A General SEM Framework for Integrating Moderation and Mediation: The Constrained Approach

  • Shu-Ping ChenEmail author
Part of the Springer Proceedings in Mathematics & Statistics book series (PROMS, volume 140)


Modeling the combination of latent moderating and mediating effects is a significant issue in the social and behavioral sciences. Chen and Cheng (Structural Equation Modeling: A Multidisciplinary Journal 21: 94–101, 2014) generalized Jöreskog and Yang’s (Advanced structural equation modeling: Issues and techniques (pp. 57–88). Mahwah, NJ: Lawrence Erlbaum, 1996) constrained approach to allow for the concurrent modeling of moderation and mediation within the context of SEM. Unfortunately, due to restrictions related to Chen and Cheng’s partitioning scheme, their framework cannot completely conceptualize and interpret moderation of indirect effects in a mediated model. In the current study, the Chen and Cheng (abbreviated below as C & C) framework is extended to accommodate situations in which any two pathways that constitute a particular indirect effect in a mediated model can be differentially or collectively moderated by the moderator variable(s). By preserving the inherent advantage of the C & C framework, i.e., the matrix partitioning technique, while at the same time further generalizing its applicability, it is expected that the current framework enhances the potential usefulness of the constrained approach as well as the entire class of the product indicator approaches.


