Abstract
In behavioral, biomedical, and psychological studies, structural equation models (SEMs) have been widely used for assessing relationships between latent variables. Regression-type structural models based on parametric functions are often used for such purposes. In many applications, however, parametric SEMs are not adequate to capture subtle patterns in the functions over the entire range of the predictor variable. A different but equally important limitation of traditional parametric SEMs is that they are not designed to handle mixed data types—continuous, count, ordered, and unordered categorical. This paper develops a generalized semiparametric SEM that is able to handle mixed data types and to simultaneously model different functional relationships among latent variables. A structural equation of the proposed SEM is formulated using a series of unspecified smooth functions. The Bayesian P-splines approach and Markov chain Monte Carlo methods are developed to estimate the smooth functions and the unknown parameters. Moreover, we examine the relative benefits of semiparametric modeling over parametric modeling using a Bayesian model-comparison statistic, called the complete deviance information criterion (DIC). The performance of the developed methodology is evaluated using a simulation study. To illustrate the method, we used a data set derived from the National Longitudinal Survey of Youth.
Similar content being viewed by others
References
Arminger, G., & Küsters, U. (1988). Latent trait models with indicators of mixed measurement level. In R. Langeheine & J. Rost (Eds.), Latent trait and latent class models (pp. 51–73). New York: Plenum.
Bartholomew, D.J., & Knott, M. (1999). Kendall’s library of statistics: Vol. 7. Latent variable models and factor analysis (2nd ed.). London: Arnold Publishers.
Bentler, P.M., & Stein, J.A. (1992). Structural equation models in medical research. Statistical Methods in Medical Research, 1, 159–181.
Berry, S.M., Carroll, R.J., & Ruppert, D. (2002). Bayesian smoothing and regression splines for measurement error problems. Journal of the American Statistical Association, 97, 160–169.
Bollen, K.A. (1989). Structural equations with latent variables. New York: Wiley.
Cai, J.H., Song, X.Y., & Hser, Y.I. (2010). A Bayesian analysis of mixture structural equation models with non-ignorable missing responses and covariates. Statistics in Medicine, 29, 1861–1874.
Cai, J.H., Song, X.Y., Lam, K.H., & Ip, H.S. (2011). A mixture of generalized latent variable models for mixed mode and heterogeneous data. Computational Statistics & Data Analysis, 55, 2889–2907.
Caldwell, B.M., & Bradley, R.H. (1984). Home observation for measurement of the environment. Little Rock: University of Arkansas at Little Rock, Center for Child Development and Education.
Celeux, G., Forbes, F., Robert, C.P., & Titterington, D.M. (2006). Deviance information criteria for missing data models. Bayesian Analysis, 1, 651–674.
Center for Human Resource Research (2004). The national longitudinal surveys NLSY user’s guide, 1979–2004. Columbus: U.S. Department of Labor, Bureau of Labor Statistics.
Cowles, M.K. (1996). Accelerating Monte Carlo Markov chain convergence for cumulative-link generalized linear models. Statistics and Computing, 6, 101–111.
De Boor, C. (1978). A practical guide to splines. New York: Springer.
DiMatteo, I., Genovese, C.R., & Kass, R.E. (2001). Bayesian curve fitting with free-knot splines. Biometrika, 88, 1055–1071.
Dunn, L.M., & Markwardt, F. (1970). Peabody individual achievement test manual. Circle Pines: American Guidance Services.
Dunson, D.B. (2000). Bayesian latent variable models for clustered mixed outcomes. Journal of the Royal Statistical Society. Series B, 62, 355–366.
Eilers, P.H.C., & Marx, B.D. (1996). Flexible smoothing with B-splines and penalties. Statistical Science, 11, 89–121.
Fahrmeir, L., & Raach, A. (2007). A Bayesian semiparametric latent variable model for mixed responses. Psychometrika, 72, 327–346.
Fan, J., & Gijbels, I. (1996). Local polynomial modelling and its applications. London: Chapman & Hall.
Fox, J.P., & Glas, C.A.W. (2003). Bayesian modeling of measurement error in predictor variables using item response theory. Psychometrika, 68, 169–191.
Gelman, A., & Meng, X.L. (1998). Simulating normalizing constant: from importance sampling to bridge sampling to path sampling. Statistical Science, 13, 163–185.
Geman, S., & Geman, D. (1984). Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6, 721–741.
Green, P.J., & Silverman, B.W. (1994). Nonparametric regression and generalized linear models: a roughness penalty approach. London: Chapman & Hall.
Hastings, W.K. (1970). Monte Carlo sampling methods using Markov chains and their application. Biometrika, 57, 97–109.
