Skip to main content

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

  • Conference paper

Part of the book series: Springer Proceedings in Mathematics & Statistics ((PROMS,volume 140))

Abstract

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.

This is a preview of subscription content, log in via an institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD   169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  • 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.

    Article  Google Scholar 

  • 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.

    Article  MATH  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

  • 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.

    Article  Google Scholar 

  • 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.

    Article  MathSciNet  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

  • Hayes, A. F. (2013). Introduction to mediation, moderation, and conditional process analysis. New York, NY: Guilford Press.

    Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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 

  • 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 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • Klein, A., & Moosbrugger, H. (2000). Maximum likelihood estimation of latent interaction effects with the LMS method. Psychometrika, 65, 457–474. doi:10.1007/BF02296338.

    Article  MathSciNet  MATH  Google Scholar 

  • 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.

    Article  MathSciNet  Google Scholar 

  • Lee, S.-Y., & Zhu, H.-T. (2002). Maximum likelihood estimation of nonlinear structural equation models. Psychometrika, 67, 189–210. doi:10.1007/BF02294842.

    Article  MathSciNet  MATH  Google Scholar 

  • 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 

  • 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.

    Article  MathSciNet  Google Scholar 

  • 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.

    Article  MathSciNet  MATH  Google Scholar 

  • Magnus, J. R., & Neudecker, H. (1988). Matrix differential calculus with applications in statistics and econometrics. New York, NY: John Wiley & Sons.

    MATH  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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 

  • 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 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  Google Scholar 

  • Seber, G. A. F. (2007). A matrix handbook for statisticians. New York, NY: John Wiley & Sons.

    Book  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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.

    Article  MathSciNet  MATH  Google Scholar 

  • 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.

    Chapter  Google Scholar 

  • 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.

    Article  Google Scholar 

  • 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 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shu-Ping Chen .

Editor information

Editors and Affiliations

Appendices

Appendix A: Expansions of \( {\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} \), \( {\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }} \), \( {\mathbf{y}}_{{\mathbf{F}}^{\ast }}, \) and \( {\mathbf{y}}_{{\mathbf{S}}^{\ast }} \)

Before \( {\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} \), \( {\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }} \), \( {\mathbf{y}}_{{\mathbf{F}}^{\ast }}, \) and \( {\mathbf{y}}_{{\mathbf{S}}^{\ast }} \) are discussed in the subsequent paragraph, it is necessary to gain familiarity with the notation of four basic types of matrices. The \( n \times n \) identity matrix will be denoted as Ι n and the \( mn \times mn \) commutation matrix will be indicated as K mn for \( m\ \ne\ n \) and K n for \( m = n \) (see definition 3.1 of Magnus and Neudecker 1979). The \( n\left(n + 1\right)/2 \times {n}^2 \) elimination matrix and \( {n}^2 \times n\left(n + 1\right)/2 \) duplication matrix will be denoted as L n and D n , respectively (see definitions 3.1a and 3.2a of Magnus and Neudecker 1980).

The expansions of \( {\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} \), \( {\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }} \), \( {\mathbf{y}}_{{\mathbf{F}}^{\ast }}, \) and \( {\mathbf{y}}_{{\mathbf{S}}^{\ast }} \) can be obtained with the aid of several theorems and properties of the Kronecker product, vech and vec operators shown in Magnus and Neudecker (1980, 1988). The resulting forms of these expansions are expressed as below.

