Skip to main content
SpringerLink
Log in

Empirical Bayes with rates and best rates of convergence in u(x)C(θ) exp(-x/θ)-family: Estimation case

  • Bayesian Procedures
  • Published:
Annals of the Institute of Statistical Mathematics Aims and scope Submit manuscript

Abstract

Let % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaai4EaiaacI% cacaWGybWaaSbaaSqaaiaadMgaaeqaaOGaaiilaiabeI7aXnaaBaaa% leaacaWGPbaabeaakiaacMcacaGG9baaaa!3ED1!\[\{ (X_i ,\theta _i )\} \] be a sequence of independent random vectors where X i , conditional on % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiUde3aaS% baaSqaaiaadMgaaeqaaaaa!38BD!\[\theta _i \], has the probability density of the form % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamOzaiaacI% cacaWG4bGaaiiFaiabeI7aXnaaBaaaleaacaWGPbaabeaakiaacMca% cqGH9aqpcaWG1bGaaiikaiaadIhacaGGPaGaam4qaiaacIcacqaH4o% qCdaWgaaWcbaGaamyAaaqabaGccaGGPaGaaeyzaiaabIhacaqGWbGa% aiikaiabgkHiTiaadIhacaGGVaGaeqiUde3aaSbaaSqaaiaadMgaae% qaaOGaaiykaaaa!4FFF!\[f(x|\theta _i ) = u(x)C(\theta _i ){\text{exp}}( - x/\theta _i )\] and the unobservable % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqiUde3aaS% baaSqaaiaadMgaaeqaaaaa!38BD!\[\theta _i \] are i.i.d. according to an unknown G in some class G of prior distributions on Θ, a subset of % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaai4EaiabeI% 7aXjabg6da+iaaicdacaGG8bGaam4qaiaacIcacqaH4oqCcaGGPaGa% eyypa0JaaiikaiaadAgacaWG1bGaaiikaiaadIhacaGGPaGaaeyzai% aabIhacaqGWbGaaeikaiabgkHiTiaadIhacaGGVaGaeqiUdeNaaiyk% aiaadsgacaWG4bGaaiykamaaCaaaleqabaGaeyOeI0IaaGymaaaaki% abg6da+iaaicdacaGG9baaaa!54DE!\[\{ \theta > 0|C(\theta ) = (fu(x){\text{exp(}} - x/\theta )dx)^{ - 1} > 0\} \]. For a S(X 1 , ..., Xn, Xn+1)-measurable function % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqOXdy2aaS% baaSqaaiaad6gaaeqaaOGaaiilaaaa!397F!\[\phi _n ,\] let % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaamOuamaaBa% aaleaacaWGUbaabeaakiabg2da9iaadweacaGGOaGaeqOXdy2aaSba% aSqaaiaad6gaaeqaaOGaeyOeI0IaeqiUde3aaSbaaSqaaiaad6gacq% GHRaWkcaaIXaaabeaakiaacMcadaahaaWcbeqaaiaaikdaaaaaaa!444A!\[R_n = E(\phi _n - \theta _{n + 1} )^2 \] denote the Bayes risk of % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqOXdy2aaS% baaSqaaiaad6gaaeqaaaaa!38C5!\[\phi _n \] and let R(G) denote the infimum Bayes risk with respect to G. For each integer s>1 we exhibit a class of S(X 1 , ..., Xn, Xn+1)-measurable functions % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqOXdy2aaS% baaSqaaiaad6gaaeqaaaaa!38C5!\[\phi _n \] such that for δ in [s −1, 1], % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaam4yamaaBa% aaleaacaaIWaaabeaakiaad6gadaahaaWcbeqaaiabgkHiTiaaikda% caWGZbGaai4laiaacIcacaaIXaGaey4kaSIaaGOmaiaadohacaGGPa% aaaOGaeyizImQaamOuamaaBaaaleaacaWGUbaabeaakiaacIcacqaH% gpGzdaWgaaWcbaGaamOBaaqabaGccaGGSaGaam4raiaacMcacqGHsi% slcaWGsbGaaiikaiaadEeacaGGPaGaeyizImQaam4yamaaBaaaleaa% caaIXaaabeaakiaad6gadaahaaWcbeqaaiabgkHiTiaaikdacaGGOa% Gaam4Caiabes7aKjabgkHiTiaaigdacaGGPaGaai4laiaacIcacaaI% XaGaey4kaSIaaGOmaiaadohacaGGPaaaaaaa!5F94!\[c_0 n^{ - 2s/(1 + 2s)} \leqslant R_n (\phi _n ,G) - R(G) \leqslant c_1 n^{ - 2(s\delta - 1)/(1 + 2s)} \] under certain conditions on u and G. No assumptions on the form or smoothness of u is made, however. Examples of functions u, including one with infinitely many discontinuities, are given for which our conditions reduce to some moment conditions on G. When Θ is bounded, for each integer s>1 S(X 1 , ..., Xn, Xn+1)-measurable functions % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaeqOXdy2aaS% baaSqaaiaad6gaaeqaaaaa!38C5!\[\phi _n \] are exhibited such that for δ in % MathType!MTEF!2!1!+-% feaafiart1ev1aaatCvAUfeBSjuyZL2yd9gzLbvyNv2CaerbuLwBLn% hiov2DGi1BTfMBaeXatLxBI9gBaerbd9wDYLwzYbItLDharqqtubsr% 4rNCHbGeaGqiVu0Je9sqqrpepC0xbbL8F4rqqrFfpeea0xe9Lq-Jc9% vqaqpepm0xbba9pwe9Q8fs0-yqaqpepae9pg0FirpepeKkFr0xfr-x% fr-xb9adbaqaaeGaciGaaiaabeqaamaabaabaaGcbaGaai4waiaaik% dacaGGVaGaam4CaiaacYcacaaIXaGaaiyxaiaadogadaqhaaWcbaGa% aGimaaqaaiaacEcaaaGccaWGUbWaaWbaaSqabeaacqGHsislcaaIYa% Gaam4Caiaac+cacaGGOaGaaGymaiabgUcaRiaaikdacaWGZbGaaiyk% aaaakiabgsMiJkaadkfadaWgaaWcbaGaamOBaaqabaGccaGGOaGaeq% OXdy2aaSbaaSqaaiaad6gaaeqaaOGaaiilaiaadEeacaGGPaGaeyOe% I0IaamOuaiaacIcacaWGhbGaaiykaiabgsMiJkaadogadaqhaaWcba% GaaGymaaqaaiaacEcaaaGccaWGUbWaaWbaaSqabeaacqGHsislcaaI% YaGaam4Caiabes7aKjaac+cacaGGOaGaaGymaiabgUcaRiaaikdaca% WGZbGaaiykaaaaaaa!637D!\[[2/s,1]c_0^' n^{ - 2s/(1 + 2s)} \leqslant R_n (\phi _n ,G) - R(G) \leqslant c_1^' n^{ - 2s\delta /(1 + 2s)} \]. Examples of functions u and class g are given where the above lower and upper bounds are achieved.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Fox, R. (1978). Solutions to empirical Bayes squared error loss estimation problems, Ann. Statist., 6, 846–853.