Huber, P., Scaillet, O., & Victoria-Feser, M.P. (2009). Assessing multivariate predictors of financial market movements: a latent factor framework for ordinal data. Annals of Applied Statistics, 3, 249–271.
Ibrahim, J.G., Chen, M.H., & Sinha, D. (2001). Criterion-based methods for Bayesian model assessment. Statistica Sinica, 11, 419–443.
Imai, K., & van Dyk, D.A. (2005). Bayesian analysis of the multinomial probit model using marginal data augmentation. Journal of Econometrics, 124, 311–334.
Jara, A., Quintana, F., & San Martín, E. (2008). Linear mixed models with skew-elliptical distributions: a Bayesian approach. Computational Statistics & Data Analysis, 52, 5033–5045.
Jöreskog, K.G., & Moustaki, I. (2001). Factor analysis for ordinal variables: a comparison of three approaches. Multivariate Behavioral Research, 36, 347–387.
Kass, R.E., & Raftery, A.E. (1995). Bayes factors. Journal of the American Statistical Association, 90, 773–795.
Kenny, D.A., & Judd, C.M. (1984). Estimating the nonlinear and interactive effects of latent variables. Psychological Bulletin, 96, 201–210.
Lang, S., & Brezger, A. (2004). Bayesian P-splines. Journal of Computational and Graphical Statistics, 13, 183–212.
Lee, S.Y. (2007). Structural equation modeling: a Bayesian approach. Chichester: Wiley.
Lu, Z.H., & Song, X.Y. (2012). Finite mixture varying coefficient models for analyzing longitudinal heterogeneous data. Statistics in Medicine, 31, 544–560.
McCullagh, P., & Nelder, J.A. (1989). Generalized linear models. New York: Chapman & Hall.
Meng, X.L. (1994). Posterior predictive p-values. The Annals of Statistics, 22, 1142–1160.
Metropolis, N., Rosenbluth, A.W., Rosenbluth, M.N., Teller, A.H., & Teller, E. (1953). Equations of state calculations by fast computing machine. Journal of Chemical Physics, 21, 1087–1091.
Moustaki, I. (1996). A latent trait and a latent class model for mixed observed variables. British Journal of Mathematical & Statistical Psychology, 49, 313–334.
Moustaki, I., & Victoria-Feser, M.-P. (2006). Bounded-influence robust estimation in generalized linear latent variable models. Journal of the American Statistical Association, 101, 644–653.
Muthén, B. (1984). A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators. Psychometrika, 49, 115–132.
Nylund, K.L., & Muthén, B. (2007). Deciding on the number of classes in latent class analysis and growth mixture modeling: a Monte Carlo simulation study. Structural Equation Modeling. A Multidisciplinary Journal, 14, 535–569.
Owen, A.B. (2001). Empirical likelihood. Boca Raton: Chapman & Hall.
Pan, J.H., Song, X.Y., & Ip, H.S. (2013, in press). A Bayesian analysis of generalized latent curve mixture models. Statistics and Its Interface.
Panagiotelis, A., & Smith, M. (2008). Bayesian identification, selection and estimation of semiparametric functions in high-dimensional additive models. Journal of Econometrics, 143, 291–316.
Pugesek, B.H., Tomer, A., & von Eye, A. (2003). Structural equation modeling applications in ecological and evolutionary biology. New York: Cambridge University Press.
Ruppert, D., Wand, M.P., & Carroll, R.J. (2003). Semiparametric regression. Cambridge: Cambridge University Press.
San Martín, E., Jara, A., Rolin, J.M., & Mouchart, M. (2011). On the Bayesian nonparametric generalization of IRT-type models. Psychometrika, 76, 385–409.
Sanchez, B.N., Budtz-Jorgenger, E., Ryan, L.M., & Hu, H. (2005). Structural equation models: a review with applications to environmental epidemiology. Journal of the American Statistical Association, 100, 1443–1455.
Schumacker, R.E. & Marcoulides, G.A. (Eds.) (1998). Interaction and nonlinear effects in structural equation models. Mahwah: Lawrence Erlbaum Associates, Publishers.
Shi, J.Q., & Lee, S.Y. (2000). Latent variable model with mixed continuous and polytomous data. Journal of the Royal Statistical Society. Series B, 62, 77–87.
Skrondal, A., & Rabe-Hesketh, S. (2004). Generalized latent variable modeling: multilevel, longitudinal, and structural equation models. Boca Raton: Chapman & Hall/CRC.
