Abstract
The paper proposes a composite likelihood estimation approach that uses bivariate instead of multivariate marginal probabilities for ordinal longitudinal responses using a latent variable model. The model considers time-dependent latent variables and item-specific random effects to be accountable for the interdependencies of the multivariate ordinal items. Time-dependent latent variables are linked with an autoregressive model. Simulation results have shown composite likelihood estimators to have a small amount of bias and mean square error and as such they are feasible alternatives to full maximum likelihood. Model selection criteria developed for composite likelihood estimation are used in the applications. Furthermore, lower-order residuals are used as measures-of-fit for the selected models.
Similar content being viewed by others
References
Arnold, B.C., & Strauss, D. (1991). Pseudolikelihood estimation: some examples. Sankya: The Indian Journal of Statistics, 53, 233–243.
Azzalini, A. (1983). Maximum likelihood estimation of order m for stationary stochastic processes. Biometrika, 70, 381–387.
Bartholomew, D.J., & Leung, S.O. (2002). A goodness-of-fit test for sparse 2p contingency tables. British Journal of Mathematical & Statistical Psychology, 55, 1–15.
Besag, J.E. (1974). Spatial interaction and the statistical analysis of lattice systems (with discussion). Journal of the Royal Statistical Society, Series B, 36, 192–236.
Cagnone, S., Moustaki, I., & Vasdekis, V. (2009). Latent variable models for multivariate longitudinal ordinal responses. British Journal of Mathematical & Statistical Psychology, 62, 401–415.
Cai, L. (2010). A two-tier full-information item factor analysis model with applications. Psychometrika, 75, 581–612.
Cai, L., Maydeu-Olivares, A., Coffman, D.L., & Thissen, D. (2006). Limited information goodness-of-fit testing of item response theory models for sparse 2p tables. British Journal of Mathematical & Statistical Psychology, 59, 173–194.
Cox, D.R. (1975). Partial likelihood. Biometrika, 62, 269–274.
Cox, D.R., & Reid, N. (2004). A note on pseudolikelihood constructed from marginal densities. Biometrika, 91, 729–737.
Dunson, B. (2003). Dynamic latent trait models for multidimensional longitudinal data. Journal of the American Statistical Association, 98, 555–563.
Feddag, M., & Bacci, S. (2009). Pairwise likelihood for the longitudinal mixed Rasch model. Computational Statistics & Data Analysis, 53, 1027–1037.
Geys, H., Molenberghs, G., & Ryan, L.M. (1999). Pseudolikelihood modeling of multivariate outcomes in developmental toxicology. Journal of the American Statistical Association, 94, 734–745.
Gibbons, R.D., & Hedeker, D. (1992). Full-information item bifactor analysis. Psychometrika, 57, 423–436.
Heagerty, P., & Lele, S. (1998). A composite likelihood approach to binary spatial data. Journal of the American Statistical Association, 93, 1099–1111.
Huber, P., Ronchetti, E., & Victoria-Feser, M.-P. (2004). Estimation of generalized linear latent variable models. Journal of the Royal Statistical Society, Series B, 66, 893–908.
Joe, H., & Maydeu-Olivares, A. (2010). A general family of limited information goodness-of-fit statistics for multinomial data. Psychometrika, 75, 393–419.
Jöreskog, K.G., & Moustaki, I. (2001). Factor analysis of ordinal variables: a comparison of three approaches. Multivariate Behavioral Research, 36, 347–387.
Lindsay, B. (1988). Composite likelihood methods. In N.U. Prabhu (Ed.), Statistical inference from stochastic processes (pp. 221–239). Providence: Am. Math. Soc.
Louis, T.A. (1982). Finding the observed information matrix when using the EM algorithm. Journal of the Royal Statistical Society, Series B, 44, 226–233.
Maydeu-Olivares, A., & Joe, H. (2005). Limited and full-information estimation and goodness-of-fit testing in 2n contingency tables: a unified framework. Journal of the American Statistical Association, 100, 1009–1020.
Maydeu-Olivares, A., & Joe, H. (2006). Limited information goodness-of-fit testing in multidimensional contingency tables. Psychometrika, 71, 713–732.
