Model-Based Clustering of Multistate Data with Latent Change: An Application with DHS Data

Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)

Abstract

Finite mixture modeling has been used extensively as a model-based clustering technique. This research addresses the application of mixture models to multistate data (sequences of states) under the Markov assumption. By assuming a latent or hidden Markov process, the model incorporates the estimation of the misclassification error. The data are from the life history calendar from the Brazilian Demographic and Health Survey (DHS) 1996 in which contraceptive use dynamics are surveyed retrospectively. The results show that the dynamics are heterogeneous with two subpopulations.

Notes

Acknowledgements

The author would like to thank the Fundação para a Ciência e a Tecnologia (Portugal) for its financial support (PTDC/CS-DEM/108033/2008). I also wish to express my gratitude to the two anonymous referees for their valuable comments on this paper.

References

  1. Baum, L. E., Petrie, T., Soules, G., & Weiss, N. (1970). A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Annals of Mathematical Statistics,41, 164–171.Google Scholar
  2. Belli, R. F., Shay, W. L., & Stafford, F. P. (2001). Event history calendars and question list surveys. Public Opinion Quarterly,65, 45–74.Google Scholar
  3. BENFAM & Macro International (1997). Pesquisa Nacional Sobre Demografia e Sade (PNDS), Brasil, 1996, Rio de Janeiro.Google Scholar
  4. Clogg, C. C. (1995). Latent class models. In G. Arminger, C. C. Clogg, & M. E. Sobel (Eds.), Handbook of statistical modeling for the social and behavioral sciences (pp. 311–359). New York: Plenum Press.Google Scholar
  5. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm (with discussion). Journal of the Royal Statistical Society, Series B,39, 1–38.Google Scholar
  6. Dias, J. G., & Vermunt J. K. (2007). Latent class modeling of website users’ search patterns: Implications for online market segmentation. Journal of Retailing and Consumer Services,14, 359–368.Google Scholar
  7. Dias, J. G., & Wedel, M. (2004). On EM, SEM and MCMC performance for problematic Gaussian mixture likelihoods. Statistics and Computing,14(4), 323–332.Google Scholar
  8. Dias, J. G., & Willekens, F. (2005). Model-based clustering of sequential data with an application to contraceptive use dynamics. Mathematical Population Studies,12(3), 135–157.Google Scholar
  9. McLachlan, G. J., & Peel, D. (2000). Finite Mixture Models. New York: Wiley.Google Scholar
  10. Rabiner, L. R., & Juang, B. H. (1986). An introduction to hidden Markov models. IEEE Acoustics, Speech and Signal Processing Magazine,3, 4–16.Google Scholar
  11. Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics,6, 461–464.Google Scholar
  12. Wedel, M., & Kamakura, W. (2000). Market segmentation: Conceptual and methodological foundations. Boston: Kluwer Academic Publishers.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Business Research Unit (BRU-IUL)Instituto Universitário de Lisboa (ISCTE-IUL)LisboaPortugal

Personalised recommendations