Journal of the Korean Data and Information Science Society

The Korean Data and Information Science Society (한국데이터정보과학회)
권호 표지
DOI QR코드

DOI QR Code

A Bayesian uncertainty analysis for nonignorable nonresponse in two-way contingency table

  • Woo, Namkyo (Department of Statistics, Kyungpook National University) ;
  • Kim, Dal Ho (Department of Statistics, Kyungpook National University)
  • Received : 2015.08.19
  • Accepted : 2015.10.23
  • Published : 2015.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

We study the problem of nonignorable nonresponse in a two-way contingency table and there may be one or two missing categories. We describe a nonignorable nonresponse model for the analysis of two-way categorical table. One approach to analyze these data is to construct several tables (one complete and the others incomplete). There are nonidentifiable parameters in incomplete tables. We describe a hierarchical Bayesian model to analyze two-way categorical data. We use a nonignorable nonresponse model with Bayesian uncertainty analysis by placing priors in nonidentifiable parameters instead of a sensitivity analysis for nonidentifiable parameters. To reduce the effects of nonidentifiable parameters, we project the parameters to a lower dimensional space and we allow the reduced set of parameters to share a common distribution. We use the griddy Gibbs sampler to fit our models and compute DIC and BPP for model diagnostics. We illustrate our method using data from NHANES III data to obtain the finite population proportions.

Keywords

References

  1. Choi, S. M. and Kim, D. H. (2013). Bayesian estimation for finite population proportion under selection bias via surrogate samples. Journal of the Korean Data & Information Science Society, 24, 1543-1550. https://doi.org/10.7465/jkdi.2013.24.6.1543
  2. Choi, S. M. and Kim, D. H. (2014). Sensitivity analysis in Bayesian nonignorable selection model for binary responses. Journal of the Korean Data & Information Science Society, 25, 187-194. https://doi.org/10.7465/jkdi.2014.25.1.187
  3. Little, R. J. A. and Rubin, D. B. (2002). Statistical analysis with missing data, 2nd Ed., John Wiley & Sons, New York.
  4. Nandram, B. (2009). Bayesian inference of the cell probabilities of a two-way categorical table under nonignorability. Communications in Statistics - Theory and Methods, 38, 3015-3030. https://doi.org/10.1080/03610920902947295
  5. Nandram, B. and Choi, J. W. (2002). A Bayesian analysis of a proportion under nonignorable nonresponse. Statistics in Medicine, 21, 1189-1212. https://doi.org/10.1002/sim.1100
  6. Nandram, B. and Choi, J. W. (2008). A Bayesian allocation of undecided voters. Survey Methodology, 34, 37-49.
  7. Nandram, B., Cox, L. and Choi, J. W. (2005). Bayesian analysis of nonignorable missing categorical data: An application to bone mineral density and family income. Survey Methodology, 31, 213-225.
  8. National Center for Health Statistics. (1992). Third National Health and Nutrition Examination Survey. Vital and Health Statistics Series 2, 113.
  9. Rubin, D. B. (1976). Inference and missing data. Biometrika, 63, 581-592. https://doi.org/10.1093/biomet/63.3.581
  10. Yan, G. and Sedransk, J. (2007). Bayesian diagnostic techniques for detecting hierarchical structure. Bayesian Analysis, 2, 735-760. https://doi.org/10.1214/07-BA230

Cited by

  1. Bayesian pooling for contingency tables from small areas vol.27, pp.6, 2016, https://doi.org/10.7465/jkdi.2016.27.6.1621
  2. Bayes tests of independence for contingency tables from small areas vol.28, pp.1, 2015, https://doi.org/10.7465/jkdi.2017.28.1.207
  3. Bayesian test of homogenity in small areas: A discretization approach vol.28, pp.6, 2017, https://doi.org/10.7465/jkdi.2017.28.6.1547