Statistics and Computing

, Volume 15, Issue 4, pp 255–265

Multivariate Poisson regression with covariance structure

Article
  • 1.5k Downloads

Abstract

In recent years the applications of multivariate Poisson models have increased, mainly because of the gradual increase in computer performance. The multivariate Poisson model used in practice is based on a common covariance term for all the pairs of variables. This is rather restrictive and does not allow for modelling the covariance structure of the data in a flexible way. In this paper we propose inference for a multivariate Poisson model with larger structure, i.e. different covariance for each pair of variables. Maximum likelihood estimation, as well as Bayesian estimation methods are proposed. Both are based on a data augmentation scheme that reflects the multivariate reduction derivation of the joint probability function. In order to enlarge the applicability of the model we allow for covariates in the specification of both the mean and the covariance parameters. Extension to models with complete structure with many multi-way covariance terms is discussed. The method is demonstrated by analyzing a real life data set.

Keywords

data augmentation EM algorithm Markov chain Monte Carlo multivariate reduction crime data 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bennett J.E., Racine-Poon A., and Wakefield J.C. 1996. MCMC for nonlinear hierarchical models. In: Gilks W.R., Richardson S., and Spiegelhalter D.J. (Eds.), Markov Chain Monte Carlo in Practice. Chapman and Hall, New York, pp. 339–357.Google Scholar
  2. Berkhout P. and Plug E. 2004. A bivariate Poisson count data model using conditional probabilities. Statistica Neerlandica 58: 349–364.CrossRefMathSciNetGoogle Scholar
  3. Chib S. and Greenberg E. 1995. Understanding the Metropolis-Hastings algorithm. The American Statistician 49: 327–335.Google Scholar
  4. Chib S. and Winkelmann R. 2001. Markov chain Monte Carlo analysis of correlated count data. Journal of Business and Economic Statistics 19: 428–435.CrossRefMathSciNetGoogle Scholar
  5. Dellaportas P. and Smith A.F.M. 1993. Bayesian inference for generalized linear and proportional hazard models via Gibbs sampling. Applied Statistics 41: 443–459.Google Scholar
  6. Dey D.K., Ghosh S.K., and Mallick B.K. 2000. Generalized Linear Models: A Bayesian Perspective. Marcel-Dekker, Inc., New York.Google Scholar
  7. Efron B. and Tibshirani R.J. 1993. An Introduction to the Bootstrap, Chapman and Hall, New York.Google Scholar
  8. Gilks W.R., Best N.G., and Tan K.K.C. 1995. Adaptive rejection metropolis sampling within gibbs sampling. Applied Statistics 44: 155–73.Google Scholar
  9. Gilks W.R., Richardson S., and Spiegelhalter D.J. 1996. Markov Chain Monte Carlo in Practice. Chapman and Hall, New York.Google Scholar
  10. Ho L.L. and Singer J.M. 2001. Generalized least squares methods for bivariate Poisson regression. Communications in Statistics, Theory and Methods 30: 263–277.Google Scholar
  11. Ibrahim J.G. and Laud P.W. 1991. On Bayesian analysis of generalized linear models using Jeffreys's prior. Journal of the American Statistical Association 86: 981–986.Google Scholar
  12. Johnson N., Kotz S., and Balakrishnan N. 1997. Discrete Multivariate Distributions, New York, Wiley.Google Scholar
  13. Kano K. and Kawamura K. 1991. On recurrence relations for the probability function of multivariate generalized Poisson distribution. Communications in Statistics-Theory and Methods 20: 165–178.Google Scholar
  14. Kocherlakota, S. and Kocherlakota, K. 1992. Bivariate Discrete Distributions, Marcel Dekker, New York.Google Scholar
  15. Kocherlakota S. and Kocherlakota K. 2001. Regression in the bivariate Poisson distribution. Communications in Statistics-Theory and Methods 30: 815–827.CrossRefMathSciNetGoogle Scholar
  16. Karlis D. 2003. An EM algorithm for multivariate Poisson distribution and related models. Journal of Applied Statistics 30: 63–77.CrossRefMathSciNetGoogle Scholar
  17. Karlis D. and Ntzoufras J. 2003. Analysis of sports data using bivariate Poisson models. The Statistician 52: 381–393 .MathSciNetGoogle Scholar
  18. Lee L.F. 2001. On the range of correlation coefficients of bivariate ordered discrete random variables. Econometrics Journal 17: 247–256Google Scholar
  19. Li C.S, Lu J.C., Park J., Kim K., and Peterson J. 1999. Multivariate zero-inflated Poisson models and their applications. Technometrics 41: 29–38.Google Scholar
  20. Mahamunulu D.M. 1967. A note on regression in the multivariate Poisson distribution. Journal of the American Statistical Association 62: 251–258Google Scholar
  21. McLachlan G. and Krishnan T. 1997. The EM Algorithm and Extensions, Wiley, New York.Google Scholar
  22. Ntzoufras I., Dellaportas P., and Forster J.J. 2003. Bayesian variable and link determination for generalised linear models. Journal of Statistical Planning and Inference 111: 165–180.CrossRefMathSciNetGoogle Scholar
  23. Roberts G.O., Gelman A., and Gilks W. 1997. Weak convergence and optimal scaling of random walk Metropolis algorithms. Annals of Applied Probability 7: 110–120.CrossRefGoogle Scholar
  24. Roberts G.O. and Rosenthal S. 2001. Optimal scaling for various Metropolis-Hastings algorithms. Statistical Science 16: 351–367.CrossRefGoogle Scholar
  25. Tanner M.A. and Wong W.H. 1987. The calculation of posterior distributions by data augmentation. Journal of the American Statistical Association 82: 528–540.Google Scholar
  26. Tierney L. 1994. Markov chains for exploring posterior distributions (with discussion). The Annals of Statistics 22: 1701–1762.Google Scholar
  27. Tsionas E.G. 1999. Bayesian analysis of the multivariate Poisson distribution. Communications in Statistics-Theory and Methods 28: 431–451.Google Scholar
  28. Tsionas E.G. 2001. Bayesian multivariate Poisson regression. Communications in Statistics—Theory and Methods 30: 243–255.CrossRefMathSciNetGoogle Scholar
  29. Van Ophem H. 1999. A general method to estimate correlated discrete random variables. Econometric Theory 15: 228–237CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Science + Business Media, Inc. 2005

Authors and Affiliations

  1. 1.Department of StatisticsAthens University of Economics and BusinessAthensGreece
  2. 2.Department of Mathematics and StatisticsLancaster UniversityLancasterUnited Kingdom

Personalised recommendations