Song, X.Y., & Lee, S.Y. (2007). Bayesian analysis of latent variable models with nonignorable missing outcomes from exponential family. Statistics in Medicine, 26, 681–693.
Song, X.Y., Lee, S.Y., Ng, M.C.Y., So, W.Y., & Chan, J.C.N. (2007). Baysian analysis of structural equation models with multinomial variables and an application to type 2 diabetic nephropathy. Statistics in Medicine, 26, 2348–2369.
Song, X.Y., & Lu, Z.H. (2010). Semiparametric latent variable models with Bayesian P-splines. Journal of Computational and Graphical Statistics, 19, 590–608.
Song, X.Y., & Lu, Z.H. (2012). Semiparametric transformation models with Bayesian P-splines. Statistics and Computing, 22, 1085–1098.
Song, X.Y., Pan, J.H., Kwok, T., Vandenput, L., Ohlsson, C., & Leung, P.C. (2010). A semiparametric Bayesian approach for structural equation models. Biometrical Journal, 52, 314–332.
Spiegelhalter, D.J., Best, N.G., Carlin, B.P., & van der Linde, A. (2002). Bayesian measures of model complexity and fit (with discussion). Journal of the Royal Statistical Society. Series B, 64, 583–639.
Spiegelhalter, D.J., Thomas, A., Best, N.G., & Lunn, D. (2003). WinBUGS user manual. Version 1.4. Cambridge: MRC Biostatistics Unit.
Yang, M.G., & Dunson, D.B. (2010). Bayesian semiparametric structural equation models with latent variables. Psychometrika, 75, 675–693.
Yang, M.G., Dunson, D.B., & Baird, D. (2010). Semiparametric Bayes hierarchical models with mean and variance constraints. Computational Statistics & Data Analysis, 54, 2172–2186.
Zill, N. (1985). Behavior problem scales developed from the 1981 child health supplement to the national health interview survey. Washington: Child Trends, Inc.
Acknowledgements
This paper is supported by the grants GRF 446609 and GRF 404711 from the Research Grant Council of the Hong Kong Special Administration Region; NSFC 11101443 from the National Natural Science Foundation of China, and the Fundamental Research Funds for the Central Universities. The last author is supported by the NIH grant R01AG031827A and 1U01HL101066. This study is also supported by the high-performance grid computing platform of Sun Yat-sen University.
Author information
Authors and Affiliations
Corresponding author
Appendix: The Full Conditional Distributions
Appendix: The Full Conditional Distributions
The full conditional distributions involved in the Gibbs sampler are given as follows.
(1) The full conditional distribution of Ω: \(p(\boldsymbol{\varOmega} |\mathbf{D},\mathbf{Z}^{*},\mathbf{W},\boldsymbol{\theta}_{*})= \prod_{i=1}^{n} p(\boldsymbol{\omega}_{i}|\mathbf{d}_{i},\mathbf {z}_{i}^{*},\mathbf{w}_{i},\boldsymbol{\theta}_{*})\), and
(2) The full conditional distribution of W: \(p(\mathbf {W}|\mathbf{D} ,\mathbf{Z}^{*},\boldsymbol{\varOmega},\boldsymbol{\theta}_{*})=\prod_{i=1}^{n} \prod_{j=r_{3}+1}^{r_{4}} p(\mathbf{w}_{ij}|u_{ij},\allowbreak\boldsymbol{\omega }_{i}, \boldsymbol{\theta}_{*})\), and
