Lifetime Data Analysis

, Volume 11, Issue 1, pp 5–27 | Cite as

Multivariate Parametric Spatiotemporal Models for County Level Breast Cancer Survival Data

Article

Abstract

In clustered survival settings where the clusters correspond to geographic regions, biostatisticians are increasingly turning to models with spatially distributed random effects. These models begin with spatially oriented frailty terms, but may also include further region-level terms in the parametrization of the baseline hazards or various covariate effects (as in a spatially-varying coefficients model). In this paper, we propose a multivariate conditionally autoregressive (MCAR) model as a mixing distribution for these random effects, as a way of capturing correlation across both the regions and the elements of the random effect vector for any particular region. We then extend this model to permit analysis of temporal cohort effects, where we use the term “temporal cohort” to mean a group of subjects all of whom were diagnosed with the disease of interest (and thus, entered the study) during the same time period (say, calendar year). We show how our spatiotemporal model may be efficiently fit in a hierarchical Bayesian framework implemented using Markov chain Monte Carlo (MCMC) computational techniques. We illustrate our approach in the context of county-level breast cancer data from 22 annual cohorts of women living in the state of Iowa, as recorded by the Surveillance, Epidemiology, and End Results (SEER) database. Hierarchical model comparison using the Deviance Information Criterion (DIC), as well as maps of the fitted county-level effects, reveal the benefit of our approach.

Keywords

cancer survival data Geographic Information System (GIS) lattice data Markov chain Monte Carlo methods proportional hazards random effects model 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akaike, H. 1973

    “Information theory and an extension of the maximum likelihood principle”

    Petrov, B. N.Csáki, F. eds. 2nd International Symposium on Information TheoryBudapestAkadémiai Kiadó267281
    Google Scholar
  2. Assunção, R. M. 2003“Space-varying coefficient models for small area data”Environmetrics14453473Google Scholar
  3. Banerjee, S., Carlin, B. P.,  et al. 2002

    “Spatial semiparametric proportional hazards models for analyzing infant mortality rates in Minnesota counties”

    Gatsonis, C. eds. Case Studies in Bayesian Statistics, Volume VISpringer-VerlagNew York137151
    Google Scholar
  4. Banerjee, S., Carlin, B. P. 2003“Semiparametric spatiotemporal frailty modeling’Environmetrics14523535Google Scholar
  5. Banerjee, S., Wall, M. M., Carlin, B. P. 2003“Frailty modeling for spatially correlated survival data, with application to infant mortality in Minnesota”Biostatistics4123142Google Scholar
  6. Besag, J. 1974“Spatial interaction and the statistical analysis of lattice systems (with discussion)”Journal of Royal Statistical Society Series B36192236Google Scholar
  7. Besag, J., Green, P., Higdon, D., Mengersen, K. 1995“Bayesian computation and stochastic systems (with discussion)”Statistical Science10366Google Scholar
  8. Brinkley, D., Haybittle, J. L., Alderson, M. R. 1984“Death certification in cancer of the breast”British Medical Journal288465467Google Scholar
  9. Carlin, B. P., Banerjee, S. 2003

    “Hierarchical multivariate CAR models for spatiotemporally correlated survival data (with discussion)”

    Bernardo, J. M.Bayarri, M. J.Berger, J. O.Dawid, A. P.Heckerman, D.Smith, A. F. M.West, M. eds. Bayesian Statistics 7Oxford University PressOxford4563
    Google Scholar
  10. Carlin, B. P., Hodges, J. S. 1999“Hierarchical proportional hazards regression models for highly stratified data”Biometrics5511621170Google Scholar
  11. Carlin, B. P., Louis, T. A. 2000Bayes and Empirical Bayes Methods for Data Analysis2Chapman Hall/CRC PressBoca Raton FLGoogle Scholar
  12. Gelfand, A. E., Ghosh, S. K. 1998“Model choice: a minimum posterior predictive loss approach”Biometrika85111Google Scholar
  13. Gelfand, A. E., Sahu, S. K., Carlin, B. P. 1995“Efficient parametrizations for normal linear mixed models”Biometrika82479488Google Scholar
  14. Gelfand, A. E., Sahu, S. K., Carlin, B. P. 1996

    “Efficient parametrizations for generalized linear mixed models (with discussion)”

    Bernardo, J. M.Berger, J. O.Dawid, A. P.Smith, A. F. M. eds. Bayesian Statistics 5Oxford University PressOxford165180
    Google Scholar
  15. Gelfand, A. E., Smith, A. F. M. 1990“Sampling-based approaches to calculating marginal densities”Journal of American Statistical Association85398409Google Scholar
  16. Gelfand, A. E., Vounatsou, P. 2003“Proper multivariate conditional autoregressive models for spatial data analysis”Biostatistics41125Google Scholar
  17. Hemming, K., Shaw, J. 2002“A parametric dynamic survival model applied to breast cancer survival times”Journal of Royal Statistical Society Series C (Applied Statistics)51421435Google Scholar
  18. Ibrahim, J. G., Chen, M.-H, Sinha, D. 2001Bayesian Survival AnalysisSpringer-VerlagNew YorkGoogle Scholar
  19. X. Jin, “Multivariate conditional autoregressive models for spatiotemporal disease data”, Unpublished PhD dissertation, Division of Biostatistics, University of Minnesota, 2005.Google Scholar
  20. T. A. Louis, “Discussion of ‘Parameter orthogonality and appropriate conditional inference’, by D. R. Cox and N. Reid”, Journal of Royal Statistical Society, Series B vol. 49 pp. 31, 1987.Google Scholar
  21. Mardia, K. V. 1988“Multi-dimensional multivariate Gaussian Markov random fields with application to image processing”Journal of Multivariate Analysis24265284Google Scholar
  22. Schwarz, G. 1978“Estimating the dimension of a model”Annals of Statistics6461464Google Scholar
  23. Spiegelhalter, D. J., Best, N., Carlin, B. P., Linde, A. 2002“Bayesian measures of model complexity and fit (with discussion)”Journal of Royal Statistical Society Series B64583639Google Scholar
  24. Wall, M. M. 2004“A close look at the spatial structure implied by the CAR and SAR models”Journal of Statistical Planning and Inference121311324Google Scholar
  25. Waller, L. A., Carlin, B. P., Xia, H., Gelfand, A. E. 1997“Hierarchical spatiotemporal mapping of disease rates”Journal American Statistical Association92607617Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  1. 1.Division of Biostatistics, School of Public HealthUniversity of MinnesotaMinneapolisUSA

Personalised recommendations