Moderation Mediation The constrained approach 


  1. Algina, J., & Moulder, B. C. (2001). A note on estimating the Jöreskog-Yang model for latent variable interaction using LISREL 8.3. Structural Equation Modeling: A Multidisciplinary Journal, 8, 40–52. doi: 10.1207/S15328007SEM0801_3.CrossRefGoogle Scholar
  2. Arminger, G., & Muthén, B. O. (1998). A Bayesian approach to nonlinear latent variable models using the Gibbs sampler and the Metropolis-Hastings algorithm. Psychometrika, 63, 271–300. doi: 10.1007/BF02294856.CrossRefzbMATHGoogle Scholar
  3. Baron, R. M., & Kenny, D. A. (1986). The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173–1182. doi: 10.1037/0022-3514.51.6.1173.CrossRefGoogle Scholar
  4. Bollen, K. A., & Noble, M. D. (2011). Structural equation models and the quantification of behavior. Proceedings of the National Academy of Sciences, 108, 15639–15646. doi: 10.1073/pnas.1010661108.
  5. Busemeyer, J. R., & Jones, L. E. (1983). Analysis of multiplicative combination rules when the causal variables are measured with error. Psychological Bulletin, 93, 549–562. doi: 10.1037/0033-2909.93.3.549.CrossRefGoogle Scholar
  6. Chen, S.-P., & Cheng, C.-P. (2014). Model specification for latent interactive and quadratic effects in matrix form. Structural Equation Modeling: A Multidisciplinary Journal, 21, 94–101. doi: 10.1080/10705511.2014.859509.MathSciNetCrossRefGoogle Scholar
  7. Coenders, G., Batista-Foguet, J. M., & Saris, W. E. (2008). Simple, efficient and distribution-free approach to interaction effects in complex structural equation models. Quality & Quantity, 42, 369–396. doi: 10.1007/s11135-006-9050-6.CrossRefGoogle Scholar
  8. Cole, M. S., Walter, F., & Bruch, H. (2008). Affective mechanisms linking dysfunctional behavior to performance in work teams: A moderated mediation study. Journal of Applied Psychology, 93, 945–958. doi: 10.1037/0021-9010.93.5.945.CrossRefGoogle Scholar
  9. Edwards, J. R., & Lambert, L. S. (2007). Methods for integrating moderation and mediation: A general analytical framework using moderated path analysis. Psychological Methods, 12, 1–22. doi: 10.1037/1082-989X.12.1.1.CrossRefGoogle Scholar
  10. Fairchild, A. J., & MacKinnon, D. P. (2009). A general model for testing mediation and moderation effects. Prevention Science, 10, 87–99. doi: 10.1007/s11121-008-0109-6.CrossRefGoogle Scholar
  11. Ghazal, G. A., & Neudecker, H. (2000). On second-order and fourth-order moments of jointly distributed random matrices: A survey. Linear Algebra and its Applications, 321, 61–93. doi: 10.1016/S0024-3795(00)00181-6.
  12. Hayes, A. F. (2013). Introduction to mediation, moderation, and conditional process analysis. New York, NY: Guilford Press.Google Scholar
  13. Jaccard, J., & Wan, C. K. (1995). Measurement error in the analysis of interaction effects between continuous predictors using multiple regression: Multiple indicator and structural equation approaches. Psychological Bulletin, 117, 348–357. doi: 10.1037/0033-2909.117.2.348.CrossRefGoogle Scholar
  14. James, L. R., & Brett, J. M. (1984). Mediators, moderators, and tests for mediation. Journal of Applied Psychology, 69, 307–321. doi: 10.1037/0021-9010.69.2.307.CrossRefGoogle Scholar
  15. Jöreskog, K. G., & Yang, F. (1996). Nonlinear structural equation models: The Kenny-Judd model with interaction effects. In G. A. Marcoulides & R. E. Schumacker (Eds.), Advanced structural equation modeling: Issues and techniques (pp. 57–88). Mahwah, NJ: Lawrence Erlbaum.Google Scholar
  16. Kelava, A., & Brandt, H. (2009). Estimation of nonlinear latent structural equation models using the extended unconstrained approach. Review of Psychology, 16(2), 123–131.Google Scholar
  17. Kenny, D. A., & Judd, C. M. (1984). Estimating the nonlinear and interactive effects of latent variables. Psychological Bulletin, 96, 201–210. doi: 10.1037/0033-2909.96.1.201.CrossRefGoogle Scholar
  18. Klein, A. G., & Muthén, B. O. (2007). Quasi-maximum likelihood estimation of structural equation models with multiple interaction and quadratic effects. Multivariate Behavioral Research, 42, 647–673. doi: 10.1080/00273170701710205.CrossRefGoogle Scholar
  19. Klein, A., & Moosbrugger, H. (2000). Maximum likelihood estimation of latent interaction effects with the LMS method. Psychometrika, 65, 457–474. doi: 10.1007/BF02296338.MathSciNetCrossRefzbMATHGoogle Scholar
  20. Lee, S.-Y., Song, X.-Y., & Tang, N.-S. (2007). Bayesian methods for analyzing structural equation models with covariates, interaction, and quadratic latent variables. Structural Equation Modeling: A Multidisciplinary Journal, 14, 404–434. doi: 10.1080/10705510701301511.MathSciNetCrossRefGoogle Scholar
  21. Lee, S.-Y., & Zhu, H.-T. (2002). Maximum likelihood estimation of nonlinear structural equation models. Psychometrika, 67, 189–210. doi: 10.1007/BF02294842.MathSciNetCrossRefzbMATHGoogle Scholar
  22. Luszczynska, A., Cao, D. S., Mallach, N., Pietron, K., Mazurkiewicz, M., & Schwarzer, R. (2010). Intentions, planning, and self-efficacy predict physical activity in Chinese and polish adolescents: Two moderated mediation analyses. International Journal of Clinical and Health Psychology, 10(2), 265–278.Google Scholar
  23. Magnus, J. R., & Neudecker, H. (1979). The commutation matrix: Some properties and applications. The Annals of Statistics, 7, 237–466. doi: 10.1214/aos/1176344621.MathSciNetCrossRefGoogle Scholar
  24. Magnus, J. R., & Neudecker, H. (1980). The elimination matrix: Some lemmas and applications. SIAM Journal on Algebraic Discrete Methods, 1, 422–449. doi: 10.1137/0601049.MathSciNetCrossRefzbMATHGoogle Scholar
  25. Magnus, J. R., & Neudecker, H. (1988). Matrix differential calculus with applications in statistics and econometrics. New York, NY: John Wiley & Sons.zbMATHGoogle Scholar
  26. Marsh, H. W., Wen, Z., & Hau, K.-T. (2004). Structural equation models of latent interactions: Evaluation of alternative estimation strategies and indicator construction. Psychological Methods, 9, 275–300. doi: 10.1037/1082-989X.9.3.275.CrossRefGoogle Scholar
  27. Marsh, H. W., Wen, Z., & Hau, K.-T. (2006). Structural equation models of latent interaction and quadratic effects. In G. R. Hancock & R. O. Mueller (Eds.), Structural equation modeling: A second course (pp. 225–265). Greenwich, CT: Information Age Publishing.Google Scholar
  28. Moosbrugger, H., Schermelleh-Engel, K., Kelava, A., & Klein, A. G. (2009). Testing multiple nonlinear effects in structural equation modeling: A comparison of alternative estimation approaches. In T. Teo & M. S. Khine (Eds.), Structural equation modelling in educational research: Concepts and applications (pp. 103–136). Rotterdam, NL: Sense Publishers.Google Scholar
  29. Muthén, B. (1984). A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators. Psychometrika, 49, 115–132. doi: 10.1007/BF02294210.CrossRefGoogle Scholar
  30. Pollack, J. M., Vanepps, E. M., & Hayes, A. F. (2012). The moderating role of social ties on entrepreneurs’ depressed affect and withdrawal intentions in response to economic stress. Journal of Organizational Behavior, 33, 789–810. doi: 10.1002/job.1794.CrossRefGoogle Scholar
  31. Preacher, K. J., Rucker, D. D., & Hayes, A. F. (2007). Addressing moderated mediation hypotheses: Theory, methods, and prescriptions. Multivariate Behavioral Research, 42, 185–227. doi: 10.1080/00273170701341316.CrossRefGoogle Scholar
  32. Seber, G. A. F. (2007). A matrix handbook for statisticians. New York, NY: John Wiley & Sons.CrossRefGoogle Scholar
  33. Slater, M. D., Hayes, A. F., & Ford, V. L. (2007). Examining the moderating and mediating roles of news exposure and attention on adolescent judgments of alcohol-related risks. Communication Research, 34, 355–381. doi: 10.1177/0093650207302783.CrossRefGoogle Scholar
  34. Tracy, D. S., & Sultan, S. A. (1993). Higher order moments of multivariate normal distribution using matrix derivatives. Stochastic Analysis and Applications, 11, 337–348. doi: 10.1080/07362999308809320.MathSciNetCrossRefzbMATHGoogle Scholar
  35. Wall, M. M. (2009). Maximum likelihood and Bayesian estimation for nonlinear structural equation models. In R. E. Millsap & A. Maydeu-Olivares (Eds.), The SAGE handbook of quantitative methods in psychology (pp. 540–567). London, England: Sage.CrossRefGoogle Scholar
  36. Wall, M. M., & Amemiya, Y. (2001). Generalized appended product indicator procedure for nonlinear structural equation analysis. Journal of Educational and Behavioral Statistics, 26, 1–29. doi: 10.3102/10769986026001001.CrossRefGoogle Scholar
  37. Yang-Wallentin, F., & Jöreskog, K. G. (2001). Robust standard errors and chi-squares for interaction models. In G. A. Marcoulides & R. E. Schumacker (Eds.), New developments and techniques in structural equation modeling (pp. 159–171). Mahwah, NJ: Erlbaum.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of PsychologyNational Chengchi UniversityTaipei CityTaiwan, ROC

Personalised recommendations