$$ {\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} = {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\upalpha}}_{\mathbf{F}}{\boldsymbol{\upalpha}}_{\mathbf{F}}^{\mathrm{T}}\right) + {\boldsymbol{\upzeta}}_{{\mathbf{F}}^{\ast }}, $$
$$ {\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }} = {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\upalpha}}_{\mathbf{S}}{\boldsymbol{\upalpha}}_{\mathbf{F}}^{\mathrm{T}}\right) + {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}{\mathbf{S}}_{\mathbf{2}}{\boldsymbol{\upeta}}_{\mathbf{F}} + {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}{\mathbf{S}}_{\mathbf{3}}{\boldsymbol{\upeta}}_{\mathbf{F}}^{\ast } + {\boldsymbol{\upzeta}}_{{\mathbf{S}}^{\ast }}, $$
$$ {\mathbf{y}}_{{\mathbf{F}}^{\ast }} = {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\upnu}}_{\mathbf{F}}{\boldsymbol{\upnu}}_{\mathbf{F}}^{\mathrm{T}}\right) + {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p{\mathbf{E}}_{\mathbf{1}}{\boldsymbol{\upeta}}_{\mathbf{F}} + {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p{\mathbf{E}}_{\mathbf{2}}{\mathbf{D}}_f{\mathbf{W}}_{\mathbf{1}}^{\mathrm{T}}{\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} + {\boldsymbol{\upvarepsilon}}_{{\mathbf{F}}^{\ast }}, $$
$$ {\mathbf{y}}_{{\mathbf{S}}^{\ast }} = {\mathbf{W}}_{\mathbf{4}}\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\upnu}}_{\mathbf{S}}{\boldsymbol{\upnu}}_{\mathbf{F}}^{\mathrm{T}}\right) + {\mathbf{W}}_{\mathbf{4}}{\mathbf{A}}_{\mathbf{1}}{\boldsymbol{\upeta}}_{\mathbf{F}} + {\mathbf{W}}_{\mathbf{4}}{\mathbf{A}}_{\mathbf{2}}{\boldsymbol{\upeta}}_{\mathbf{S}} + {\mathbf{W}}_{\mathbf{4}}{\mathbf{A}}_{\mathbf{3}}{\mathbf{W}}_{\mathbf{2}}^{\mathrm{T}}{\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }} + {\boldsymbol{\upvarepsilon}}_{{\mathbf{S}}^{\ast }}, $$

where \( {\boldsymbol{\upzeta}}_{{\mathbf{F}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}\left({\mathbf{F}}_{\mathbf{2}}{\boldsymbol{\upzeta}}_{\mathbf{F}} + {\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) \),

$$ {\boldsymbol{\upzeta}}_{{\mathbf{S}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\left[{\mathbf{S}}_{\mathbf{4}}{\boldsymbol{\upzeta}}_{\mathbf{F}} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\upzeta}}_{\mathbf{S}} + {\mathbf{S}}_{\mathbf{6}}\left({\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) + {\mathbf{S}}_{\mathbf{7}}\left({\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) + {\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{S}}\right], $$
$$ {\boldsymbol{\upvarepsilon}}_{{\mathbf{F}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p\left[{\mathbf{E}}_{\mathbf{3}}{\boldsymbol{\upvarepsilon}}_{\mathbf{F}} + {\mathbf{E}}_{\mathbf{4}}\left({\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) + {\mathbf{E}}_{\mathbf{5}}\left({\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upvarepsilon}}_{\mathbf{F}}\right) + {\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upvarepsilon}}_{\mathbf{F}}\right], $$
$$ \begin{aligned}{\boldsymbol{\upvarepsilon}}_{{\mathbf{S}}^{\ast }}\ &\underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{4}}\big[{\mathbf{A}}_{\mathbf{4}}{\boldsymbol{\upvarepsilon}}_{\mathbf{F}} + {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\upvarepsilon}}_{\mathbf{S}} + {\mathbf{A}}_{\mathbf{6}}\left({\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) + {\mathbf{A}}_{\mathbf{7}}\left({\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upvarepsilon}}_{\mathbf{S}}\right) + {\mathbf{A}}_{\mathbf{8}}\left({\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{S}}\right)\\ &\quad+ {\mathbf{A}}_{\mathbf{9}}\left({\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}} \otimes {\boldsymbol{\upzeta}}_{\mathbf{F}}\right) + {\boldsymbol{\upvarepsilon}}_{\mathbf{F}} \otimes {\boldsymbol{\upvarepsilon}}_{\mathbf{S}}\big]\end{aligned} $$