    Google Scholar 

  • Hannan, J. and Macky, D. W. (1971). Empirical Bayes squared-error loss estimation of unbounded functionals in exponential families, RM-290, Department of Statistics and Probability, Michigan State University, East Lansing.

    Google Scholar 

  • Johns, M. V.Jr. (1957). Nonparametric empirical Bayes procedures, Ann. Math. Statist., 28, 649–669.

    Google Scholar 

  • Johns, M. V.Jr. and VanRyzin, J. R. (1971). Convergence rates for empirical Bayes two-action problems I: discrete case, Ann. Math. Statist., 42, 1521–1539.

    Google Scholar 

  • Johns, M. V.Jr. and VanRyzin, J. R. (1972). Convergence rates for empirical Bayes two-action problems II: continuous case, Ann. Math. Statist., 43, 934–947.

    Google Scholar 

  • Lamperty, J. (1966). Probability, W. A. Benjamin, New York.

    Google Scholar 

  • Lehmann, E. L. (1959). Testing of Statistical Hypothesis, Wiley, New York.

    Google Scholar 

  • Liang, T. (1988). On the convergence rates of empirical Bayes rules for two-action problems: discrete case, Ann. Statist., 16, 1635–1642.

    Google Scholar 

  • Lin, P. E. (1975) Rates of convergence in empirical Bayes estimation problems: continuous case, Ann. Statist., 3, 155–164.

    Google Scholar 

  • Maritz, J. S. (1969). Empirical Bayes estimation for continuous distributions. Biometrika, 56, 349–359.