where I L−1 is an identity matrix with order L−1, and
The distribution of p(w ij |u ij ,ω i ,θ ∗) is a truncated multivariate normal distribution. Following Song et al. (2007), we use the following partitioning of variables to simulate observations {w ij,1,…,w ij,L−1} via Gibbs sampler. Let w ij,−l be w ij with w ij,l deleted, the distribution of w ij,l given u ij , w ij,−l , ω i , and θ ∗ is a univariate truncated normal distribution as follows:
(3) The full distribution of b l is
with the constraint \(\mathbf{1}_{n}'\mathbf{B}_{l}^{c} \mathbf{b}_{l}=0\), where \(\boldsymbol{\varSigma}_{bl}^{*}=({\mathbf{B}_{l}^{c}}'\mathbf {B}_{l}^{c}/\psi_{\delta}+ \mathbf{M}_{bl}/\tau_{bl})^{-1}\), \(\mathbf{b}_{l}^{*}=\boldsymbol{\varSigma}_{bl}^{*}{\mathbf {B}_{l}^{c}}'\boldsymbol{\eta}_{c}^{*}/\psi_{\delta}\), and \(\boldsymbol{\eta}_{c}^{*}=(\eta_{c1}^{*}, \ldots,\eta_{cn}^{*})'\) with
To sample an observation b l from its full conditional distribution with the constraint, we can sample an observation \(\mathbf{b}_{l}^{(\mathrm{new})}\) from \(N[\mathbf{b}_{l}^{*},\boldsymbol{\varSigma}_{bl}^{*}]\), then transform \(\mathbf{b}_{l}^{(\mathrm{new})}\) to b l as follows:
(4) The full distribution of γ l is
with the constraint \(\mathbf{1}_{n}'\mathbf{B}_{l} \boldsymbol{\gamma}_{l}=0\), where \(\boldsymbol{\varSigma}_{\gamma l}^{*}=(\mathbf{B}_{l}'\mathbf {B}_{l}/\psi_{\delta}+ \mathbf{M}_{\gamma l}/\tau_{\gamma l})^{-1}\), \(\boldsymbol{\gamma}_{l}^{*}=\boldsymbol{\varSigma}_{\gamma l}^{*}\mathbf {B}_{l}'\boldsymbol{\eta}^{*}/\psi_{\delta}\), and \(\boldsymbol{\eta}^{*}=(\eta_{1}^{*}, \ldots,\eta_{n}^{*})'\) with
Similar to b l , we can sample an observation \(\boldsymbol {\gamma}_{l}^{( \mathrm{new})}\) from \(N[\boldsymbol{\gamma}_{l}^{*},\boldsymbol {\varSigma}_{\gamma l}^{*}]\), then transform \(\boldsymbol{\gamma}_{l}^{(\mathrm{new})}\) to γ l as follows:
(5) The full conditional distributions of τ b and τ γ are as follows:
(6) The full conditional distribution of μ is given as follows:
where \(\sigma_{j}^{*}=(\sigma_{j0}^{-1}+n \psi_{j}^{-1})^{-1}\), \(\mu_{j}^{*}=\sigma_{j}^{*}(n \bar{z}_{j}^{*}/\psi_{j}+\mu_{j0}/\sigma_{j0})\), with \(\bar{z}_{j}^{*}=n^{-1}\sum _{i=1}^{n} (z_{ij}^{*}-\boldsymbol{\varLambda}_{j}'\boldsymbol{\omega}_{i})\), \(\mu_{j}^{**}=\sigma_{j}^{*}(n \bar{y}_{j}/\psi_{j}+\mu_{j0}/\sigma_{j0})\) with \(\bar{y}_{j}=n^{-1}\sum_{i=1}^{n} (y_{ij}-\boldsymbol{\varLambda}_{j}'\boldsymbol{\omega}_{i})\), \(\boldsymbol{\varSigma}_{\mu j}=(n\mathbf{I}_{L-1}+\mathbf{H}_{\mu j0}^{-1})^{-1}\), \(\tilde {\boldsymbol{\mu}}_{j}=\boldsymbol{\varSigma}_{\mu j}(n\bar{\mathbf{w}}_{j}+\mathbf{H}_{\mu j0}^{-1}\boldsymbol{\mu }_{j0})\) with \(\bar{\mathbf{w}}_{j}=n^{-1} \sum_{i=1}^{n} (\mathbf{w}_{ij}-\mathbf{1}_{L-1}\boldsymbol {\varLambda}_{j}'\boldsymbol{\omega}_{i})\).