(here “\( \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}} \)” is the symbol for “defined as”) in which \( {\mathbf{F}}_{\mathbf{1}} = [({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}}) \otimes ({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}}{)]}^{\hbox{-} 1} \), \( {\mathbf{F}}_{\mathbf{2}} = {\mathbf{I}}_f \otimes {\boldsymbol{\upalpha}}_{\mathbf{F}} + {\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\mathbf{I}}_f \), \( {\mathbf{S}}_{\mathbf{1}} = [({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{FF}}) \otimes ({\mathbf{I}}_s - {\mathbf{B}}_{\mathbf{S}\mathbf{S}}{)]}^{\hbox{-} 1} \), \( {\mathbf{S}}_{\mathbf{2}} = {\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\mathbf{B}}_{\mathbf{S}\mathbf{F}} \), \( {\mathbf{S}}_{\mathbf{3}} = {\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }} \), \( {\mathbf{S}}_{\mathbf{4}} = {\mathbf{I}}_f \otimes [{\boldsymbol{\upalpha}}_{\mathbf{S}} + {\mathbf{B}}_{\mathbf{S}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1}{\boldsymbol{\upalpha}}_{\mathbf{F}} + {\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}({\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\boldsymbol{\upalpha}}_{\mathbf{F}})] \), \( {\mathbf{S}}_{\mathbf{5}} = {\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\mathbf{I}}_s \), \( {\mathbf{S}}_{\mathbf{6}} = {\mathbf{I}}_f \otimes [{\mathbf{B}}_{\mathbf{S}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1} + {\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}{\mathbf{F}}_{\mathbf{2}}] \), \( {\mathbf{S}}_{\mathbf{7}} = {\mathbf{I}}_f \otimes ({\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}) \), \( {\mathbf{E}}_{\mathbf{1}} = {\boldsymbol{\Lambda}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\upnu}}_{\mathbf{F}} + {\boldsymbol{\upnu}}_{\mathbf{F}} \otimes {\boldsymbol{\Lambda}}_{\mathbf{F}\mathbf{F}} \), \( {\mathbf{E}}_{\mathbf{2}} = {\boldsymbol{\Lambda}}_{\mathbf{FF}} \otimes {\boldsymbol{\Lambda}}_{\mathbf{FF}} \), \( {\mathbf{E}}_{\mathbf{3}} = {\mathbf{I}}_p \otimes [{\boldsymbol{\upnu}}_{\mathbf{F}} + {\boldsymbol{\Lambda}}_{\mathbf{F}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1}{\boldsymbol{\upalpha}}_{\mathbf{F}}] + [{\boldsymbol{\upnu}}_{\mathbf{F}} + {\boldsymbol{\Lambda}}_{\mathbf{F}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1}{\boldsymbol{\upalpha}}_{\mathbf{F}}] \otimes {\mathbf{I}}_p \), \( {\mathbf{E}}_{\mathbf{4}} = {\mathbf{I}}_p \otimes ({\boldsymbol{\Lambda}}_{\mathbf{FF}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{FF}})}^{\hbox{-} 1}) \), \( {\mathbf{E}}_{\mathbf{5}} = ({\boldsymbol{\Lambda}}_{\mathbf{FF}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{FF}})}^{\hbox{-} 1}) \otimes {\mathbf{I}}_p \), \( {\mathbf{A}}_{\mathbf{1}} = {\boldsymbol{\Lambda}}_{\mathbf{FF}} \otimes {\boldsymbol{\upnu}}_{\mathbf{S}} \), \( {\mathbf{A}}_{\mathbf{2}} = {\boldsymbol{\upnu}}_{\mathbf{F}} \otimes {\boldsymbol{\Lambda}}_{\mathbf{SS}} \), \( {\mathbf{A}}_{\mathbf{3}} = {\boldsymbol{\Lambda}}_{\mathbf{FF}} \otimes {\boldsymbol{\Lambda}}_{\mathbf{SS}} \), \( {\mathbf{A}}_{\mathbf{4}} = {\mathbf{I}}_p \otimes [{\boldsymbol{\upnu}}_{\mathbf{S}} + {\boldsymbol{\Lambda}}_{\mathbf{S}\mathbf{S}}{({\mathbf{I}}_s - {\mathbf{B}}_{\mathbf{S}\mathbf{S}})}^{\hbox{-} 1}({\boldsymbol{\upalpha}}_{\mathbf{S}} + {\mathbf{B}}_{\mathbf{S}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1}{\boldsymbol{\upalpha}}_{\mathbf{F}} + {\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}({\boldsymbol{\upalpha}}_{\mathbf{F}} \otimes {\boldsymbol{\upalpha}}_{\mathbf{F}}))] \), \( {\mathbf{A}}_{\mathbf{5}} = [{\boldsymbol{\upnu}}_{\mathbf{F}} + {\boldsymbol{\Lambda}}_{\mathbf{F}\mathbf{F}}{({\mathbf{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1}{\boldsymbol{\upalpha}}_{\mathbf{F}}] \otimes {\mathbf{I}}_q \), \( {\mathbf{A}}_{\mathbf{6}} = {\mathbf{I}}_p \otimes [{\boldsymbol{\Lambda}}_{\mathbf{S}\mathbf{S}}{({\mathbf{I}}_s - {\mathbf{B}}_{\mathbf{S}\mathbf{S}})}^{\hbox{-} 1}({\mathbf{B}}_{\mathbf{S}\mathbf{F}}{({\mathrm{I}}_f - {\mathbf{B}}_{\mathbf{F}\mathbf{F}})}^{\hbox{-} 1} + {\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}{\mathbf{F}}_{\mathbf{2}})] \), \( {\mathbf{A}}_{\mathbf{7}} = ({\boldsymbol{\Lambda}}_{\mathbf{FF}}{\left({\mathbf{I}}_f - {\mathbf{B}}_{\mathbf{FF}}\right)}^{\hbox{-} 1}) \otimes {\mathbf{I}}_q \), \( {\mathbf{A}}_{\mathbf{8}} = {\mathbf{I}}_p \otimes ({\boldsymbol{\Lambda}}_{\mathbf{SS}}{({\mathbf{I}}_s - {\mathbf{B}}_{\mathbf{SS}})}^{\hbox{-} 1}) \) and \( {\mathbf{A}}_{\mathbf{9}} = {\mathbf{I}}_p \otimes ({\boldsymbol{\Lambda}}_{\mathbf{S}\mathbf{S}}{({\mathbf{I}}_s - {\mathbf{B}}_{\mathbf{S}\mathbf{S}})}^{\hbox{-} 1}{\mathbf{B}}_{\mathbf{S}{\mathbf{F}}^{\ast }}{\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}) \).

