also possible, see Muthén and Asparouhov, 2012) helps in verifying why the model does not represent the data well.”
BackgroundMethodInfluential
Metadata
- Authors
- Muthén, B., & Asparouhov, T.
- Affiliations
- Muthén & Muthén (United States) (US)
- Venue
- Psychological Methods
- Published
- 2012-09
- Volume
- 17
- Issue
- 3
- Pages
- 313-335
- ISSN
- 1082-989X (ISSN-L)
- 1939-1463
- OpenAlex
- W2157335584
- Cited by
- 1,562
- References
- 43
- Citations by year
- 2026: 148 · 2025: 140 · 2024: 136 · 2023: 118 · 2022: 135 · 2021: 169 · 2020: 124 · 2019: 127 · 2018: 103 · 2017: 99 · 2016: 74 · 2015: 77 · 2014: 60 · 2013: 32 · 2012: 12
- FWCI
- 76.81
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Psychological Methods (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Distribution Estimation and Applications
- Keywords
- Bayesian structural equation modeling, confirmatory factor analysis, structural equation modeling, system identification, cross-loadings, residual correlation, model misspecification, posterior predictive checking, model modification, latent variable measurement, Big Five personality traits, science achievement
- MeSH terms
- Bayes Theorem, Factor Analysis, Statistical, Humans, Markov Chains, Monte Carlo Method, Neuropsychological Tests, Personality Tests, Models, Statistical, Likelihood Functions
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.