Environmental and Ecological Statistics

, Volume 17, Issue 4, pp 521–541 | Cite as

Non-homogeneous Poisson models with a change-point: an application to ozone peaks in Mexico city

  • Jorge Alberto Achcar
  • Eliane R. RodriguesEmail author
  • Carlos Daniel Paulino
  • Paulo Soares


In this paper, we use some non-homogeneous Poisson models in order to study the behavior of ozone measurements in Mexico City. We assume that the number of ozone peaks follows a non-homogeneous Poisson process. We consider four types of rate function for the Poisson process: power law, Musa–Okumoto, Goel–Okumoto, and a generalized Goel–Okumoto rate function. We also assume that a change-point may or may not be present. The analysis of the problem is performed by using a Bayesian approach via Markov chain Monte Carlo methods. The best model is chosen using the DIC criterion as well as graphical approach.


Non-homogeneous Poisson process Bayesian inference Change-point MCMC methods Air pollution data 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Achcar JA, Bolfarine H (1989) Constant hazard against a change-point alternative: a Bayesian approach with censored data. Commun Stat Theory Methods 18: 3801–3819CrossRefGoogle Scholar
  2. Achcar JA, Loibel S (1998) Constant hazard models with a change-point: a Bayesian analysis using Markov chain Monte Carlo methods. Biom J 40: 543–555CrossRefGoogle Scholar
  3. Achcar JA, Fernández-Bremauntz AA, Rodrigues ER, Tzintzun G (2008) Estimating the number of ozone peaks in Mexico City using a non-homogeneous Poisson model. Environmetrics 19: 469–485CrossRefGoogle Scholar
  4. Akaike HA (1974) New look at the statistical model identification. IEEE Trans Autom Control 19: 716–723CrossRefGoogle Scholar
  5. Álvarez LJ, Fernández-Bremauntz AA, Rodrigues ER, Tzintzun G (2005) Maximum a posteriori estimation of the daily ozone peaks in Mexico City. J Agric Biol Environ Stat 10: 276–290CrossRefGoogle Scholar
  6. Austin J, Tran H (1999) A characterization of the weekday–weekend behavior of ambient ozone concentrations in California. Air Pollution VI. WIT Press, Ashurst Lodge, pp, pp 645–661Google Scholar
  7. Bell ML, McDermontt A, Zeger SL, Samet JM, Dominici F (2004) Ozone and short-term mortality in 95 US urban communities 1987–2000. J Am Med Soc 292: 2372–2378Google Scholar
  8. Carlin BP, Gelfand AE, Smith AFM (1992) Hierarchical Bayesian analysis of change-point problems. Appl Stat 41: 389–405CrossRefGoogle Scholar
  9. Chib S, Greenberg E (1995) Understanding the Metropolis–Hastings algorithm. Am Stat 49: 327–335CrossRefGoogle Scholar
  10. Comrie AC (1997) Comparing neural network and regression models for ozone forecasting. J Air and Waste Manag Assoc 47: 653–663Google Scholar
  11. Cox DR, Lewis PA (1996) Statistical analysis of series of events. Methuem, UKGoogle Scholar
  12. Dey DK, Purkayastha S (1997) Bayesian approach to change-point problems. Commun Stat Theory Methods 26: 2035–2047CrossRefGoogle Scholar
  13. Gelfand AE, Smith AFM (1990) Sampling-based approaches to calculating marginal densities. J Am Stat Assoc 85: 398–409CrossRefGoogle Scholar
  14. Gelman A, Rubin DB (1992) Inference from iterative simulation using multiple sequences (with discussion). Stat Sci 7: 457–511CrossRefGoogle Scholar
  15. Goel AL, Okumoto K (1978) An analysis of recurrent software failures on a real-time control system. In: Proceedings of ACM Conference. Washington, pp 496–500Google Scholar
  16. Guardani R, Nascimento CAO, Guardani MLG, Martins MHRB, Romano J (1999) Study of atmospheric ozone formation by means of a neural network based model. J Air and Waste Manag Assoc 49: 316–323Google Scholar
  17. Guardani R, Aguiar JL, Nascimento CAO, Lacava CIV, Yanagi Y (2003) Ground-level ozone mapping in large urban areas using multivariate analysis: application to the São Paulo metropolitan area. J Air and Waste Manag Assoc 53: 553–559Google Scholar
  18. Horowitz J (1980) Extreme values from a nonstationary stochastic process: an application to air quality analysis. Technometrics 22: 469–482CrossRefGoogle Scholar
  19. Huang CY, Lyu MR, Kuo SY (2003) A unified scheme of some nonhomogeneous Poisson process models for software reliability estimation. IEEE Trans Softw Eng 29: 261–269CrossRefGoogle Scholar
  20. Javits JS (1980) Statistical interdependencies in the ozone national ambient air quality standard. J Air Poll Control Assoc 30: 58–59Google Scholar
  21. Kuo L, Yang TY (1996) Bayesian computation for nonhomogeneous Poisson process in software reliability. J Am Stat Assoc 91: 763–773CrossRefGoogle Scholar