Here, \( {\boldsymbol{\upzeta}}_{{\mathbf{F}}^{\ast }} \) and \( {\boldsymbol{\upzeta}}_{{\mathbf{S}}^{\ast }} \) are vectors of disturbance terms of \( {\boldsymbol{\upeta}}_{{\mathbf{F}}^{\ast }} \) and \( {\boldsymbol{\upeta}}_{{\mathbf{S}}^{\ast }}, \) while \( {\boldsymbol{\upvarepsilon}}_{{\mathbf{F}}^{\ast }} \) and \( {\boldsymbol{\upvarepsilon}}_{{\mathbf{S}}^{\ast }} \) are vectors of measurement errors of \( {\mathbf{y}}_{{\mathbf{F}}^{\ast }} \) and \( {\mathbf{y}}_{{\mathbf{S}}^{\ast }} \). Meanwhile, F 1 , F 2 , S 1 to S 7 , E 1 to E 5 , and A 1 to A 9 are all constant matrices.

Appendix B: Partitioned Matrices Ψ and Θ

The disturbance covariance matrix Ψ is partitioned into a \( 5 \times 5 \) array of submatrices as expressed below:

$$ \boldsymbol{\Psi} = \left[\begin{array}{ccccc} {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} & & & & \\ {} {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} & {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{S}} & & & \\ {} {\boldsymbol{\Psi}}_{\mathbf{TF}} & {\boldsymbol{\Psi}}_{\mathbf{TS}} & {\boldsymbol{\Psi}}_{\mathbf{TT}} & & \\ {} {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{F}} & {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{S}} & {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{T}} & {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast }{\mathbf{F}}^{\ast }} & \\ {} {\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{F}} & {\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{S}} & {\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{T}} & {\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast }{\mathbf{F}}^{\ast }} & {\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast }{\mathbf{S}}^{\ast }} \end{array}\right], $$

