Information inequalities for the Bayes risk of predictors

• Autorzy: Kałuszka M.
• Języki publikacji: EN

Abstrakty

EN

The paper provides several lower bounds and an upper bound for the Bayes risk in statistical prediction theory. The bounds depend on the Fisher information or the bias of the Bayes predictor. The results improve and extend the inequalities of Brown and Gajek (1990), Takada (1999) and Koike (1999). As an application we evaluate the minimax risk in a problem of sequential prediction.

Słowa kluczowe

EN

prediction; Bayes risk; information inequality

• Wydawca: Wrocław University of Science and Technology
• Czasopismo: Probability and Mathematical Statistics
• Rocznik: 2007
• Tom: Vol. 27, Fasc. 2
• Strony: 167--179
• Opis fizyczny: Bibliogr. 24 poz.

Twórcy

autor

Kałuszka M.

• Institute of Mathematics, Technical University of Łódź, ul. Wólczańska 215, 93-005 Łódź, Poland

Bibliografia

• [1] E. N. Belitser and B. Y. Levit, Asymptotically minimax nonparametric regression in L2, Statistics 28 (1996), pp. 105-132.
• [2] J. F. Bjørnstad, On the generalization of the likelihood function and the likelihood principle, J. Amer. Statist. Assoc. 91 (1996), pp. 791-806.
• [3] B. Z. Bobrovsky, E. Mayer-Wolf and M. Zakai, Some classes of global Cramer-Rao bounds, Ann. Statist. 15 (1987), pp. 1421-1438.
• [4] A. A. Borovkov and A. U. Sakhanienko, On estimates of the expected quadratic risk, Probab. Math. Statist. 1 (1980), pp. 185-195.
• [5] L. D. Brown and L. Gajek, Information inequalities for the Bayes risk, Ann. Statist. 18 (1990), pp. 1578-1594.
• [6] L. Gajek and M. Kałuszka, Lower bounds for the asymptotic Bayes risk in the scale model (with an application to the second order minimax estimation), Ann. Statist. 22 (1994), pp. 1831-1839.
• [7] L. Gajek and M. Kałuszka, Nonexponential applications of a global Cramér-Rao inequality, Statistics 26 (1995), pp. 111-122.
• [8] L. Gajek and V. Lipińska, Sharp inequality for the Bayes prediction risk, Inequality Theory and Applications 5 (2006), pp. 32-45.
• [9] R. D. Gill and B. Y. Levit, Applications of the Van Trees inequality: a Bayesian Cramér-Rao bound, Bernoulli 1 (1995), pp. 59-79.
• [10] A. Jokiel-Rokita, Minimax prediction under random sample size, Appl. Math. 29 (2002), pp. 127-134.
• [11] M. Kałuszka, Influence of censorship on the minimax risk of decision procedures, Statistics 29 (1997), pp. 169-178.
• [12] K. Koike, A lower bound for the Bayes risk in the sequential case, Comm. Statist. Theory Methods 28 (1999), pp. 857-871.
• [13] Y. A. Kutoyants and У. Spokoiny, Optimal choice of observation window for Poisson observations, Statist. Probab. Lett. 44 (1999), pp. 291-298.
• [14] Y. Miyata, The lower bound for MSE in statistical prediction theory, J. Japan Statist. Soc. 31 (2001), pp. 111-127.
• [15] B. Mizera, Lower bounds on the minimax risk of sequential estimators, Statistics 28 (1996), pp. 123-129.
• [16] A. Munk and F. Ruymgaart, Minimax rates for estimating the variance and its derivatives in nonparametric regression -an application of the Van Trees inequality, Aust. N.Z.J. Stat. 44 (2002), pp. 479-488.
• [17] Т. K. Nayak, Rao-Cramér type inequalities for mean squared error of prediction, Amer. Statist. 56 (2002), pp. 102-106.
• [18] M. Sato and M. Akahira, An information inequality for the Bayes risk, Ann. Statist. 24 (1996), pp. 2288-2295.
• [19] Y. Таkada, Lower bounds on the Bayes risk for statistical prediction problems, Comm. Statist. Theory Methods 28 (1999), pp. 693-703.
• [20] H. Van Trees, Detection, Estimation and Modulation Theory, Wiley, New York 1968.
• [21] S. Trybuła, Minimax mutual prediction of multinomial random variables, Appl. Math. 30 (2003), pp. 371-377.
• [22] M. Wilczyński, Minimax nonparametric prediction under random sample size, Sci. Math. Jpn. 53 (2001), pp. 401-409.
• [23] Y. G. Yatracos, On prediction and mean squared error, Canad. J. Statist. 20 (1992), pp. 187-200.
• [24] T. Zhang and M. Woodroofe, Admissible minimax estimation of the signal with known background, Statist. Sinica 15 (2005), pp. 59-72.