Advertisement

Computational Statistics

, Volume 33, Issue 2, pp 807–836 | Cite as

On the zero-modified Poisson–Shanker regression model and its application to fetal deaths notification data

  • Wesley Bertoli
  • Katiane S. Conceição
  • Marinho G. Andrade
  • Francisco Louzada
Original Paper

Abstract

In this paper, we propose the zero-modified Poisson–Shanker regression model as an alternative to model overdispersed count data exhibiting inflation or deflation of zeros in the presence of covariates. The zero modification has been incorporated using the zero-truncated Poisson–Shanker distribution. The zero-modified Poisson–Shanker distribution has been written as a hurdle model using a simple reparameterization of the probability function which leads to the fact that the proposed model can be fitted without any previous information about the zero modification present in a given dataset. The standard Bayesian procedures have been considered for estimation and inference. A simulation study has been presented to illustrate the performance of the developed methodology. The usefulness of the proposed model has been evaluated using a real dataset on fetal deaths notification data in Bahia State, Brazil. A sensitivity study to detect points which can influence the parameter estimates has been performed using Kullback–Leibler divergence measure. The randomized quantile residuals have been considered for the model validation issue. General comparison of the proposed model with some well-known discrete distributions has been provided.

Keywords

Poisson–Shanker distribution Zero inflated/deflated data Zero-modified and hurdle models Bayesian estimation Influential points 

Notes

Acknowledgements

The authors are grateful for the insightful comments and constructive suggestions provided by the associate editor and the anonymous referees. Also, the first author would like to thank the Federal Technology University of Paraná and the Araucária Foundation for the financial support during this research.

Supplementary material

180_2017_788_MOESM1_ESM.txt (8 kb)
Supplementary material 1 (txt 8 KB)