where \({{ {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{F}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}{\mathbf{F}}_{\mathbf{2}}{\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}}} \), \( {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{S}}\underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}{\mathbf{F}}_{\mathbf{2}}{\left({\boldsymbol{\Psi}}_{\mathbf{SF}}\right)}^{\mathrm{T}} \), \( {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast}\mathbf{T}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}{\mathbf{F}}_{\mathbf{2}} {\left({\boldsymbol{\Psi}}_{\mathbf{TF}}\right)}^{\mathrm{T}} \), \( {\boldsymbol{\Psi}}_{{\mathbf{F}}^{\ast }{\mathbf{F}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{1}}{\mathbf{L}}_f{\mathbf{F}}_{\mathbf{1}}\left[{\mathbf{F}}_{\mathbf{2}}{\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}{\mathbf{F}}_{\mathbf{2}}^{\mathrm{T}} + \left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right)\right]{\mathbf{F}}_{\mathbf{1}}^{\mathrm{T}}{\mathbf{L}}_f^{\mathrm{T}}{\mathbf{W}}_{\mathbf{1}}^{\mathrm{T}} \),

$$ \begin{array}{l}{\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{F}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\big[{\mathbf{S}}_{\mathbf{4}}{\boldsymbol{\Psi}}_{\mathbf{FF}} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\\ {} + {\mathbf{S}}_{\mathbf{7}}{\Delta}_{f^3 \times f}\left[{\mathbf{K}}_{f{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right.\right.\\ {} + \left.\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\big]\big],\end{array} $$
$$ \begin{array}{l}{\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{S}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\big[{\mathbf{S}}_{\mathbf{4}}{\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{S}}\\ {} + {\mathbf{S}}_{\mathbf{7}}{\varDelta}_{f^3 \times s}\left[{\mathbf{K}}_{s{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right) + {\mathbf{K}}_{fs}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right.\right.\\ {} \left.+ \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)\right)\big]\big],\end{array} $$
$$ \begin{array}{l}{\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast}\mathbf{T}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\big[{\mathbf{S}}_{\mathbf{4}}{\left({\boldsymbol{\Psi}}_{\mathbf{TF}}\right)}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{5}}{\left({\boldsymbol{\Psi}}_{\mathbf{TS}}\right)}^{\mathrm{T}}\\ {} + {\mathbf{S}}_{\mathbf{7}}{\varDelta}_{f^3 \times t}\left[{\mathbf{K}}_{t{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{TF}}\right) + {\mathbf{K}}_{ft}\left({\boldsymbol{\Psi}}_{\mathbf{TF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right.\right.\\ {} \left.+ \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{TF}}\right)\right)\big]\big],\end{array} $$
$${\fontsize{9}{11}\selectfont{ \begin{array}{l}{\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast }{\mathbf{F}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\big[{\mathbf{S}}_{\mathbf{4}}{\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}{\mathbf{F}}_{\mathbf{2}}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}{\mathbf{F}}_{\mathbf{2}}^{\mathrm{T}}\\ {} + {\mathbf{S}}_{\mathbf{7}}{\Delta}_{f^3 \times f}\left[{\mathbf{K}}_{f{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right)\right) + \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right)\right)\right]{\mathbf{F}}_{\mathbf{2}}^{\mathrm{T}}\\ {} + {\mathbf{S}}_{\mathbf{6}}\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right) + {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} + {\mathbf{K}}_{fs}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right)\big]{\mathbf{F}}_{\mathbf{1}}^{\mathrm{T}}{\mathbf{L}}_f^{\mathrm{T}}{\mathbf{W}}_{\mathbf{1}}^{\mathrm{T}},\end{array} }} $$
$$ {\fontsize{8.5}{10.5}\selectfont{ \begin{array}{l}{\boldsymbol{\Psi}}_{{\mathbf{S}}^{\ast }{\mathbf{S}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{2}}{\mathbf{S}}_{\mathbf{1}}\big[{\mathbf{S}}_{\mathbf{4}}{\boldsymbol{\Psi}}_{\mathbf{FF}}{\mathbf{S}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{S}}{\mathbf{S}}_{\mathbf{5}}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{6}}\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right){\mathbf{S}}_{\mathbf{6}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{7}}\big[\left({\mathbf{I}}_{f^3} + {\mathbf{K}}_{f{f}^2} + {\mathbf{K}}_{f^2f} + {\mathbf{I}}_f \otimes {\mathbf{K}}_{ff} + {\mathbf{K}}_{ff} \otimes {\mathbf{I}}_f + \left({\mathbf{I}}_f \otimes {\mathbf{K}}_{ff}\right){\mathbf{K}}_{f{f}^2}\right)\\[10pt] {} \cdot \left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right) + \left({\mathbf{I}}_{f^3} + {\mathbf{K}}_{f{f}^2} + {\mathbf{K}}_{f^2f}\right)\left(\left(\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\mathrm{v}\mathrm{e}\mathrm{c}{\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)}^{\mathrm{T}}\right) \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\\[10pt] {} \cdot \left({\mathbf{I}}_{f^3} + {\mathbf{K}}_{f{f}^2} + {\mathbf{K}}_{f^2f}\right)\big]{\mathbf{S}}_{\mathbf{7}}^{\mathrm{T}} + \left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{S}}\right) + {\mathbf{K}}_{fs}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right)\\[10pt] {} + {\mathbf{S}}_{\mathbf{5}}{\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}{\mathbf{S}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{S}}_{\mathbf{4}}{\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}{\mathbf{S}}_{\mathbf{5}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{7}}{\Delta}_{f^3 \times f}\left[{\mathbf{K}}_{f{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right) + \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{S}}_{\mathbf{4}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{4}}{\Delta}_{f \times {f}^3}\left[{\mathbf{K}}_{f^3f}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\mathbf{I}}_{f^2} + {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right) + \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{S}}_{\mathbf{7}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{7}}{\Delta}_{f^3 \times s}\left[{\mathbf{K}}_{s{f}^3}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left(\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right) + {\mathbf{K}}_{fs}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right) + \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)\right)\right]{\mathbf{S}}_{\mathbf{5}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{5}}{\Delta}_{s \times {f}^3}\left[{\mathbf{K}}_{f^3s}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left[\left({\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right) + {\mathbf{K}}_{ff}\left({\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right]\right.\right.\\[10pt] {} + \mathrm{v}\mathrm{e}\mathrm{c}\left({\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\big)\big]{\mathbf{S}}_{\mathbf{7}}^{\mathrm{T}}\\[10pt] {} + \left[\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right) + {\mathbf{K}}_{fs}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right]{\mathbf{S}}_{\mathbf{6}}^{\mathrm{T}}\\[10pt] {} + {\mathbf{S}}_{\mathbf{6}}\left[\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right) + {\mathbf{K}}_{ff}\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right)\right]\big]{\mathbf{S}}_{\mathbf{1}}^{\mathrm{T}}{\mathbf{W}}_{\mathbf{2}}^{\mathrm{T}}\end{array} }} $$

