Environmental and Ecological Statistics

, Volume 17, Issue 3, pp 347–376 | Cite as

Modelling spatial zero-inflated continuous data with an exponentially compound Poisson process

  • Sophie Ancelet
  • Marie-Pierre Etienne
  • Hugues Benoît
  • Eric Parent
Article

Abstract

A parsimonious model is presented as an alternative to delta approaches to modelling zero-inflated continuous data. The data model relies on an exponentially compound Poisson process, also called the law of leaks (LOL). It represents the process of sampling resources that are spatially distributed as Poisson distributed patches, each containing a certain quantity of biomass drawn from an exponential distribution. In an application of the LOL, two latent structures are proposed to account for spatial dependencies between zero values at different scales within a hierarchical Bayesian framework. The LOL is compared to the delta-gamma (ΔΓ) distribution using bottom-trawl survey data. Results of this case study emphasize that the LOL provides slightly better fits to learning samples with a very high proportion of zero values and small strictly positive abundance data. Additionally, it offers better predictions of validation samples.

Keywords

Bayes factor Bayesian hierarchical modelling Excess zeros Intrinsic AutoRegressive spatial model MCMC algorithms Posterior predictive loss criterion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aitchison J, Brown JAC (1957) The lognormal distribution with special reference to its uses in econometrics. Cambridge University Press, CambridgeGoogle Scholar
  2. Ancelet S (2008) Exploiter l’approche hiérarchique bayésienne pour la modélisation statistique de structures spatiales. Application en écologie des populations. Dissertation, Agro Paris Tech, Paris Institute of Life and Environmental Science and TechnologyGoogle Scholar
  3. Banerjee S, Carlin B, Gelfand A (2004) Hierarchical modeling and analysis for spatial data. Chapman and Hall/CRC, Boca RatonGoogle Scholar
  4. Bernier J, Fandeux D (1970) Théorie du renouvellement—application à l’étude statistique des précipitations mensuelles. Rev Stat Appl 18(2): 75–87Google Scholar
  5. Besag J, York J, Mollié A (1991) Bayesian image restoration with two applications in spatial statistics. Ann I Stat Math 43(1): 1–51CrossRefGoogle Scholar
  6. Brooks SP, Gelman A (1998) Alternative methods for monitoring convergence of iterative simulations. J Comput Graph Stat 7(4): 434–455CrossRefGoogle Scholar
  7. Chyan-Huei Lo N, Jacobson LD, Squire JL (1992) Indices of relative abundance from fish spotter data based on delta-lognormal models. Can J Fish Aquat Sci 49(12): 2515–2526CrossRefGoogle Scholar
  8. Congdon P (2001) Bayesian statistical modelling. John Wiley & Sons Inc., New YorkGoogle Scholar
  9. Cressie NAC (1993) Statistics for spatial data. John Wiley & Sons Inc., New YorkGoogle Scholar
  10. Feller W (1971) An introduction to probability theory and its applications. John Wiley & Sons Inc., New YorkGoogle Scholar
  11. Fletcher D, MacKenzie D, Villouta E (2005) Modelling skewed data with many zeros: a simple approach combining ordinary and logistic regression. Environ Ecol Stat 12(1): 45–54CrossRefGoogle Scholar
  12. Gelfand AE, Ghosh S (1998) Model choice: a minimum posterior predictive loss approach. Biometrika 85(1): 1–11CrossRefGoogle Scholar
  13. Gelfand AE, Smith AFM (1990) Sampling based approach to calculating marginal densities. J Am Stat Assoc 85(410): 398–409CrossRefGoogle Scholar
  14. Hall DB (2000) Zero-inflated Poisson and binomial regression with random dffects: a case study. Biometrics 56(4): 1030–1039CrossRefPubMedGoogle Scholar
  15. Heilbron DC (1994) Zero-altered and other regression models for count data with added zeros. Biometrical J 36(5): 531–547CrossRefGoogle Scholar
  16. Hurlbut T, Clay D (1990) Protocols for research vessel cruises within the Gulf Region (demersal fish)(1970–1987). Can Manus Rep Fish Aquat Sci 2082: 2143Google Scholar
  17. Kass RE, Raftery AE (1994) Bayes factors. J Am Stat Assoc 90(430): 773–795CrossRefGoogle Scholar
  18. Lambert D (1992) Zero-inflated Poisson regression, with an application to defects in manufacturing. Technometrics 34(1): 1–4CrossRefGoogle Scholar
  19. Legendre P, Legendre L (1998) Numerical ecology. Elsevier Science, AmsterdamGoogle Scholar
  20. Lempers FB (1971) Posterior probabilities of alternative linear models. Rotterdam University Press, RotterdamGoogle Scholar
  21. Loring DH, Nota DJG (1973) Morphology and sediments of the Gulf of St. Lawrence. B Fish Res Board Can 182: 147Google Scholar
  22. Martin TG et al (2005) Zero tolerance ecology: improving ecological inference by modelling the source of zero observations. Ecol Lett 8: 1235–1246CrossRefGoogle Scholar
  23. Myers RA, Pepin P (1990) The robustness of lognormal based estimators of abundance. Biometrics 46(4): 1185–1192CrossRefGoogle Scholar
  24. O’Hagan A (1995) Fractional bayes factors for model comparison. J Roy Stat Soc B 57(1): 99–138Google Scholar
  25. Pennington M (1983) Efficient estimators of abundance for fish and planktons survey. Biometrics 39(1): 281–286CrossRefGoogle Scholar
  26. Pennington M (1996) Estimating the mean and variance from highly skewed marine data. Fish B 94: 498–505Google Scholar
  27. Ridout M, Demétrio CGB, Hinde J (1998) Models for count data with many zeros, International biometric conference, Cape TownGoogle Scholar
  28. Robert CP, Casella G (2004) Monte Carlo statistical methods. Springer, New YorkGoogle Scholar
  29. Sinharay S, Stern HS (2002) On the sensitivity of Bayes factors to the prior distributions. Am Stat 56(6): 196–201CrossRefGoogle Scholar
  30. Spiegelhalter D, Best N, Carlin BP, VanDer Linde A (2002) Bayesian measures of model complexity and fit. J Roy Stat Soc B 64(4): 583–639CrossRefGoogle Scholar
  31. Spiegelhalter D, Thomas A, Best N, Lunn D (2007) OpenBUGS user manual, Version 3.0.2, MRC Biostatistics Unit, Cambridge, Available via http://www.mathstat.helsinki.fi/openbugs/
  32. Stefansson G (1996) Analysis of groundfish survey abundance data: combining the GLM and delta approaches. ICES J Mar Sci 53(3): 577–588CrossRefGoogle Scholar
  33. Thomas A, Best N, Lunn D, Arnold R, Spiegelhalter D (2007) GeoBUGS user manual, Version 1.3, Rolf Nevanlinna Institute, Available via http://www.mathstat.helsinki.fi/openbugs/
  34. Welsh AH, Cunningham RB, Donnelly CF, Lindenmayer DB (1996) Modelling the abundance of rare species: statistical counts with extra zeros. Ecol Model 88(1): 297–308CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Sophie Ancelet
    • 1
  • Marie-Pierre Etienne
    • 2
  • Hugues Benoît
    • 3
  • Eric Parent
    • 2
  1. 1.INSERM-INED U822, Equipe “Epidémiologie de la reproduction et du développement de l’enfant”, Hôpital de BicêtreLe Kremlin-Bicêtre CedexFrance
  2. 2.AgroParisTech-INRA UMR518Paris Cedex 05France
  3. 3.Fisheries and Oceans CanadaMonctonCanada

Personalised recommendations