A Bayesian Analysis of Leukemia Incidence Surrounding an Inactive Hazardous Waste Site

  • Ronald C. Neath
Conference paper
Part of the Lecture Notes in Statistics book series (LNS, volume 196)


Abstract In this chapter we consider a subset of the data analyzed by Waller, Turnbull, Clark, and Nasca (Case Studies in Biometry 1994), concerning incidence of leukemia cases in an area surrounding the GE Auburn hazardous waste site in Cayuga County in upstate New York. The data consist of exposed population and leukemia cases by census block for the five-year period from 1978 to 1982, and the goal of our analysis is to quantify the extent to which close proximity to the hazardous waste site increases risk of contracting leukemia. We follow roughly the methodology of Wakefield and Morris (JASA 2001), who utilized a location-risk model embedded in a standard disease-mapping framework to analyze incidence of stomach cancer in relation to a municipal solid waste incinerator on the northeast coast of England. We describe in detail the three-stage Bayesian hierarchical model, and the selection of prior distributions for the model parameters. A major emphasis of this chapter will be on the use of R and WinBUGS, and the R2WinBUGS interface between them, in conducting the data analysis.


Markov Chain Monte Carlo Prior Distribution Census Block Municipal Solid Waste Incinerator Markov Chain Monte Carlo Sample 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Banerjee, S., Carlin, B.P., Gelfand, A.E.: Hierarchical Modeling and Analysis for Spatial Data. Chapman & Hall / CRC (2004)Google Scholar
  2. 2.
    Diggle, P.J.: A point process modelling approach to raised incidence of a rare phenomenon in the vicinity of a prespecified point. Journal of the Royal Statistical Society, Series A 153, 349–362 (1990)Google Scholar
  3. 3.
    Flegal, J.M., Haran, M., Jones, G.L.: Markov chain Monte Carlo: Can we trust the third significant figure? Statistical Science 23, 250–260 (2008)CrossRefGoogle Scholar
  4. 4.
    Gelman, A., Rubin, D.B.: Inference from iterative simulation using multiple sequences. Statistical Science 7, 457–472 (1992)CrossRefGoogle Scholar
  5. 5.
    Jones, G.L., Haran, M., Caffo, B.S., Neath, R.: Fixed-width output analysis in Markov chain Monte Carlo. Journal of the American Statistical Association 101, 1537–1547 (2006)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Jones, G.L., Hobert, J.P.: Honest exploration of intractable probability distributions via Markov chain Monte Carlo. Statistical Science 16, 312–334 (2001)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Lunn, D.J., Thomas, A., Best, N., Spiegelhalter, D.: WinBUGS – a Bayesian modelling framework: Concepts, structure, and extensibility. Statistics and Computing 10, 325–337 (2000)CrossRefGoogle Scholar
  8. 8.
    Spiegelhalter, D.J., Best, N.G., Carlin, B.P., van der Linde, A.: Bayesian measures of model complexity and fit. Journal of the Royal Statistical Society, Series B 64, 583–616 (2002)MATHCrossRefGoogle Scholar
  9. 9.
    Sturtz, S., Ligges, U., Gelman, A.: R2WinBUGS: A package for running WinBUGS from R. Juornal of Statistical Software 12, 1–16 (2005)Google Scholar
  10. 10.
    Wakefield, J.C., Morris, S.E.: The Bayesian modeling of disease risk in relation to a point source. Journal of the American Statistical Association 96, 77–91 (2001)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Waller, L.A., Turnbull, B.W., Clark, L.C., Nasca, P.: Spatial pattern analyses to detect rare disease clusters. In: N. Lange, L. Ryan, L. Billard, D. Brillinger, L. Conquest, J. Greenhouse (eds.) Case Studies in Biometry, pp. 3–23. John Wiley & Sons, Inc. (1994)Google Scholar

Copyright information

© Springer-Verlag New York 2010

Authors and Affiliations

  1. 1.Department of Statistics and CIS, Baruch CollegeCity University of New YorkNew YorkUSA

Personalised recommendations