Abstract
Generalized structured component analysis (GSCA) is a component-based approach to structural equation modeling, where components of observed variables are used as proxies for latent variables. GSCA has thus far focused on analyzing two-way (e.g., subjects by variables) data. In this paper, GSCA is extended to deal with three-way data that contain three different types of entities (e.g., subjects, variables, and occasions) simultaneously. The proposed method, called three-way GSCA, permits each latent variable to be loaded on two types of entities, such as variables and occasions, in the measurement model. This enables to investigate how these entities are associated with the latent variable. The method aims to minimize a single least squares criterion to estimate parameters. An alternating least squares algorithm is developed to minimize this criterion. We conduct a simulation study to evaluate the performance of three-way GSCA. We also apply three-way GSCA to real data to demonstrate its empirical usefulness.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Acar, E., & Yener, B. (2009). Unsupervised multiway data analysis: A literature survey. IEEE Transactions on knowledge and Data Engineering, 21(1), 6–20.
Andersen, C. M., & Bro, R. (2003). Practical aspects of PARAFAC modeling of fluorescence excitation-emission data. Journal of Chemometrics, 17(4), 200–215.
Bezdek, J. C. (1974). Numerical taxonomy with fuzzy sets. Journal of Mathematical Biology, 1(1), 57–71.
Biederman, J., Monuteaux, M. C., Greene, R. W., Braaten, E., Doyle, A. E., & Faraone, S. V. (2001). Long-term stability of the child behavior check list in a clinical sample of youth with attention deficit hyperactivity disorder. Journal of Clinical Child Psychology, 30(4), 492–502.
Bollen, K. A., Kirby, J. B., Curran, P. J., Paxton, P. M., & Chen, F. (2007). Latent variable models under misspecification: Two-stage least squares (2SLS) and maximum likelihood (ML) estimators. Sociological Methods & Research, 36(1), 48–86.
Bradley, R. H., & Caldwell, B. M. (1984). The HOME inventory and family demographics. Developmental Psychology, 20, 315–320.
Bro, R. (1996). Multiway calidration. multilinear PLS. Journal of Chemometrics, 10, 47–61.
Bro, R. (1997). PARAFAC. Tutorial and applications. Chemometrics and Intelligent Laboratory Systems, 38(2), 149–171.
Bro, R., & Smilde, A. K. (2003). Centering and scaling in component analysis. Journal of Chemometrics, 17(1), 16–33.
Center for Human Resource Research. (2004). NLSY79 Child and Young Adult Data Users Guide. Columbus. OH: Ohio State University.
Christensen, J., Becker, E. M., & Frederiksen, C. S. (2005). Fluorescence spectroscopy and PARAFAC in the analysis of yogurt. Chemometrics and Intelligent Laboratory Systems, 75(2), 201–208.
Cox, R. W. (1996). AFNI: Software for analysis and visualization of functional magnetic resonance neuroimages. Computers and Biomedical research, 29(3), 162–173.
de Leeuw, J., Young, F. W., & Takane, Y. (1976). Additive structure in qualitative data: An alternating least squares method with optimal scaling features. Psychometrika, 41, 471–514.
De Roover, K., Ceulemans, E., Timmerman, M. E., Vansteelandt, K., Stouten, J., & Onghena, P. (2012). Clusterwise simultaneous component analysis for analyzing structural differences in multivariate multiblock da ta. Psychological Methods, 17(1), 100.
Efron, B. (1982). The jackknife, the bootstrap and other resampling plans. Philadelphia: SIAM.
Ferrer, E., & McArdle, J. J. (2010). Longitudinal modeling of develo mental changes in psychological research. Current Directions in Psycho logical Science, 19(3), 149–154.
Germond, L., Dojat, M., Taylor, C., & Garbay, C. (2000). A cooperative framework for segmentation of MRI brain scans. Artificial Intelligence in Medicine, 20(1), 77–93.
Harshman, R. A. (1970). Foundations of the PARAFAC procedure: Models and conditions for an” explanatory” multimodal factor analysis. UCLA Working Papers in Phonetics, 16, 1–84.
Hartigan, J. A., & Wong, M. A. (1979). Algorithm AS 136: A k-means clustering algorithm. Applied Statistics, 100–108.
Hwang, H., Desarbo, W. S., & Takane, Y. (2007a). Fuzzy clusterwise generalized structured component analysis. Psychometrika, 72(2), 181–198.
Hwang, H., Ho, M. R., & Lee, J. (2010). Generalized structured component analysis with latent interactions. Psychometrika, 75(2), 228–242.
Hwang, H., & Takane, Y. (2004). Generalized structured component analysis. Psychometrika, 69(1), 81–99.
Hwang, H., & Takane, Y. (2014). Generalized structured component analysis: A component-based approach to structural equation modeling. Boca Raton, FL: Chapman & Hall/CRC Press.
Hwang, H., Takane, Y., & Malhotra, N. (2007b). Multilevel generalized structured component analysis. Behaviormetrika, 34(2), 95–109.
Kroonenberg, P. M. (1987). Multivariate and longitudinal data on growing children. Solutions using a three-mode principal component analysis and some comparison results with other approaches. In F. M. J. M. P. J. Janssen (Ed.), Data analysis. The ins and outs of solving real problems. (pp. 89–112). New York: Plenum.
Kroonenberg, P. M. (2008). Applied multiway data analysis (Vol. 702). Wiley.
Kuze, T., Goto, M., Ninomiya, K., Asano, K., Miyazawa, S., Munekata, H., et al. (1985). A longitudinal study on development of adolescents’ social attitudes. Japanese Psychological Research, 27(4), 195–205.