(7) The full conditional distributions of Λ and Ψ are given as follows:
where \(\mathbf{H}_{j}^{*}=(\mathbf{H}_{j0}^{-1}+\boldsymbol{\varOmega }\boldsymbol{\varOmega}')^{-1}\), \(\boldsymbol{\varLambda}_{j}^{*}=\mathbf{H}_{j}^{*} [\mathbf{H}_{j0}^{-1}\boldsymbol{\varLambda}_{j0}+\boldsymbol {\varOmega}\widetilde{\mathbf{Z}}^{*}_{j}]\), \(\boldsymbol{\varLambda}_{j}^{**}=\mathbf{H}_{j}^{*} [\mathbf{H}_{j0}^{-1}\boldsymbol{\varLambda}_{j0}+\boldsymbol {\varOmega}\widetilde{\mathbf{Y}}_{j}]\), \(\beta_{j}^{*}=\beta_{j0}+2^{-1}[\widetilde{\mathbf{Z}}_{j}^{*'} \widetilde{\mathbf{Z}}^{*}_{j}-{\boldsymbol{\varLambda}^{*}_{j}}'\mathbf {H}_{j}^{*-1}{\boldsymbol{\varLambda}^{*}_{j}} +\boldsymbol{\varLambda}_{j0}'\mathbf{H}_{j0}^{-1}\boldsymbol {\varLambda}_{j0}]\), \(\beta_{j}^{**}=\beta_{j0}+2^{-1}[\widetilde{\mathbf{Y}}_{j}' \widetilde{\mathbf{Y}}_{j}-{\boldsymbol{\varLambda}^{**}_{j}}'\mathbf {H}_{j}^{*-1} {\boldsymbol{\varLambda}^{**}_{j}}+\boldsymbol{\varLambda }_{j0}'\mathbf{H}_{j0}^{-1}\boldsymbol{\varLambda}_{j0}]\), with \(\widetilde{\mathbf{Z}}_{j}^{*}=(z_{1j}^{*}-\mu_{j},\ldots ,z_{nj}^{*}-\mu_{j})'\) and \(\widetilde{\mathbf{Y}}_{j}=(y_{1j}-\mu_{j},\ldots,y_{nj}-\mu_{j})'\). Finally, \(\mathbf{H}_{j}^{**}=(\mathbf{H}_{j0}^{-1}+(L-1)\boldsymbol {\varOmega}\boldsymbol{\varOmega}')^{-1}\) and \(\boldsymbol{\varLambda}_{j}^{***}=\mathbf{H}_{j}^{**} [\mathbf{H}_{j0}^{-1}\boldsymbol{\varLambda}_{j0}+\boldsymbol {\varOmega}\widetilde{\mathbf{W}}_{j}]\) with \(\widetilde{\mathbf{W}}_{j}=(\mathbf{1}_{L-1}' (\mathbf {w}_{1j}-\nobreak\boldsymbol{\mu}_{j} ),\ldots, \mathbf{1}_{L-1}' (\mathbf{w}_{nj}-\boldsymbol{\mu}_{j}) )'\).
(8) The full conditional distributions of ψ δ and Φ are as follows:
where \(\beta_{\delta}^{*}=\beta_{\delta0}+2^{-1} [\eta_{i}-\sum_{l=1}^{m} \sum_{k=1}^{K_{bl}} b_{lk} B_{lk}^{c}(c_{il})-\sum_{l=1}^{q_{2}} \sum_{k=1}^{K_{l}} \gamma_{lk} B_{lk}(\varPhi^{*}(\xi_{i})) ]^{2}\), and \(\mathbf{R}^{*}=\mathbf{R}_{0}+\sum_{i=1}^{n} \boldsymbol{\xi}_{i} \boldsymbol{\xi}_{i}'\).
(9) The full conditional distributions of α and Z ∗ are given as follows. For j=1,…,r 1, let \(\mathbf{Z}_{j}^{*}=(z_{1j}^{*},\ldots,z_{nj}^{*})'\), Z j =(z 1j ,…,z nj )′ we have \(p(\boldsymbol{\alpha},\mathbf{Z}^{*}|\mathbf{D},\mathbf {W},\boldsymbol{\varOmega},\boldsymbol{\theta}_{*})=\prod_{j=1}^{r_{1}} p(\boldsymbol{\alpha}_{j},\mathbf{Z}_{j}^{*}|\mathbf{Z}_{j},\allowbreak \boldsymbol {\varOmega}, \boldsymbol{\theta}_{*})\), and \(p(\boldsymbol{\alpha}_{j},\mathbf{Z}^{*}_{j}|\mathbf {Z}_{j},\boldsymbol{\varOmega},\boldsymbol{\theta}_{*})= p(\boldsymbol{\alpha}_{j}|\mathbf{Z}_{j},\boldsymbol{\varOmega },\boldsymbol{\theta}_{*}) p(\mathbf{Z}^{*}_{j}|\boldsymbol{\alpha}_{j}, \mathbf {Z}_{j},\boldsymbol{\varOmega},\boldsymbol{\theta}_{*})\), with
Finally, \(p(\mathbf{Z}^{*}_{j}|\boldsymbol{\alpha}_{j},\mathbf {Z}_{j},\boldsymbol{\varOmega},\boldsymbol{\theta}_{*})= \prod_{i=1}^{n} p(z^{*}_{ij}|\boldsymbol{\alpha}_{j},z_{ij}, \boldsymbol {\omega}_{i}, \boldsymbol{\theta}_{*})\), and
Rights and permissions
About this article
Cite this article
Song, XY., Lu, ZH., Cai, JH. et al. A Bayesian Modeling Approach for Generalized Semiparametric Structural Equation Models. Psychometrika 78, 624–647 (2013). https://doi.org/10.1007/s11336-013-9323-7
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11336-013-9323-7