Journal of Statistical Theory and Practice

, Volume 6, Issue 4, pp 725–744 | Cite as

Analysis of Partially Incomplete Tables of Breast Cancer Characteristics With an Ordinal Variable

  • B. Nebiyou Bekele
  • Luis E. Nieto-Barajas
  • Mark F. Munsell


Our goal is to model the joint distribution of a series of 4 × 2 × 2 × 2 contingency tables for which some of the data are partially collapsed (i.e., aggregated in as few as two dimensions). More specifically, the joint distribution of four clinical characteristics in breast cancer patients is estimated. These characteristics include estrogen receptor status (positive/negative), nodal involvement (positive/negative), HER2-neu expression (positive/negative), and stage of disease (I, II, III, IV). The joint distribution of the first three characteristics is estimated conditional on stage of disease and we propose a dynamic model for the conditional probabilities that let them evolve as the stage of disease progresses. The dynamic model is based on a series of Dirichlet distributions whose parameters are related by a Markov prior structure (called dynamic Dirichlet prior). This model makes use of information across disease stage (known as “borrowing strength” and provides a way of estimating the distribution of patients with particular tumor characteristics. In addition, since some of the data sources are aggregated, a data augmentation technique is proposed to carry out a meta-analysis of the different datasets.


Bayesian methods Breast cancer CISNET Data augmentation Dynamic model Markov Dirichlet sequence Meta-analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Agresti, A. 2007. An introduction to categorical data analysis. Hoboken, NJ, Wiley.CrossRefGoogle Scholar
  2. Bernardo, J. M., and A. F. M. Smith. 2000. Bayesian theory. New York, Wiley.zbMATHGoogle Scholar
  3. Berry, D. A., K. A. Cronin, S. K. Plevritis, D. G. Fryback, L. Clarke, M. Zelen, J. S. Mandelblatt, A. Y. Yakovlev, J. D. Habbema, and E. J. Feuer. 2005. Effect of screening and adjuvant therapy on mortality from breast cancer. N. Eng. J. M. 353, 1784–1792.CrossRefGoogle Scholar
  4. Choi, D. H., D. B. Shin, M. H. Lee, D. W. Lee, D. Dhandapani, D. Carter, B. L. King, and B. G. Haffty. 2003. A comparison of five immunohistochemical biomarkers and HER-2/neu gene amplification by fluorescence in situ hybridization in white and Korean patients with early-onset breast carcinoma. Cancer 9(8), 1587–1595.CrossRefGoogle Scholar
  5. De Laurentiis, M., G. Arpino, E. Massarelli, et al. 2005. A meta-analysis on the interaction between HER-2 expression and response to endocrine treatment in advanced breast cancer. Cli. Cancer Res. 11, 4741–4748.CrossRefGoogle Scholar
  6. Di Fiore, P. P., J. H. Pierce, T. P. Fleming, et al. 1987. Overexpression of the human EGF receptor confers an EGF-dependent transformed phenotype to NIH3T3 cells. Cell, 51, 1063–1070.CrossRefGoogle Scholar
  7. Feuer, E. J., et al. 2006. The impact of mammography and adjuvant therapy on U.S. breast cancer mortality (1975–2000): Collective results from the Cancer Intervention and Surveillance Modeling Network. JNCI Monogr., 36, 1–126.Google Scholar
  8. Hudziak, R. M., J. Schlessinger, and A. Ullrich. 1987. Increased expression of the putative growth factor receptor p185HER2 causes transformation and tumorigenesis of NIH3T3 cells. Proc. Nat. Acad. Sci. 84, 7159–7163.CrossRefGoogle Scholar
  9. Hunter, J. E., and F. L. Schmidt. 2000. Fixed effects vs. random effects meta-analysis models: Implications for cumulative research knowledge. Int. J. Selection Assess., 8, 275–292.CrossRefGoogle Scholar
  10. Ibrahim, J. G., and P. W. Laud. 1994. A predictive approach to the analysis of designed experiments. J. Am. Stat. Assoc., 89, 309–319.MathSciNetCrossRefGoogle Scholar
  11. Nieto-Barajas, L. E., and S. G. Walker. 2002. Markov beta and gamma processes for modelling hazard rates. Scand. J. Stat. 29, 413–424.MathSciNetCrossRefGoogle Scholar
  12. Sinha, D., and D. K. Dey. 1997. Semiparametric Bayesian analysis of survival data. J. Am. Stat. Assoc., 92, 1195–1212.MathSciNetCrossRefGoogle Scholar
  13. Slamon, D. J., G. M. Clark, S. G. Wong, et al. 1987. Human breast cancer: Correlation of relapse and survival with amplification of the HER-2/neu oncogene. Science, 235, 177–182.CrossRefGoogle Scholar
  14. Slamon, D. J., W. Godolphin, L. A. Jones, et al. 1989. Studies of the HER-2/neu proto-oncogene in human breast and ovarian cancer. Science, 244, 707–712.CrossRefGoogle Scholar
  15. Smith, A. F. M., and G. O. Roberts. 1993. Bayesian computations via the Gibbs sampler and related Markov chain Monte Carlo methods. J. R. Stat. Soc. Ser. B, 55, 3–23.MathSciNetzbMATHGoogle Scholar
  16. Spiegelhalter, D., A. Thomas, N. Best, and D. Lunn. 2003. WinBugs user manual: Version 1.4.
  17. Surveillance, Epidemiology, and End Results (SEER) Program. 2006. SEER * STAT Database: Incidence—SEER 9 Regs Public-Use, Nov 2005 Sub (1973–2003), National Cancer Institute, DCCPS, Surveillance Research Program, Cancer Statistics Branch, released April 2006, based on the November 2005 submission.
  18. Tanner, M. A. 1991. Tools for statistical inference: Observed data and data augmentation methods. New York, Springer.CrossRefGoogle Scholar
  19. Tierney, L., 1994. Markov chains for exploring posterior distributions. Ann. Stat. 22, 1701–1728.MathSciNetCrossRefGoogle Scholar
  20. Tudur Smith, C., and P. R. Williamson. 2007. A comparison of methods for fixed effects meta-analysis of individual patient data with time to event outcomes. Clin. Trials, 6, 621–630.CrossRefGoogle Scholar
  21. Veeramachaneni, S., D. Sona, and P. Avesani. 2005. Hierarchical Dirichlet model for document classification. In Proceedings of the 22nd International Conference on Machine Learning, 928–935. New York, ACM Press.Google Scholar

Copyright information

© Grace Scientific Publishing 2012

Authors and Affiliations

  • B. Nebiyou Bekele
    • 1
  • Luis E. Nieto-Barajas
    • 2
  • Mark F. Munsell
    • 3
  1. 1.Gilead Sciences, Inc.Foster CityUSA
  2. 2.Department of StatisticsITAMMexico CityMexico
  3. 3.Department of BiostatisticsUniversity of Texas M. D. Anderson Cancer CenterHoustonUSA

Personalised recommendations