(here the symbol “\( {\Delta}_{n \times m} \)” is used to transform a \( nm \times 1 \) vector into an \( n \times m \) matrix).

The measurement error covariance matrix Θ is partitioned into a \( 5 \times 5 \) array of submatrices as expressed below:

$$ \boldsymbol{\Theta} = \left[\begin{array}{ccccc} {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} & & & & \\ {} {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} & {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{S}} & & & \\ {} {\boldsymbol{\Theta}}_{\mathbf{TF}} & {\boldsymbol{\Theta}}_{\mathbf{TS}} & {\boldsymbol{\Theta}}_{\mathbf{TT}} & & \\ {} {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{F}} & {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{S}} & {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{T}} & {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast }{\mathbf{F}}^{\ast }} & \\ {} {\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{F}} & {\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{S}} & {\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{T}} & {\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast }{\mathbf{F}}^{\ast }} & {\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast }{\mathbf{S}}^{\ast }} \end{array}\right], $$

where \( {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{F}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p{\mathbf{E}}_{\mathbf{3}}{\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \), \( {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{S}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p{\mathbf{E}}_{\mathbf{3}}{\left({\boldsymbol{\Theta}}_{\mathbf{SF}}\right)}^{\mathrm{T}} \), \( {\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast}\mathbf{T}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p{\mathbf{E}}_{\mathbf{3}}{\left({\boldsymbol{\Theta}}_{\mathbf{TF}}\right)}^{\mathrm{T}} \),

