On Compatibility/Incompatibility of Two Discrete Probability Distributions in the Presence of Incomplete Specification

Abstract

Conditional specification of distributions is a developing area with several applications. In the finite discrete case, a variety of compatible conditions can be derived. In this paper, we revisit a rank–based criterion for identifying compatible distributions corresponding to complete conditional specification, including the case with zeros under the finite discrete set up. Based on this, we primarily focus on the compatibility of two conditionals (under the finite discrete set-up) in which incomplete specification on either or both the conditional matrices are present. Compatibility in the general case are also briefly discussed. The proposed methods are finally illustrated with several examples.

This is a preview of subscription content, access via your institution.

References

  1. Arnold, B.C., Castillo, E. and Sarabia, J.M. (1999). Conditional Specification of Statistical Models. Springer, New York.

    Google Scholar 

  2. Arnold, B.C., Castillo, E. and Sarabia, J.M. (2001). Quantification of incompatibility of conditional and marginal information. Commun. Stat. Theory Methods 30, 381–395.

    MathSciNet  Article  Google Scholar 

  3. Arnold, B.C. and Gokhale, D.V. (1994). On uniform marginal representations of contingency tables. Stat. Probab. Lett. 21, 311–316.

    MathSciNet  Article  Google Scholar 

  4. Arnold, B.C. and Gokhale, D.V. (1998). Distributions most nearly compatible with given families of conditional distributions. Test 7, 377–390.

    MathSciNet  Article  Google Scholar 

  5. Arnold, B.C. and Press, S.J. (1989). Compatible conditional distributions. J. Am. Stat. Assoc. 84, 152–156.

    MathSciNet  Article  Google Scholar 

  6. Cacoullos, T. and Papageorgiou, H. (1983). Characterizations of discrete distributions by a conditional distribution and a regression function. Annals of the Institute of Statistical Mathematics 35, 1, 95–103.

    MathSciNet  Article  Google Scholar 

  7. Ghosh, I. (2011). Inference for the bivariate and multivariate hidden truncated Pareto(type II) and Pareto(type IV) distribution and some measures of divergence related to incompatibility of probability distribution. Ph D thesis, University of California, Riverside.

  8. Ghosh, I. and Balakrishnan, N. (2013). Study of incompatibility or near compatibility of bivariate discrete conditional probability distributions through divergence measures. J. Stat. Comput. Simul. 84, 1–14.

    MATH  Google Scholar 

  9. Ghosh, I. and Nadarajah, S. (2016). An alternative approach for compatibility of two discrete conditional distributions. J. Commun. Stat. Theory Methods45, 4416–4432.

    MathSciNet  Article  Google Scholar 

  10. Wesolowski, J. (1995). Bivariate distributions via a Pareto conditional distribution and a regression function. Ann. Inst. Stat. Math. 47, 177–183.

    MathSciNet  Article  Google Scholar 

Download references

Acknowledgments

We are grateful to the referees as well as the Editor-in-Chief for making some constructive suggestions and comments on an earlier version of this manuscript, which resulted in this much improved version.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Indranil Ghosh.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ghosh, I., Balakrishnan, N. On Compatibility/Incompatibility of Two Discrete Probability Distributions in the Presence of Incomplete Specification. Sankhya A (2021). https://doi.org/10.1007/s13171-021-00243-6

Download citation

Keywords

  • Compatible conditional distribution
  • rank–based criterion
  • incomplete specification.

PACS Nos

  • Primary; 62E20