  22. Kuo L, Yang TY (1999) Bayesian computation for the superposition of Poisson process in software reliability. Can J Stat 27: 547–556CrossRefGoogle Scholar
  23. Larsen LC, Bradley RA, Honcoop GL (1980) A new method of characterizing the variability of air quality-related indicators. In: Air and Waste Management Association’s International Specialty Conference of Tropospheric Ozone and the Environment. Los AngelesGoogle Scholar
  24. Leadbetter MR (1991) On a basis for “peak over threshold” modeling. Stat Probab Lett 12: 357–362CrossRefGoogle Scholar
  25. Loomis DP, Borja-Arbuto VH, Bangdiwala SI, Shy CM (1996) Ozone exposure and daily mortality in Mexico City: a time series analysis. Health Eff Inst Res Rep 75: 1–46Google Scholar
  26. Matthews DE, Farewell VT (1982) On testing for a constant hazard against a change-point alternative. Biometrics 71: 299–304Google Scholar
  27. Mudholkar GS, Srivastava DK, Friemer M (1995) The exponentiated-Weibull family: a reanalysis of the bus-motor failure data. Technometrics 37: 436–445CrossRefGoogle Scholar
  28. Musa JD, Okumoto K (1984) A logarithmic Poisson execution time model for software reliability measurement. In: Proceedings of 7th International Conference on Software Engineering. Orlando, pp 230–238Google Scholar
  29. Musa JD, Iannino A, Okumoto K (1987) Software reliability: measurement, prediction, application. McGraw Hill, USAGoogle Scholar
  30. NOM (2002) Modificación de la Norma Oficial Mexicana NOM-020-SSA1-1993. Diario Oficial de la Federación, 30 de OctubreGoogle Scholar
  31. Pievatolo A, Ruggeri F (2004) Bayesian reliability analysis of complex repairable systems. Appl Stoch Models Bus Ind 20: 253–264CrossRefGoogle Scholar
  32. Raftery AE (1989) Are ozone exceedance rate decreasing? Comment on the paper “Extreme value analysis of environmental time series: an application to trend detection in ground-level ozone” by R. L. Smith. Stat Sci 4: 378–381CrossRefGoogle Scholar
  33. Raftery AE, Akman VE (1986) Bayesian analysis of a Poisson process with a change-point. Biometrics 73: 85–89CrossRefGoogle Scholar
  34. Ramírez-Cid JE, Achcar JA (1999) Bayesian inference for nonhomogeneous Poisson processes in software reliability models assuming nonhomogeneous nonmonotonic intensity functions. Comput Stat Data Anal 32: 147–159CrossRefGoogle Scholar
  35. Roberts EM (1979) Review of statistics extreme values with applications to air quality data. Part I. Review. J Air Pollut Control Assoc 29: 632–637Google Scholar
  36. Roberts EM (1979) Review of statistics extreme values with applications to air quality data. Part II. Applications. J Air Pollut Control Assoc 29: 733–740Google Scholar
  37. Ruggeri F, Sivaganesan S (2005) On modelling change-points in nonhomogeneous Poisson processes. Stat Inference Stoch Models 8: 311–329CrossRefGoogle Scholar
  38. Schwarz G (1978) Estimating the dimension of a model. Annal Stat 6: 461–466CrossRefGoogle Scholar
  39. Smith RL (1989) Extreme value analysis of environmental time series: an application to trend detection in ground-level ozone. Stat Sci 4: 367–393CrossRefGoogle Scholar
  40. Smith AFM, Roberts GO (1993) Bayesian computation via the Gibbs sampler and related Markov chain Monte Carlo methods. J R Stat Soc Series B 55: 3–23Google Scholar
  41. Spiegelhalter DJ, Thomas A, Best NG (1999) WinBugs: Bayesian inference using Gibbs sampling. MRC Biostatistics Unit, CambridgeGoogle Scholar
  42. Spiegelhalter DJ, Best NG, Carlin BP, Vander Linde A (2002) Bayesian measures of model complexity and fit (with discussion and rejoinder). J R Stat Soc Series B 64: 583–639CrossRefGoogle Scholar
  43. Wilson R, Colone SD, Spengler JD, Wilson DG (1980) Health effects of fossil fuel burning: assessment and mitigation. Ballenger, CambridgeGoogle Scholar
  44. Yamada S, Osaki S (1984) Nonhomogeneous error detection rate models for software reliability growth. In: Osaki S, Hatoyama Y (eds) Reliability theory. Springer, Berlin., pp 120–143Google Scholar
  45. Yamada Y, Osaki S (1985) Software reliability modeling: models and applications. IEEE Trans Softw Eng 12: 1431–1437CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  • Jorge Alberto Achcar
    • 1
  • Eliane R. Rodrigues
    • 2
    Email author
  • Carlos Daniel Paulino
    • 3
  • Paulo Soares
    • 3
  1. 1.Departamento de Medicina SocialFMRP—USPRibeirão PretoBrazil
  2. 2.Instituto de Matemáticas—UNAMMexicoMexico
  3. 3.Departamento de MatemáticaUniversidade Técnica de Lisboa—ISTLisboaPortugal

Personalised recommendations