$$ \begin{aligned}{\boldsymbol{\Theta}}_{{\mathbf{F}}^{\ast }{\mathbf{F}}^{\ast }}\ &\underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{3}}{\mathbf{L}}_p\big[{\mathbf{E}}_{\mathbf{3}}{\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}{\mathbf{E}}_{\mathbf{3}}^{\mathrm{T}} + {\mathbf{E}}_{\mathbf{4}}\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{E}}_{\mathbf{5}}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{5}}^{\mathrm{T}}\\ &+ \left({\mathbf{I}}_{p^2} + {\mathbf{K}}_{pp}\right)\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right) + {\mathbf{E}}_{\mathbf{5}}{\mathbf{K}}_{fp}\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{4}}^{\mathrm{T}} \\ &+ {\mathbf{E}}_{\mathbf{4}}{\mathbf{K}}_{pf}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{5}}^{\mathrm{T}}\big]{\mathbf{L}}_p^{\mathrm{T}}{\mathbf{W}}_{\mathbf{3}}^{\mathrm{T}},\end{aligned} $$
$$ {\fontsize{10}{12}\selectfont{{\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{F}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{4}}\left[{\mathbf{A}}_{\mathbf{4}}{\boldsymbol{\Theta}}_{\mathbf{FF}} + {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} + {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times p}\left[{\mathbf{K}}_{p\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fp}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]\right],}} $$
$$ {\fontsize{9}{11}\selectfont{{\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{S}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{4}}\left[{\mathbf{A}}_{\mathbf{4}}{\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{S}} + {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times q}\left[{\mathbf{K}}_{q\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]\right],}} $$
$$ {\fontsize{9}{11}\selectfont{{\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast}\mathbf{T}}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{4}}\left[{\mathbf{A}}_{\mathbf{4}}{\left({\boldsymbol{\Theta}}_{\mathbf{TF}}\right)}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{5}}{\left({\boldsymbol{\Theta}}_{\mathbf{TS}}\right)}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times r}\left[{\mathbf{K}}_{r\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fr}\left({\boldsymbol{\Theta}}_{\mathbf{TF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]\right],}} $$
$$ {\fontsize{10}{12}\selectfont{\begin{aligned}&{\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast }{\mathbf{F}}^{\ast }}\ \underset{{\mkern6mu}}{\underset{={\mkern1mu}}{\Delta}}\ {\mathbf{W}}_{\mathbf{4}}\big[{\mathbf{A}}_{\mathbf{4}}{\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}{\mathbf{E}}_{\mathbf{3}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}{\mathbf{E}}_{\mathbf{3}}^{\mathrm{T}} \\[-10pt] &\quad+ {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times p}\left[{\mathbf{K}}_{p\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fp}\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right)\right)\right]{\mathbf{E}}_{\mathbf{3}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{6}}\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{7}}{\mathbf{K}}_{fq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{8}}\left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{4}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{6}}{\mathbf{K}}_{pf}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{5}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{7}}\left({\boldsymbol{\Psi}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{5}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{8}}{\mathbf{K}}_{ps}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right){\mathbf{E}}_{\mathbf{5}}^{\mathrm{T}}\\ &\quad+ \left({\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right) + {\mathbf{K}}_{pq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Theta}}_{\mathbf{F}\mathbf{F}}\right)\big]{\mathbf{L}}_p^{\mathrm{T}}{\mathbf{W}}_{\mathbf{3}}^{\mathrm{T}},\end{aligned}}} $$