Rabe-Hesketh, S., Skrondal, A., & Pickles, A. (2005). Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects. Journal of Econometrics, 128, 301–323.
Reiser, M. (1996). Analysis of residuals for the multinomial item response model. Psychometrika, 61, 509–528.
Ronchetti, E. (1997). Robustness aspects of model choice. Statistica Sinica, 7, 327–338.
Schilling, S., & Bock, R. (2005). High-dimensional maximum marginal likelihood item factor analysis by adaptive quadrature. Psychometrika, 70, 533–555.
Stone, M. (1977). An asymptotic equivalence of choice of model by cross-validation and Akaike’s criterion. Journal of the Royal Statistical Society, Series B, 39, 44–47.
Straud, A.H., & Sechrest, D. (1966). Gaussian quadrature formulas. Englewood Cliffs: Prentice Hall.
Tsonaka, R., & Moustaki, I. (2007). Parameter constraints in generalized linear latent variable models. Computational Statistics & Data Analysis, 51, 4164–4177.
Varin, C. (2008). On composite marginal likelihoods. Advances in Statistical Analysis, 92, 1–28.
Varin, C., Reid, N., & Firth, D. (2011). An overview of composite likelihood methods. Statistica Sinica, 21, 5–42.
Varin, C., & Vidoni, P. (2005). A note on composite likelihood inference and model selection. Biometrika, 92, 519–528.
Acknowledgements
The authors would like to thank the referees for their helpful comments which improved the paper a lot. This research was partially funded by the Basic Research Funding Program 2009–2010 of the Athens University of Economics and Business and by grants from the Italian Ministry of University and Research (MIUR): PRIN2008 “Latent structure analysis: New boundaries in statistical methods and models.”
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
1.1 A.1 Computational Details
The first and second derivatives of the densities involved in the calculation of the E-step of Section 2.2 and the standard errors of Section 2.3 are presented. The computational issues that emerge involve both the log-likelihood of the univariate probabilities of response and that of the latent variables. The first issue considers the first and the second derivative of \(\log (\gamma_{it}^{(s)}-\gamma_{it}^{(s-1)})\). It is easily seen that
where
The second derivative of \(\log(\gamma_{it}^{(s)}-\gamma _{it}^{(s-1)})\) is,
where
Regarding the log-likelihood of the latent variables, two cases will be discriminated: the first case involves two time-dependent latent variables and two item random effects (z t ,z t′,u i ,u i′), when, for example, a pair (y it ,y i′t′) is considered; whereas, the other case involves one time-dependent latent variable and two item random effects (z t ,u i ,u i′) corresponding to a pair (y it ,y i′t ). The covariance matrix of z t and z t′ is
with
Therefore, the logarithm of the joint density of (z t ,z t′,u i ,u i′) is
where \(\omega_{11}=\phi^{2(t'-1)}\sigma_{1}^{2}+A^{*}_{t'}\), \(\omega _{12}=\phi^{t+t'-2}\sigma_{1}^{2}+\phi^{t'-t}A_{t}^{*}\), \(\omega_{22}=\phi ^{2(t-1)}\sigma_{1}^{2}+A_{t}^{*}\). With respect to the parameters, ϕ or \(\sigma_{1}^{2}\), the derivatives of the logarithm of the joint density, are
and
The first derivative with respect to the parameters \(\sigma^{2}_{uk}\) is
The second derivative with respect to θ k and θ l :
where \(\theta_{k},\theta_{l}=\sigma_{1}^{2},\phi\) and
where α=ω 11,ω 12,ω 22. The second partial derivative of the logarithm of the joint density with respect to \(\sigma^{2}_{ui}\) or \(\sigma^{2}_{ui'}\) is
When the k indices are different, this second derivative is zero.
When the joint density of the triplet (z t ,u i ,u i′) is considered, we set |Σ|=Var(z t ), and ω 11=1 and ω 12=ω 22=0.
Rights and permissions
About this article
Cite this article
Vasdekis, V.G.S., Cagnone, S. & Moustaki, I. A Composite Likelihood Inference in Latent Variable Models for Ordinal Longitudinal Responses. Psychometrika 77, 425–441 (2012). https://doi.org/10.1007/s11336-012-9264-6
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11336-012-9264-6