Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Three Binomial-related Models in the Estimation of Correlations

  • Published : 2003.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

It has been generally recognized that conventional binomial or Poisson model provides poor fits to the actual correlated binary data due to the extra-binomial variation. A number of generalized statistical models have been proposed to account for this additional variation. Among them, beta-binomial, correlated-binomial, and modified-binomial models are binomial-related models which are frequently used in modeling the sum of n correlated binary data. In many situations, it is reasonable to assume that n correlated binary data are exchangeable, which is a special case of correlated binary data. The sum of n exchangeable correlated binary data is modeled relatively well when the above three binomial-related models are applied. But the estimation results of correlation coefficient turn to be quite different. Hence, it is important to identify which model provides better estimates of model parameters(success probability, correlation coefficient). For this purpose, a small-scale simulation study is performed to compare the behavior of above three models.

Keywords

References

  1. Applied Statistics v.27 Two Generalizations of the Binomial Distribution Altham,P.M.E. https://doi.org/10.2307/2346943
  2. Studies in Item Analysis and Prediction A Representation of the Joint Distribution of Responses to n Dichotomous Items Bahadur,R.R.;H.Solomon(ed.)
  3. Mutation Research v.41 The Distribution of Fetal Death in Control Mice and Its Implications on Statistical Tests for Dominant Lethal Effects Haseman,J.K.;Soares,E.F. https://doi.org/10.1016/0027-5107(76)90101-9
  4. IMSL User's Manual IMSL Inc.
  5. Biometrics v.42 The Impact of Litter Effects on Dose-response Modeling in Teratology Kupper,L.L.;Portier,C.;Hogan,M.D.;Yamamoto,E. https://doi.org/10.2307/2531245
  6. Biometrics v.34 The Use of a Correlated Binomial Model for the Analysis of Certain Toxicological Experiments Kupper,L.L.;Haseman,J.K. https://doi.org/10.2307/2529589
  7. Biometrika v.85 no.2 A Note on Generating Correlated Binary Variables Lunn,A.D.;Davies,S.J. https://doi.org/10.1093/biomet/85.2.487
  8. Communications in Statistics-Theory and Methods v.22 Generalized Binomial Distributions Madsen,R. https://doi.org/10.1080/03610929308831203
  9. Communications in Statistics-Theory and Methods v.18 A New Class of Modified Binomial Distributions with Applications to Certain Toxicological experiments Ng,T.H. https://doi.org/10.1080/03610928908830104
  10. Communications in Statistics-Theory and Methods v.14 A Three Parameter Generalization of the Binomial Distribution Paul,S.R. https://doi.org/10.1080/03610928508828990
  11. Communications in Statistics-Theory and Methods v.16 On the Beta-correlated Binomial Distribution-A Three Parameter Generalizations of the Binomial Distribution Paul,S.R. https://doi.org/10.1080/03610928708829449
  12. Biometrics v.31 The Analysis of binary Reponses from Toxicological Experiments Involving Reproduction and Teratogenicity Williams,D.A. https://doi.org/10.2307/2529820

Cited by

  1. Comparative Simulation Studies on Generalized Binomial Models vol.18, pp.4, 2011, https://doi.org/10.5351/CKSS.2011.18.4.507