Abstract
This article presents applications of different growth mixture models considering unobserved heterogeneity within the framework of Mplus (Muthén & Muthén, 2001a, 2001b, 2004). Latent class growth mixture models are discussed under special consideration of count variables that can be incorporated into the mixtures via the Poisson and the zero-inflated Poisson model. Fourwave panel data from a German criminological youth study (Boers et al., 2002) is used for the model analyses. Three classes can be obtained from the data: Adolescents with almost no deviant and delinquent activities, a medium proportion of adolescents with a low increase of delinquency, and a small number with a larger growth starting on a higher level. Considering the zero inflation of the data results in better model fits compared to the Poisson model only. Linear growth specifications are almost sufficient. The conditional application of the mixture models includes gender and educational level of the schools as time-independent predictors that are able to explain a large proportion of the latent class distribution. The stepwise procedure from latent class growth analysis to growth mixture modeling is feasible for longitudinal analyses where individual growth trajectories are heterogenous even when the dependent variable under study cannot be treated as a continuous variable.
References
Bentler, P. M. (2001). EQS 6: Structural equations program manual. . Encino: Multivariate SoftwareDempster, A. P. , Laird, N. M. , Rubin, D. B. et al (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39, 1– 38Duncan, T. E. , Duncan, S. C. , Strycker, L. A. , Li, F. , Alpert, A. et al (1999). An introduction to latent variable growth curve modeling: Concepts, issues, and applications. . Mahwah: Lawrence ErlbaumD’Unger, A. , Land, K. C. , McCall, P. L. , Nagin, D. S. et al (1998). How many latent classes of delinquent/criminal careers? Results from mixed Poisson regression analyses of the London, Philadelphia and Racine cohort studies. American Journal of Sociology, 103, 1593– 1630Farrington, D. P. , West, D. J. (1990). The Cambridge study in delinquent devlopment: A longterm follow-up of 411 London males. In H. J. Kerner, G. Kaiser (Eds.), Kriminalität: Persönlichkeit, Lebensgeschichte und Verhalten (pp. 115-138). Berlin: SpringerJeffries, N. O. (2003). A note on “Testing the number of components in a normal mixture.”. Biometrika, 90, 991– 994Jones, B. L. , Nagin, D. S. , Roeder, K. et al (2001). A SAS procedure based on mixture models for estimating developmental trajectories. Sociological Methods & Research, 29, 374– 393Jöreskog, K. G. , Sörbom, D. (2004). LISREL 8.7 for Windows. . Lincolnwood: Scientific Software International, IncKreuter, F. (2004). Longitudinal models with zero inflation. Unpublished manuscript . University of California at Los Angels, StatisticsLambert, D. (1992). Zero-inflated Poisson regression with an application to defects in manufacturing.. Technometrics, 34, 1– 13Land, K. C. , McCall, P. L. , Nagin, D. S. et al (1996). A comparison of Poisson, negative binomial, and semiparametric mixed Poisson regression models with empirical applications to criminal careers data. Sociological Methods & Research, 24, 387– 442Li, F. , Duncan, T. E. , Duncan, S. C. , Acock, A. et al (2001). Latent growth modeling of longitudinal data: A finite growth mixture modeling approach. Structural Equation Modeling, 8, 493– 530Lo, Y. , Mendell, N. R. , Rubin, D. B. et al (2001). Testing the number of components in a normal mixture. Biometrika, 88, 767– 778McArdle, J. J. (1988). Dynamic but structural equation modeling of repeated measures data. In J. R. Nesselroade, R. B. Cattell (Eds.), Handbook of multivariate experimental psychology (pp. 561-614). New York: PlenumMcArdle, J. J. , Epstein, D. (1987). Latent growth curves within developmental structural equation models. Child Development, 58, 110– 133McDermott, S. , Nagin, D. S. (2001). Same or different? Comparing offender groups and covariates over time. Sociological Methods & Research, 29, 282– 318Muthén, B. , Shedden, K. (1999). Finite mixture modeling with mixture outcomes using the EM algorithm. Biometrics, 55, 463– 469Muthén, B. (1991). Analysis of longitudinal data using latent variable models with varying parameters. In L. Collins, J. Horn (Eds.), Best methods for the analysis of change (pp. 1-17). Washington, DC: American Psychological AssociationMuthén, B. (1997). Latent variable modeling with longitudinal and multilevel data. In A. Raftery (Ed.), Sociological methodology (pp. 453-480). Boston: Blackwell PublishersMuthén, B. (2001a). Latent variable mixture modeling. In G. A. Marcoulides, R. E. Schumacker (Eds.), New developments and techniques in structural equation modeling (pp. 1-33). Lawrence Erlbaum AssociatesMuthén, B. (2001b). Second-generation structural equation modeling with a combination of categorical and continuous latent variables: New opportunities for latent class/latent growth modeling. In L. M. Collins, A. Sayer (Eds.), New methods for the analysis of change (pp. 291-322). Washington, DC: American Psychological AssociationMuthén, B. O. (2002). Beyond SEM: General latent variable modeling. Behaviormetrika, 29, 81– 117Muthén, B. O. (2003). Statistical and substantive checking in growth mixture modeling: Comment on Bauer and Curran (2003). Psychological Methods, 8, 369– 377Muthén, B. O. (2004). Latent variable analysis: Growth mixture modeling and related techniques for longitudinal data. In D. Kaplan (Ed.), The Sage handbook of quantitative methodology for the social sciences (pp. 345-368). Thousand Oaks: SageMuthén, B. O , Curran, P. J. (1997). General longitudinal modeling of individual differences in experimental designs: A latent variable framework for analysis and power estimation. Psychological Methods, 2, 371– 402Muthén, L. , Muthén, B. O. (2001). M plus: The comprehensive modeling program for applied researchers, User’s guide . (2nd ed.). Los Angeles: Muthén & MuthénMuthén, L. , Muthén, B. O. (2004). M plus user’s guide . (3rd ed.). Los Angeles: Muthén & MuthénNagin, D. S. (1999). Analyzing developmental trajectories: A semi-parametric, group-based approach. Psychological Methods, 4, 139– 157Nagin, D. S. (2005). Group-based modeling of development . Cambridge: Harvard University PressNagin, D. S. , Land, K. C. (1993). Age, criminal careers, and population heterogeneity: Specification and estimation of a nonparametric, mixed Poisson model. Criminology, 31, 327– 362Pöge, A. (2005). Persönliche Codes bei Längsschnittstudien: Ein Erfahrungsbericht. ZA-Information, 8, 50– 69Rao, C. R. (1958). Some statistical methods for comparison of growth curves. Biometrics, 14, 1– 17Roeder, K. , Lynch, K. G. , Nagin, D. S. et al (1999). Modeling uncertainty in latent class membership: A case study in criminology. Journal of the American Statistical Association, 94, 766– 776Ross, S. M. (1993). Introduction to probability models. (5th ed.). New York: Academic PressTracy, P. E. , Wolfgang, M. E. , Figlio, R. M. et al (1990). Delinquency in two birth cohorts. . New York: PlenumTremblay, R. E. , Desmarais-Gervais, L. , Gagnon, C. , Charlebois, P. et al (1987). The preschool behavior questionnaire: Stability of its factor structure between cultures, sexes, ages and socioeconomic classes. International Journal of Behavioral Development, 10, 467– 484Tucker, L. R. (1958). Determination of parameters of a functional relation by factor analysis. Psychometrika, 23, 19– 23Yang, C. C. (1998). Finite mixture model selection with psychometric applications. Unpublished doctoral dissertation, University of Groningen