Lobachevskii Journal of Mathematics

, Volume 39, Issue 3, pp 413–423 | Cite as

Asymptotic Expansion of D-Risks for Hypothesis Testing in Bernoulli Scheme

Article

Abstract

Currently there is not a single asymptotic expansion of d-risk of any statistical procedure. In this paper we present the asymptotic expansion of d-risk function of the optimal test for Bernoulli scheme. The expansion derivation is based on the Edgeworth series of the sufficient statistic for Bernoulli scheme and therefore it is applicable to any one-parametric exponential model.

Keywords

Bayesian analysis d-risk asymptotic expansion Bernoulli distribution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    I. N. Volodin and A. A. Novikov, “Statistical estimators with asymptotically minimum d-risk,” Theory Probab. Appl. 38, 118–128 (1993).MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    I. N. Volodin and A. A. Novikov, “Asymptotics of the necessary sample size for D-guaranteed discrimination of two close hypotheses,” Sov. Math. 27 (11), 67–178 (1983).MathSciNetMATHGoogle Scholar
  3. 3.
    S. V. Simushkin and R. F. Salimov, “Asymptotically most precise two-sided confidence intervals for mean in Normal-Normal model,” Uch. Zap. Kazan. Univ. 152, 205–218 (2010).MATHGoogle Scholar
  4. 4.
    I. N. Volodin and A. A. Novikov, “Local asymptotic efficiency of a sequential probability ratio test for dguarantee discrimination of composite hypotheses,” Theory Probab. Appl. 43, 269–281 (1999).MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    A. A. Novikov, “Asymptotic optimality of the sequential d-guaranty test,” Theory Probab. Appl. 32, 358–361 (1987).CrossRefMATHGoogle Scholar
  6. 6.
    J. K. Ghosh, B. K. Sinha, and S. N. Joshi, “Expansions for posterior probability and integrated Bayes risk,” in Statistical Decision Theory and Related Topics III, Proceedings of the 3rd Purdue Symposium (Academic, New York, 1982), Vol. 1, pp. 403–456.MathSciNetMATHGoogle Scholar
  7. 7.
    S. I. Gusev, “Asymptotic expansions that are connected with certain statistical estimates in the smooth case. II. Expansions of moments and of distributions,” Teor. Veroyatn. Prilozh. 21, 16–32 (1976).MathSciNetGoogle Scholar
  8. 8.
    R. A. Johnson, “Asymptotic expansions associated with posterior distributions,” Ann. Math. Stat. 41, 851–864 (1970).MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    A. A. Zaikin, “On asymptotic expansion of posterior distribution,” Lobachevskii J. Math. 37, 515–525 (2016).MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    A. A. Zaikin, “Asymptotic expansion of posterior distribution of parameter centered by n-consistent estimate,” Zap. Nauch. Sem. SPb. Otd. Mat. Inst. Steklova POMI 454, 121–150 (2016).Google Scholar
  11. 11.
    S. V. Simushkin, “Optimal d-guaranteed procedures of testing two hypotheses,” Available from VINITI No. 5547-81 (1981).Google Scholar
  12. 12.
    I. N. Volodin and A. A. Novikov, “Asymptotics of necessary sample size for guaranteed parametric hypotheses testing,” Issled. Prikl.Mat. 21, 3–41 (1999) [in Russian].MATHGoogle Scholar
  13. 13.
    D. M. Chibisov, “An asymptotic expansion for the distribution of a statistic admitting an asymptotic epansion,” Theory Probab. Appl. 17, 620–630 (1972).CrossRefGoogle Scholar
  14. 14.
    A. A. Zaikin, “Defect of the size of nonrandomized test and randomization effect on decreasing of the necessary sample size in testing the Bernoulli success probability,” Theory Probab. Appl. 59, 466–480 (2015).MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    J. E. Kolassa and P. McCullagh, “Edgeworth series for lattice distributions,” Ann. Stat. 18, 981–985 (1990).MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    R. N. Bhattachariya and R. R. Rao, Normal Approximation and Asymptotic Expansions (SIAM, Philadelphia, 1986).Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  1. 1.Department of Mathematical StatisticsKazan Federal University, Institute of Computational Mathematics and Information TechnologiesKazanRussia

Personalised recommendations