Probability Theory and Related Fields

, Volume 76, Issue 4, pp 509–522

Characterizations of natural exponential families with power variance functions by zero regression properties

  • Shaul K. Bar-Lev
  • Osnat Stramer


Series of new characterizations by zero regression properties are derived for the distributions in the class of natural exponential families with power variance functions. Such a class of distributions has been introduced in Bar-Lev and Enis (1986) in the context of an investigation of reproductible exponential families. This class is broad and includes the following families: normal, Poisson-type, gamma, all families generated by stable distributions with characteristic exponent an element of the unit interval (among these are the inverse Gaussian, Modified Bessel-type, and Whittaker-type distributions), and families of compound Poisson distributions generated by gamma variates. The characterizations by zero regression properties are obtained in a unified approach and are based on certain relations which hold among the cumulants of the distributions in this class. Some remarks are made indicating how the techniques used here can be extended to obtain characterizations of general exponential families.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bar-Lev, S.K., Enis, P.: Reproducibility and natural exponential families with power variance functions. Ann. Statist.14, 1507–1522 (1986)Google Scholar
  2. Christensen, I.F.: Some further extensions of a theorem of Marcinkiewicz. Pacific J. Math.12, 59–67 (1962)Google Scholar
  3. Gordon, F.S.: Characterizations of populations using regressions properties. Ann. Statist.1, 114–126 (1973)Google Scholar
  4. Heller, B.: Special functions and characterizations of probability distributions by constant regression of polynomial statistics on the mean. Unpublished Ph. D. dissertation, Department of Statistics, University of Chicago 1979Google Scholar
  5. Heller, B.: Special functions and characterizations of probability distributions by zero regression properties. J. Multi. Anal.13, 473–487 (1983)Google Scholar
  6. Hougaard, P.: Survival models for heterogeneous populations derived from stable distributions. Biometrika73, 387–396 (1986)Google Scholar
  7. Jørgensen, B.: Exponential dispersion models (with discussion). To appear in J. Roy Statist. Soc. Ser. B49 (1987)Google Scholar
  8. Kagan, A.M., Linnik, Yu. V., Rao, C.R.: Characterizations problems in mathematical statistics. New York: Wiley 1973Google Scholar
  9. Kawata, T.: Fourier analysis in probability theory. New York London: Academic Press 1972Google Scholar
  10. Lukacs, E.: Characterizations of populations by properties of suitable statistics. Proc. 3rd Berkeley Symp. on Math. Statist, and Probab. Theory2, 195–214 (1956)Google Scholar
  11. Lukacs, E.: On the characterization of a family of populations which includes the Poisson population. Ann. Univ. Sci. Budapest Eotuos Sect. Math.3–4, 159–175 (1962)Google Scholar
  12. Lukacs, E.: Characterization problems for discrete distributions. In: Patil, G. (ed.) Proceedings International Symposium on Classical and Contagious discrete Distributions, pp. 65–73. Oxford New York: Pergamon 1963Google Scholar
  13. Lukacs, E.: Characteristic functions, 2nd edn. New York: Hafner 1970Google Scholar
  14. Lukacs, E., Laha, R.G.: Applications of characteristic functions. London: Griffin 1964Google Scholar
  15. Seshadri, V.: The inverse Gaussian distributions: some properties and characterizations. Can. J. Statist.11, 131–136 (1983)Google Scholar
  16. Tweedie, M.C.K.: An index which distinguishes between some important exponential families. In: Ghosh, J.K., Roy, J. (eds.) Statistics: applications and new directions. Proceedings of the Indian Statistical Institute Golden Jubilee International Conference, pp. 579–604. Calcutta: Indian Statistical Institute 1984Google Scholar

Copyright information

© Springer-Verlag 1987

Authors and Affiliations

  • Shaul K. Bar-Lev
    • 1
  • Osnat Stramer
    • 1
  1. 1.Department of StatisticsUniversity of HaifaHaifaIsrael

Personalised recommendations