    Google Scholar 

  • Maritz, J. S. and Lwin, T. (1975). Construction of simple empirical Bayes estimators, J. Roy. Statist. Soc. Ser. B, 75, 421–425.

    Google Scholar 

  • O'Bryan, T. E. and Susarla, V. (1976). Rates in the empirical Bayes estimation problem with nonidentical components: case of normal distributions, Ann. Inst. Statist. Math., 28, 389–397.

    Google Scholar 

  • Prasad, B. and Singh, R. S. (1990). Estimation of prior distribution and empirical Bayes estimation in a nonexponential family, J. Statist. Plann. Inference, 24, 81–86.

    Google Scholar 

  • Robbins, H. (1955). An empirical Bayes approach to statistics, Proc. Third Berkeley Symp. on Math. Statist. Prob., Vol. 1, 157–163, Univ. California Press, Berkeley.

    Google Scholar 

  • Robbins, H. (1963). The empirical Bayes approach to the testing of statistical hypothesis, Review International Statistical Institute, 31, 195–208.

    Google Scholar 

  • Robbins, H. (1964). The empirical Bayes approach to statistical decision problems, Ann. Math. Statist., 35, 1–20.

    Google Scholar 

  • Samuel, E. (1963). An empirical Bayes approach to the testing of certain parametric hypotheses, Ann. Math. Statist., 34, 1370–1385.

    Google Scholar 

  • Singh, R. S. (1974). Estimation of derivatives of average of μ-densities and sequence compound estimation in exponential family, RM-318, Department of Statistics and Probability, Michigan State University, East Lansing.

    Google Scholar 

  • Singh, R. S. (1976). Empirical Bayes estimation with convergence rates in non-continuous Lebesgue-exponential families, Ann. Statist., 4, 431–439.

    Google Scholar 

  • Singh, R. S. (1977a). Improvement on some known nonparametric uniformly consistent estimators of derivatives of a density, Ann. Statist., 5, 394–400.

    Google Scholar 

  • Singh, R. S. (1977b). Applications of estimators of a density and its derivatives to certain statistical problems, J. Roy. Statist. Soc. Ser. B, 39, 357–363.

    Google Scholar 

  • Singh, R. S. (1978a). Sequence-compound estimation in scale-exponential families and speed of convergence, J. Statist. Plann. Inference, 2, 53–62.

    Google Scholar 

  • Singh, R. S. (1978b). Nonparametric estimation of derivatives of average of μ-densities with convergence rates and applications, SIAM J. Appl. Math., 35, 637–649.

    Google Scholar 

  • Singh, R. S. (1979). Empirical Bayes estimation in Lebesgue-exponential families with rates near the best possible rate, Ann. Statist., 7, 890–902.

    Google Scholar 

  • Singh, R. S. (1980). Estimation of regression curves when the conditional density of the predictor variable is in scale-exponential family, Multivariate Statistical Analysis (ed. R. P.Gupta), 199–205, North-Holland, Amsterdam.

    Google Scholar 

  • Singh, R. S. (1981). Speed of convergence in nonparametric estimation of a multivariate μ-density and its mixed partial derivatives, J. Statist. Plann. Inference, 5, 287–298.

    Google Scholar 

  • Singh, R. S. and Prasad, B. (1991). Uniformly strongly consistent prior-distribution and empirical Bayes estimators with asymptotic optimality and rates in a nonexponential family, Sankhyā Ser. A, 53, 334–342.

    Google Scholar 

  • Yu, B. (1971). Rates of convergence in empirical Bayes two-action and estimation problems and in sequence-compound estimation problems, RM-279, Department of Statistics and Probability, Michigan State University, East Lansing.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics and Statistics, University of Guelph, N1G 2W1, Guelph, Ontario, Canada

    R. S. Singh

  2. Department of Mathematics, University of Science and Technology of China, Hefei, Anhui, P. R. China

    Laisheng Wei

Authors
  1. R. S. Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Laisheng Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Part of the research was carried out during R. S. Singh's visit to the University of Science and Technology of China.

Research supported in part by a Natural Sciences and Engineering Research Council of Canada Grant No. #A4631.

About this article

Cite this article

Singh, R.S., Wei, L. Empirical Bayes with rates and best rates of convergence in u(x)C(θ) exp(-x/θ)-family: Estimation case. Ann Inst Stat Math 44, 435–449 (1992). https://doi.org/10.1007/BF00050697

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00050697

Key words and phrases

Search

Navigation