Advertisement

Statistics and Computing

, Volume 26, Issue 6, pp 1137–1146 | Cite as

Coupling random inputs for parameter estimation in complex models

  • Michael A. Spence
  • Paul G. Blackwell
Article
  • 407 Downloads

Abstract

Complex stochastic models, such as individual-based models, are becoming increasingly popular. However this complexity can often mean that the likelihood is intractable. Performing parameter estimation on the model can then be difficult. One way of doing this when the complex model is relatively quick to simulate from is approximate Bayesian computation (ABC). Rejection-ABC algorithm is not always efficient so numerous other algorithms have been proposed. One such method is ABC with Markov chain Monte Carlo (ABC–MCMC). Unfortunately for some models this method does not perform well and some alternatives have been proposed including the fsMCMC algorithm (Neal and Huang, in: Scand J Stat 42:378–396, 2015) that explores the random inputs space as well unknown model parameters. In this paper we extend the fsMCMC algorithm and take advantage of the joint parameter and random input space in order to get better mixing of the Markov Chain. We also introduce a Gibbs step that conditions on the current accepted model and allows the parameters to move as well as the random inputs conditional on this accepted model. We show empirically that this improves the efficiency of the ABC–MCMC algorithm on a queuing model and an individual-based model of the group-living bird, the woodhoopoe.

Keywords

Approximate Bayesian computation Intractable likelihood Complex models Individual based models 

Notes

Acknowledgments

The authors would like to thank the anonymous referees for their helpful comments. This work was supported by the Engineering and Physical Sciences Research Council (Grant EP/I000917/1, National Centre for Statistical Ecology).

References

  1. Andrieu, C., Roberts, G.O.: The pseudo-marginal approach for efficient Monte Carlo computations. Ann. Stat. 41, 697–725 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  2. Andrieu, C., Doucet, A., Lee, A.: Discussion of constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. J. R. Stat. Soc. 74, 451–452 (2012)Google Scholar
  3. Baragatti, M., Grimaud, A., Pommeret, D.: Likelihood-free parallel tempering. Stat. Comput. 23(4), 535–549 (2013)Google Scholar
  4. Beaumont, M.A.: Approximate Bayesian computation in evolution and ecology. Ann. Rev. Ecol. Evol. Syst. 41, 379–406 (2010)CrossRefGoogle Scholar
  5. Beaumont, M.A., Cornuet, J.M., Marin, J.M., Robert, C.P.: Adaptive approximate Bayesian computation. Biometrika 96, 983–990 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  6. Blum, M.G.B., François, O.: Non-linear regression models for approximate Bayesian computation. Stat. Comput. 20, 63–73 (2010)MathSciNetCrossRefGoogle Scholar
  7. du Plessis, M.: Obligate cavity-roosting as a constraint on dispersal of green (red-billed) woodhoopoes: consequences for philopatry and the likelihood of inbreeding. Oecologia 90, 205–211 (1992)CrossRefGoogle Scholar
  8. Fearnhead, P., Prangle, D.: Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. J. R. Stat.l Soc. B 74, 419–474 (2012)MathSciNetCrossRefGoogle Scholar
  9. Grimm, V., Railsback, S.F.: Individual-based modelling and ecology. Princeton series in theoretical and computational biology (2005)Google Scholar
  10. Heggland, K., Frigessi, A.: Estimating functions in indirect inference. J. R. Stat. Soc. B 66, 447–462 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  11. Lee, A., Łatuszyński, K.: Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation. Biometrika 101(3), 655–671 (2014)MathSciNetCrossRefzbMATHGoogle Scholar
  12. Lee, A., Andrieu, C., Doucet, A.: Discussion of constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. J. R. Stat. Soc. B 74, 449–450 (2012)CrossRefGoogle Scholar
  13. Lee, J.E., McVinish, R., Mengersen, K.: Population Monte Carlo algorithm in high dimensions. Methodol. Comput. Appl. Probab. 13(2), 369–389 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  14. Marin, J.M., Pudlo, P., Robert, C.P., Ryder, R.J.: Approximate Bayesian computational methods. Stat. Comput. 22(6), 1167–1180 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  15. Marjoram, P., Molitor, J., Plagnol, V., Tavaré, S.: Markov chain Monte Carlo without likelihoods. Proc. Natl. Acad. Sci. 100, 15,324–15,328 (2003)CrossRefGoogle Scholar
  16. Neal, P.: Efficient likelihood-free Bayesian computation for household epidemics. Stat. Comput. 22, 1239–1256 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  17. Neal, P., Huang, C.L.T.: Forward simulation Markov Chain Monte Carlo with applications to stochastic epidemic models. Scand. J. Stat. 42, 378–396 (2015)MathSciNetCrossRefzbMATHGoogle Scholar
  18. Neuert, C., du Plessis, M., Grimm, V., Wessel, C.: Welche ökologischen faktoren bestimmen die gruppengröbe bei phoeniculus purpureus (gemeiner baumhopf) in südafrika? ein individuenbasiertes modell. Verhandlungen der Gesellschaft fur Okologie 24, 145–149 (1995)Google Scholar
  19. Piou, C., Berger, U., Grimm, V.: Proposing an information critation for individual-based models developed in a pattern-orientated modelling framework. Ecol. Model. 220, 1957–1967 (2009)CrossRefGoogle Scholar
  20. Pritchard, J.K., Seielstad, M.T., Perez-Lezaun, A., Feldman, M.W.: Population growth of human y chromosomes: a study of Y chromosome microsatellites. Mol. Biol. Evo. 16, 1791–1798 (1999)CrossRefGoogle Scholar
  21. Railsback, S.F., Grimm, V.: Agent-Based and Individual-Based Modeling a Practical Introduction. Princeton University Press, Princeton (2012)zbMATHGoogle Scholar
  22. Sisson, S.A., Fan, Y., Tanaka, M.M.: Sequential Monte Carlo without likelihoods. Proc. Natl. Acad. Sci. 104, 1760–1765 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  23. Spence, M., Blackwell, P.: Bayesian inference on individual-based models by controlling the random inputs. The contribution of young researchers to Bayesian statistics pp. 35–39. (2014)Google Scholar
  24. Spence, M.A.: Statistical issues in ecological simulation models. PhD thesis, University of Sheffield (2015)Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.School of Mathematics and StatisticsUniversity of SheffieldSheffieldUK

Personalised recommendations