References

  1. Angers JF, Biswas A (2003) A Bayesian analysis of zero-inflated generalized Poisson model. Comput Stat Data Anal 42(1):37–46MathSciNetCrossRefzbMATHGoogle Scholar
  2. Bahn GD, Massenburg R (2008) Deal with excess zeros in the discrete dependent variable, the number of homicide in Chicago census tract. In: Joint Statistical Meetings of the American Statistical Association, pp 3905–3912Google Scholar
  3. Bazán JL, Torres-Avilés F, Suzuki AK, Louzada F (2017) Power and reversal power links for binary regressions: an application for motor insurance policyholders. Appl Stoch Models Bus Ind 33(1):22–34MathSciNetCrossRefGoogle Scholar
  4. Beuf KD, Schrijver JD, Thas O, Criekinge WV, Irizarry RA, Clement L (2012) Improved base-calling and quality scores for 454 sequencing based on a hurdle Poisson model. BMC Bioinform 13(1):303CrossRefGoogle Scholar
  5. Bohara AK, Krieg RG (1996) A zero-inflated Poisson model of migration frequency. Int Reg Sci Rev 19(3):211–222CrossRefGoogle Scholar
  6. Bové DS, Held L (2011) Hyper-\(g\) priors for generalized linear models. Bayesian Anal 6(3):387–410MathSciNetzbMATHGoogle Scholar
  7. Bulmer MG (1974) On fitting the Poisson-lognormal distribution to species-abundance data. Biometrics 30:101–110CrossRefzbMATHGoogle Scholar
  8. Carlin BP, Louis TA (1997) Bayes and empirical Bayes methods for data analysis. Stat Comput 7(2):153–154CrossRefGoogle Scholar
  9. Chib S, Greenberg E (1995) Understanding the Metropolis-Hastings algorithm. Am Stat 49(4):327–335Google Scholar
  10. Cho H, Ibrahim JG, Sinha D, Zhu H (2009) Bayesian case influence diagnostics for survival models. Biometrics 65(1):116–124MathSciNetCrossRefzbMATHGoogle Scholar
  11. Cohen AC (1960) An extension of a truncated Poisson distribution. Biometrics 16(3):446–450MathSciNetCrossRefzbMATHGoogle Scholar
  12. Conceição KS, Andrade MG, Louzada Neto F (2013) Zero-modified Poisson model: Bayesian approach, influence diagnostics, and an application to a Brazilian leptospirosis notification data. Biom J 55(5):661–678MathSciNetCrossRefzbMATHGoogle Scholar
  13. Cox DR, Snell EJ (1968) A general definition of residuals. J R Stat Soc Ser B (Methodol) 30:248–275MathSciNetzbMATHGoogle Scholar
  14. Csisz I (1967) Information-type measures of difference of probability distributions and indirect observations. Stud Sci Math Hungar 2:299–318MathSciNetGoogle Scholar
  15. Dietz E, Böhning D (2000) On estimation of the Poisson parameter in zero-modified Poisson models. Comput Stat Data Anal 34(4):441–459CrossRefzbMATHGoogle Scholar
  16. Dunn PK, Smyth GK (1996) Randomized quantile residuals. J Comput Graph Stat 5(3):236–244Google Scholar
  17. Garay AM, Bolfarine H, Lachos VH, Cabral CRB (2015) Bayesian analysis of censored linear regression models with scale mixtures of Normal distributions. J Appl Stat 42(12):2694–2714MathSciNetCrossRefGoogle Scholar
  18. Gelfand AE, Dey DK (1994) Bayesian model choice: asymptotics and exact calculations. J R Stat Soc Ser B (Methodol) 56:501–514MathSciNetzbMATHGoogle Scholar
  19. Geweke J (1994) Evaluating the accuracy of sampling-based approaches to the calculation of posterior moments. J R Stat Soc 56(3):501–514Google Scholar
  20. Ghosh SK, Mukhopadhyay P, Lu JC (2006) Bayesian analysis of zero-inflated regression models. J Stat Plan Inference 136(4):1360–1375MathSciNetCrossRefzbMATHGoogle Scholar
  21. Gupta M, Ibrahim JG (2009) An information matrix prior for Bayesian analysis in generalized linear models with high dimensional data. Stat Sin 19(4):1641MathSciNetzbMATHGoogle Scholar
  22. Gurmu S, Trivedi PK (1996) Excess zeros in count models for recreational trips. J Bus Econ Stat 14(4):469–477Google Scholar
  23. Heilbron DC, Gibson DR (1990) Shared needle use and health beliefs concerning AIDS: regression modeling of zero-heavy count data. Poster session. In: Proceedings of the sixth international conference on AIDS, San Francisco, CAGoogle Scholar
  24. Hörmann W, Leydold J, Derflinger G (2013) Automatic nonuniform random variate generation. Springer Science & Business Media, BerlinzbMATHGoogle Scholar
  25. Hu MC, Pavlicova M, Nunes EV (2011) Zero-inflated and hurdle models of count data with extra zeros: examples from an HIV-risk reduction intervention trial. Am J Drug Alcohol Abuse 37(5):367–375CrossRefGoogle Scholar
  26. King G (1989) Variance specification in event count models: from restrictive assumptions to a generalized estimator. Am J Polit Sci 33:762–784CrossRefGoogle Scholar
  27. Lambert D (1992) Zero-inflated Poisson regression, with an application to defects in manufacturing. Technometrics 34(1):1–14CrossRefzbMATHGoogle Scholar
  28. McCulloch RE (1989) Local model influence. J Am Stat Assoc 84(406):473–478CrossRefGoogle Scholar
  29. McDowell A (2003) From the help desk: Hurdle models. Stata J 3(2):178–184Google Scholar
  30. Mullahy J (1986) Specification and testing of some modified count data models. J Econom 91(434):841–853MathSciNetGoogle Scholar
  31. Ngatchou-Wandji J, Paris C (2011) On the zero-inflated count models with application to modelling annual trends in incidences of some occupational allergic diseases in France. J Data Sci 9:639–659MathSciNetGoogle Scholar
  32. R Development Core Team (2007) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0Google Scholar
  33. Ridout M, Demétrio CGB, Hinde J (1998) Models for count data with many zeros. In: Proceedings of the XIXth international biometric conference, vol 19, pp 179–192Google Scholar
  34. Rodrigues J (2003) Bayesian analysis of zero-inflated distributions. Commun Stat Theory Methods 32(2):281–289MathSciNetCrossRefzbMATHGoogle Scholar
  35. Saffar SE, Adnan R, Greene W (2012) Parameter estimation on hurdle Poisson regression model with censored data. Jurnal Teknologi 57(1):189–198Google Scholar
  36. Sankaran M (1970) The discrete Poisson–Lindley distribution. Biometrics 26(1):145–149CrossRefGoogle Scholar
  37. Shanker R (2015) Shanker distribution and its applications. Int J Stat Appl 5(6):338–348MathSciNetGoogle Scholar
  38. Shanker R (2016a) The discrete Poisson–Sujatha distribution. Int J Probab Stat 5(1):1–9MathSciNetCrossRefGoogle Scholar
  39. Shanker R (2016b) The discrete Poisson–Amarendra distribution. Int J Stat Distrib Appl 2(2):14–21MathSciNetGoogle Scholar
  40. Shanker R (2016c) The discrete Poisson–Shanker distribution. Jacobs J Biostat 1(1):1–7MathSciNetGoogle Scholar
  41. Shanker R, Mishra A (2014) A two parameter Poisson–Lindley distribution. Int J Stat Syst 9(1):79–85Google Scholar
  42. Shanker R, Mishra A (2016) A quasi Poisson–Lindley distribution. J Indian Stat Assoc 54(1&2):113–125MathSciNetGoogle Scholar
  43. Shanker R, Sharma S, Shanker U, Shanker R, Leonida TA (2014) The discrete Poisson–Janardan distribution with applications. Int J Soft Comput Eng (IJSCE) 4(2):31–33Google Scholar
  44. Umbach D (1981) On inference for a mixture of a Poisson and a degenerate distribution. Commun Stat Theory Methods 10(3):299–306MathSciNetCrossRefzbMATHGoogle Scholar
  45. Zamani H, Ismail N (2010) Negative Binomial–Lindley distribution and its application. J Math Stat 6(1):4–9CrossRefzbMATHGoogle Scholar
  46. Zellner A (1986) On assessing prior distributions and Bayesian regression analysis with g-prior distributions. Bayesian inference and decision techniques: Essays in Honor of Bruno De Finetti 6:233–243MathSciNetzbMATHGoogle Scholar
  47. Zorn CJW (1996) Evaluating zero-inflated and hurdle Poisson specifications. Midwest Polit Sci Assoc 18(20):1–16Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Wesley Bertoli
    • 1
    • 2
  • Katiane S. Conceição
    • 3
  • Marinho G. Andrade
    • 3
  • Francisco Louzada
    • 3
  1. 1.Departmento Acadêmico de MatemáticaUniversidade Tecnológica Federal do ParanáCuritibaBrazil
  2. 2.Instituto de Ciências Matemáticas e de ComputaçãoUniversidade de São Paulo, São CarlosSão PauloBrazil
  3. 3.Departamento de Matemática Aplicada e Estatística, Instituto de Ciências Matemáticas e de ComputaçãoUniversidade de São PauloSão CarlosBrazil

Personalised recommendations