Summary
We investigate the relations between the speed of estimation and the metric structure of the parameter space Θ, especially in the case when its metric dimension is infinite. Given some distance d on Θ (generally Hellinger distance in the case of n i.i.d. variables), we consider the minimax risk for n observations: \(R_n (q) = \mathop {\inf \sup }\limits_{T_{n } \theta \in \Theta } {\text{IE}}_\theta [d^q (\theta , T_n )],\), T n being any estimate of θ. We shall look for functions r such that for positive constants C 1(q) and C 2(q) C 1 r q(n)≦R n(q)≦C2 r q(n). r(n) is the speed of estimation and we shall show under fairly general conditions (including i.i.d. variables and regular cases of Markov chains and stationnary gaussian processes) that r(n) is determined, up to multiplicative constants, by the metric structure of Θ. We shall also give a construction for some sort of “universal” estimates the risk of which is bounded by C 2 r q(n) in all cases where the preceding theory applies.
Article PDF
Similar content being viewed by others
Bibliographie
Assouad, P.: Espaces métriques, plongements, facteurs. Thèse d'Etat, Orsay (1976)
Assouad, P.: Classes de Vapnik-Červonenkis et vitesse d'estimation. Prépublication: Orsay 1982
Bahadur, R.R.: Examples of inconsistency of maximum likelihood estimates. Sankhya 20, 207–210 (1958)
Beckenbach, E.F., Bellman, R.: Inequalities. Berlin-Heidelberg-New York: Springer 1961
Birgé, L.: Vitesses optimales de convergence des estimateurs. Astérisque 68, 171–185 (1979)
Birgé, L.: Sur un théorème de minimax et son application aux tests. Probab. Math. Statist. III, 2 [To appear 1983]
Birgé, L.: Robust testing for independent non-identically distributed variables and Markov chains. Dans: Specifying statistical models, pp. 134–162. New York-Heidelberg-Berlin: Springer 1983
Bretagnolle, J., Huber, C.: Estimation des densités: risque minimax. Z. Wahrscheinlichkeitstheorie verw. Gebiete 47, 119–137 (1979)
Čencov, N.N.: Statistical decision rule and optimal inference. En russe. Moscou: Nauka 1972
Dacunha-Castelle, D.: Ecole d'Eté de Probabilités de Saint-Flour VII. Berlin-Heidelberg-New York: Springer 1977
Donsker, M.D., Varadhan, S.R.S.: Asymptotic evaluation of certain Markov process expectations for large time, I. Comm. Pure Appl. Math. 28, 1–47 (1975)
Farrell, R.H.: On the best obtainable asymptotic rates of convergence in estimation of a density function at a point. Ann. Math. Statist. 43, 170–180 (1972)
Farrell, R.H.: Asymptotic lower bounds for the risk of estimators of the value of a spectral density function. Z. Wahrscheinlichkeitstheorie verw. Gebiete 49, 221–234 (1979)
Huber, C: Thèse d'Etat: Orsay 1979
Huber, P.J.: A robust version of the probability ratio test. Ann. Math. Statist. 36, 1753–1758 (1965)
Ibragimov, I.A., Khas'minskii, R.Z.: Statistical estimation, Asymptotic theory. New York-Heidelberg-Berlin: Springer 1981
Ibragimov, I.A., Khas'minskii, R.Z.: On estimate of the density function. En russe. Zap. Nauchn. Semin. LOMI 98, 61–85 (1980)
Ibragimov, I.A., Khas'minskii, R.Z.: On the non-parametric density estimates. En russe. Zap. Nauchn. Semin. LOMI 108, 73–89 (1981)
Khas'minskii, R.Z.: A lower bound on the risks of non-parametric estimates of densities in the uniform metric. Theory Probability Appl. 23, 794–796 (1978)
Kolmogorov, A.N., Tihomirov, V.M.: ε-entropy and ε-capacity of sets in function spaces. Amer. Math. Soc. Transl. (2) 17, 277–364 (1961)
Kraft, C.: Some conditions for consistency and uniform consistency of statistical procedures. Univ. of Calif. Publ. in Statistics 1, 125–142 (1955)
Le Cam, L.: Théorie asymptotique de la décision statistique. Presses de l'Université de Montréal: 1968
Le Cam, L.: Convergence of estimates under dimensionality restrictions. Ann. Statist. 1, 38–53 (1973)
Le Cam, L.: On local and global properties in the theory of asymptotic normality of experiments. Dans: Stochastic processes and related topics 1, 13–54. New York-San Francisco-London: Academic Press 1975
Le Cam, L.: An inequality concerning Bayes estimates. Prépublication (1979)
Le Cam, L.: Asymptotic methods in statistical decision theory. Livre à paraître
Lorentz, G.G.: Metric entropy and approximation. Bull. Amer. Math. Society 72, 903–937 (1966)
Lorentz, G.G.: Approximation of functions. New York: Holt, Rinehart, Winston 1966
Okamoto, M.: Some inequalities relating to the partial sum of binomial probabilities. Ann. Inst. Statis. Math. 10, 29–35 (1958)
Pinsker, M.S.: Optimal filtration of square-integrable signals in gaussian noise. Problems of Inform. Transmission 16, 120–133 (1980)
Strasser, H.: Convergence of estimates: parts I and II. J. Multivariate Anal. 11, 127–172 (1981)
Vitushkin, A.G.: Theory of transmission and processing of information. New York: Pergamon Press 1961
Wahba, G.: Optimal convergence properties of variable knot, kernel and orthogonal series methods for density estimation. Ann. Statist. 3, 15–29 (1975)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Birgé, L. Approximation dans les espaces métriques et théorie de l'estimation. Z. Wahrscheinlichkeitstheorie verw Gebiete 65, 181–237 (1983). https://doi.org/10.1007/BF00532480
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00532480