Lei, P. W. (2009). Evaluating estimation methods for ordinal data in structural equation modeling. Quality & Quantity, 43(3), 495–507.
Mun, E. Y., von Eye, A., Bates, M. E., & Vaschillo, E. G. (2008). Finding groups using model-based cluster analysis: Heterogeneous emotional self-regulatory processes and heavy alcohol use risk. Developmental Psychology, 44(2), 481.
Olivieri, A. C., Escandar, G. M., Goicoechea, H. C., & de la Peña, A. M. (2015). Fundamentals and analytical applications of multi-way calibration (Vol. 29). Elsevier.
Oort, F. J. (2001). Three-mode models for multivariate longitudinal data. British Journal of Mathematical and Statistical Psychology, 54(1), 49–78.
Peterson, J. L., & Zill, N. (1986). Marital disruption, parent-child relation ships, and behavioral problems in children. Journal of Marriage and the Family, 48(2), 295–307.
Ramsay, J. O., & Silverman, B. W. (2005). Functional data analysis (2nd ed.). New York: Springer.
Tenenhaus, A., Le Brusquet, L., & Lechuga, G. (2015). Multiway Regularized Generalized Canonical Correlation Analysis. In 47èmes Journée de Statistique de la SFdS (JdS 2015).
Thirion, B., & Faugeras, O. (2003). Dynamical components analysis of fMRI data through kernel PCA. NeuroImage, 20(1), 34–49.
Totsika, V., & Sylva, K. (2004). The home observation for measurement of the environment revisited. Child and Adolescent Mental Health, 9(1), 25–35.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
The ALS algorithm repeats the following three steps until convergence.
Step 1. Update weights (w p ’s) for fixed \( {\mathbf{c}}_{p}^{\text{J} } \), \( {\mathbf{c}}_{p}^{\text{K} } \), and B. This is equivalent to minimizing
subject to \( {\varvec{\upgamma}}_{p}^{{\prime }} {\varvec{\upgamma}}_{p} = 1 \), where \( {\mathbf{q}}_{p} = ({\mathbf{c}}_{p}^{\text{K} } \, \otimes \,{\mathbf{c}}_{p}^{\text{J} } ) \), \( {\mathbf{t}}_{p} = {\mathbf{e}}_{p}^{{\prime }} - {\mathbf{b}}_{p}^{{\prime }} \), and \( {\varvec{\Delta}}_{p} = {\varvec{\Gamma}}^{( - p)} {\mathbf{B}}^{( - p)} - {\varvec{\Gamma}}^{( - p)} \). In (A.1), \( \varvec\Gamma ^{{\left( { - p} \right)}} \) and \( {\mathbf{B}}^{{\left( { - p} \right)}} \) indicate Γ and B, whose columns are all zero vectors except the pth column, respectively, and \( {\mathbf{e}}_{p}^{{\prime }} \) indicates a 1 by P vector, whose elements are all zero except the pth element being unity. Based on (1), (A.1) can be re-expressed as
Solving \( \frac{\partial \phi }{{\partial} \mathbf{w}_{p} } \) = 0, w p is updated by
Subsequently, \( {\varvec{\upgamma}}_{p} \) is updated by \( \varvec\gamma_{p} = {\mathbf{X}}_{p} \widehat{{\mathbf{w}}}_{p} \) and normalized to satisfy the constraint \( {\varvec{\upgamma}}_{p}^{{\prime }} {\varvec{\upgamma}}_{p} = 1 \).
Step 2. Update \( {\mathbf{c}}_{p}^{\text{J} } \) and \( {\mathbf{c}}_{p}^{\text{K} } \) for fixed w p and B. This is equivalent to applying parallel factor analysis (PARAFAC) (Harshman 1970), subject to \( {\mathbf{c}}_{p}^{{\text{J} {\prime }}} {\mathbf{c}}_{p}^{\text{J} } = 1 \), and \( {\mathbf{c}}_{p}^{{\text{K} {\prime }}} {\mathbf{c}}_{p}^{\text{K} } = 1 \). We can simply use the ALS algorithm for PARAFAC to update \( {\mathbf{c}}_{p}^{\text{J} } \) and \( {\mathbf{c}}_{p}^{\text{K} } \) (Acar and Yener 2009; Harshman 1970; Olivieri et al. 2015).
Step 3. Update B for fixed w p , \( {\mathbf{c}}_{p}^{\text{J} } \) and \( {\mathbf{c}}_{p}^{\text{K} } \). This is equivalent to minimizing
where vec(S) is a super vector formed by stacking all columns of S in order, u denotes free parameters to be estimated in vec(B), and Ψ is a matrix consisting of the columns of \( {\mathbf{I}}_{p} \, \otimes \,{\varvec{\Gamma}} \) corresponding to the free parameters of vec(B) The estimate of u is obtained by
Then, \( \widehat{\mathbf{{B}}} \) is reconstructed from \( \widehat{\mathbf{{u}}} \).
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Choi, J.Y., Yang, S., Tenenhaus, A., Hwang, H. (2018). Three-Way Generalized Structured Component Analysis. In: Wiberg, M., Culpepper, S., Janssen, R., González, J., Molenaar, D. (eds) Quantitative Psychology. IMPS 2017. Springer Proceedings in Mathematics & Statistics, vol 233. Springer, Cham. https://doi.org/10.1007/978-3-319-77249-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-77249-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77248-6
Online ISBN: 978-3-319-77249-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)