Rüschendorf, Adaptive estimation of hazard functions

• Autorzy: Döhler S. , Rüschendorf L.
• Języki publikacji: EN

Abstrakty

EN

In this paper we obtain convergence rates for sieved maximum-likelihood estimators of the log-hazard function in a censoring model. We also establish convergence results for an adaptive version of the estimator based on the method of structural risk-minimization. Applications are discussed to tensor product spline estimators as well as to neural net and radial basis function sieves. We obtain simplified bounds in comparison to the known literature. This allows us to derive several new classes of estimators and to obtain improved estimation rates. Our results extend to a more general class of estimation problems and estimation methods (minimum contrast estimators).

Słowa kluczowe

EN

adaptive estimation; sieved maximum likelihood; neural nets; structural risk minimization; hazard function

• Wydawca: Wrocław University of Science and Technology
• Czasopismo: Probability and Mathematical Statistics
• Rocznik: 2002
• Tom: Vol. 22, Fasc. 2
• Strony: 355--379
• Opis fizyczny: Biblogr. 27 poz.

Twórcy

autor

Döhler S.

• University of Freiburg, Institute for Mathematical Stochastics, Eckerstr. 1 79104 Freiburg, Germany

autor

Rüschendorf L.

• University of Freiburg, Institute for Mathematical Stochastics, Eckerstr. 1 79104 Freiburg, Germany

Bibliografia

• [1] P. K. Andersen, O. Borgan, R. Gill and N, Keiding, Statistical Models Based on Counting Processes, Springer, 1993.
• [2] A. R. Barron, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inform. Theory 39 (3) (1993), pp. 930-945.
• [3] A. R. Barron, Approximation and estimation bounds for artificial neural networks, Machine Learning 14 (1994), pp. 115-133.
• [4] A. R. Barron, L. Birgé and P. Massart, Risk bounds for model selection via penalization, Probab. Theory Related Fields 113 (3) (1999), pp. 301-413.
• [5] L. Birgé and P. Massart, Minimum contrast estimators on sieves: Exponential bounds and rates of convergence, Bernoulli 4 (3) (1998), pp. 329-375.
• [6] S. Döhler, Consistent hazard regression estimation by sieved maximum likelihood estimators, in: Proceedings of Conference on Limit Theorems in Balatonlelle, 2000.
• [7] S. Döhler, Empirische Risiko-Minimierung bei zensierten Daten, Ph. D. Thesis, Universität Freiburg 2000, http://webdoc.sub.gwdg.de/ebook/e/2001/freidok/69.dpf.
• [8] S. Döhler and L. Rüschendorf, A consistency result in general censoring models, Statistics (2000).
• [9] S. Döhler and L. Rüschendorf, An approximation result for nets in functional estimation, Statist. Probab. Lett. 52 (2001), pp. 373-380.
• [10] S. Döhler and L. Rüschendorf, On adaptive estimation by neural net type estimators, in: Nonlinear Estimation and Classification, D. Denison, M. Hausen, C. Holmes, B. Mallick and B. Yu (Eds.), Lecture Notes in Statist., Springer 2002.
• [11] M. Kohler, Nichtparametrische Regressionsschätzung mit Splines, Ph. D. Thesis, Universität Stuttgart, 1997, http ://www.mathematik.unistuttgart.de/mathA/lst3/kohler/papers!html.
• [12] M. Kohler, Nonparametric estimation of piecewise smooth regression functions, Statist. Probab. Lett. 43 (1999), pp. 49-55.
• [13] M. Kohler, Universally consistent regression function estimation using hierarchical B-splines, J. Multivariate Anal. 68 (1999), pp. 138-164.
• [14] C. Kooperberg, C. J. Stone and Y. K. Truong, Hazard regression, J. Amer. Statist. Assoc. 90 (1995), pp. 78-94.
• [15] C. Koopérberg, C. J. Stone and Y. K. Truong, The L2 rate of convergence for hazard regression, Scand. J. Statist. 22 (1995), pp. 143-157.
• [16] A. Krzyzak and T. Linder, Radial basis function networks and computational regularization in function learning, IEEE Trans. Inform. Theory 9 (1998), pp. 247-256.
• [17] W. Lee, P. Bartlett and R. Williamson, Efficient agnostic learning of neural networks with bounded fan-in, IEEE Trans. Inform. Theory 42 (6) (1996), pp. 2118-2132.
• [18] G. Lugosi and K. Zeger, Nonparametric estimation via empirical risk minimization, IEEE Trans. Inform. Theory 41 (3) (1995), pp. 677-687.
• [19] D. Modha and E. Masry, Rate of convergence in density estimation using neural networks, Neural Computation 8 (1996), pp. 1107-1122.
• [20] D. Pollard, Convergence of Stochastic Processes, Series in Statistics, Vol. 14, Springer, 1984.
• [21] D. Pollard, Empirical Processes: Theory and Applications, Institute of Mathematical Statistics, Hayward, 1990.
• [22] A. van der Vaart and J. Wellner, Weak Convergence and Empirical Processes, Springer, New York 1996.
• [23] I. van Keilegom and N. Veraverbeke, Hazard rate estimation in non-parametric regression with censored data, Ann. Inst. Statist. Math. 53 (2001), pp. 730-745.
• [24] V. Vapnik, The Nature of Statistical Learning Theory, Springer, New York 1995.
• [25] W. Wong and X. Shen, Probability inequalities for likelihood ratios and convergence rates of sieve mles, Ann. Statist. 23 (1995), pp. 339-362.
• [26] Y. Yang and A. Barron, An asymptotic property of model selection criteria, IEEE Trans. Inform. Theory 44 (1998), pp. 95-116.
• [27] J. Yukich, M. Stichcombe and H. White, Sup-norm approximation bounds for networks through probabilistic methods, IEEE Trans. Inform. Theory 41 (4) (1995), pp. 1021-1027.