$$ \begin{aligned}{\boldsymbol{\Theta}}_{{\mathbf{S}}^{\ast }{\mathbf{S}}^{\ast }} &= {\mathbf{W}}_{\mathbf{4}}\big[{\mathbf{A}}_{\mathbf{4}}{\boldsymbol{\Theta}}_{\mathbf{FF}}{\mathbf{A}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{S}}{\mathbf{A}}_{\mathbf{5}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{6}}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right){\mathbf{A}}_{\mathbf{6}}^{\mathrm{T}} \\ &\quad+ {\mathbf{A}}_{\mathbf{7}}\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{S}}\right){\mathbf{A}}_{\mathbf{7}}^{\mathrm{T}}+ {\mathbf{A}}_{\mathbf{8}}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{S}}\right){\mathbf{A}}_{\mathbf{8}}^{\mathrm{T}} \\ &\quad+ {\mathbf{A}}_{\mathbf{9}}\big[\left({\mathbf{I}}_{p{f}^2} + {\mathbf{I}}_p \otimes {\mathbf{K}}_{ff}\right)\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\\ &\quad+ {\mathbf{K}}_{p\left({f}^2\right)}\left(\left(\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\mathrm{v}\mathrm{e}\mathrm{c}{\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)}^{\mathrm{T}}\right) \otimes {\boldsymbol{\Theta}}_{\mathbf{FF}}\right){\mathbf{K}}_{\left({f}^2\right)p}\big]{\mathbf{A}}_{\mathbf{9}}^{\mathrm{T}}\\ &\quad+ \left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{S}}\right) + {\mathbf{K}}_{pq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right)\\ &\quad+ {\mathbf{A}}_{\mathbf{5}}{\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}{\mathbf{A}}_{\mathbf{4}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times p}\left[{\mathbf{K}}_{p\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fp}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{A}}_{\mathbf{4}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{4}}{\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}{\mathbf{A}}_{\mathbf{5}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{9}}{\Delta}_{\left(p{f}^2\right) \times q}\left[{\mathbf{K}}_{q\left(p{f}^2\right)}\mathrm{v}\mathrm{e}\mathrm{c}\left({\mathbf{K}}_{fq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{A}}_{\mathbf{5}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{7}}{\mathbf{K}}_{fq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\boldsymbol{\Psi}}_{\mathbf{FF}}\right){\mathbf{A}}_{\mathbf{6}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{8}}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right){\mathbf{A}}_{\mathbf{6}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{6}}{\mathbf{K}}_{pf}\left({\boldsymbol{\Psi}}_{\mathbf{FF}} \otimes {\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right){\mathbf{A}}_{\mathbf{7}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{8}}{\mathbf{K}}_{ps}\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}} \otimes {\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right){\mathbf{A}}_{\mathbf{7}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{6}}\left({\boldsymbol{\Theta}}_{\mathbf{FF}} \otimes {\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right){\mathbf{A}}_{\mathbf{8}}^{\mathrm{T}} + {\mathbf{A}}_{\mathbf{7}}{\mathbf{K}}_{fq}\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}} \otimes {\left({\boldsymbol{\Psi}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right){\mathbf{A}}_{\mathbf{8}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{4}}{\varDelta}_{p \times \left(p{f}^2\right)}\left[{\mathbf{K}}_{\left(p{f}^2\right)p}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Theta}}_{\mathbf{FF}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{A}}_{\mathbf{9}}^{\mathrm{T}}\\ &\quad+ {\mathbf{A}}_{\mathbf{5}}{\Delta}_{q \times \left(p{f}^2\right)}\left[{\mathbf{K}}_{\left(p{f}^2\right)q}\left(\mathrm{v}\mathrm{e}\mathrm{c}\left({\left({\boldsymbol{\Theta}}_{\mathbf{S}\mathbf{F}}\right)}^{\mathrm{T}}\right) \otimes \mathrm{v}\mathrm{e}\mathrm{c}\left({\boldsymbol{\Psi}}_{\mathbf{FF}}\right)\right)\right]{\mathbf{A}}_{\mathbf{9}}^{\mathrm{T}}\big]{\mathbf{W}}_{\mathbf{4}}^{\mathrm{T}}.\end{aligned} $$

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Chen, SP. (2015). A General SEM Framework for Integrating Moderation and Mediation: The Constrained Approach. In: van der Ark, L., Bolt, D., Wang, WC., Douglas, J., Chow, SM. (eds) Quantitative Psychology Research. Springer Proceedings in Mathematics & Statistics, vol 140. Springer, Cham. https://doi.org/10.1007/978-3-319-19977-1_17

Download citation

Publish with us

Policies and ethics