Almost sure properties of weighted vectorial martingales transforms with applications to prediction for linear regression models

• Autorzy: Cénac P.
• Języki publikacji: EN

Abstrakty

EN

We establish new almost sure properties for powers of weighted martingale transforms. It allows us to deduce useful asymptotic results for cumulative prediction and estimation errors associated with linear regression models. We also provide two examples of applications on the linear and functional autoregressive models.

Słowa kluczowe

EN

linear regression models; martingales transforms; least squares estimators; cumulative prediction; cumulative estimation errors

• Wydawca: Wrocław University of Science and Technology
• Czasopismo: Probability and Mathematical Statistics
• Rocznik: 2003
• Tom: Vol. 23, Fasc. 1
• Strony: 61--76
• Opis fizyczny: Bibliogr. 17 poz.

Twórcy

autor

Cénac P.

• Laboratoire de Mathématiques, UMR 8628 CNRS, Bâtiment 425, Université Paris-Sud, 91405 Orsay Cedex, France

Bibliografia

• [1] B. Bercu, Weighted estimation and tracking for ARMAX models, SIAM J. Control Optim. 33, No. 1 (1995), pp. 89-106.
• [2] 3. Bercu, On the convergence of moments in the almost sure central limit theorem for martingales with statistical applications, submitted for publication (2002).
• [3] B. Bercu and M. Duflo, Moindres carrés pondérés et poursuite, Ann. Inst. H. Poincaré 28, No. 3 (1992), pp. 403-430.
• [4] M. Duflo, Random Iterative Methods, Springer, 1997.
• [5] M. Duflo, R. Senoussi and A. Touati, Propriétés asymptotiques presque sûres de l'estimateur des moindres carrés d'un modèle autoregressif vectoriel, Ann. Inst. H. Poincaré 27, No. 1 (1991), pp. 1-25.
• [6] G. C. Goodwin and K. S. Sin, Adaptative Filtering Prediction and Control, Prentice-Hall, Englewood Cliffs, N. J, 1984.
• [7] L. Guo, Self-convergence of weighted least-squares with applications to stochastic adaptive control, IEEE Trans. Automat. Control 41, No. 1 (1996), pp. 79-89.
• [8] R. A. Horn and C. R. Johnson, Topics in Matrix Analysis, Cambridge University Press, 1991.
• [9] C. K. Ing, A note on mean-squared prediction errors of the least squares predictors in random walk models, J. Time Ser. Anal. 22, No. 6 (2001), pp. 711-724.
• [10] T. L. Lai and C. Z. Wei, Least-squares estimates in stochastic regression models with applications to identification and control of dynamic systems, Ann. Statist. 10, No. 1 (1982), pp, 154-166.
• [11] T. L. Lai and C. Z. Wei, Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters, J. Multivariate Anal. 13 (1983), pp. 1-23.
• [12] R. Lipster and V. Spokoiny, Deviation probability bound for martingales with applications to statistical estimation, Statist. Probab. Lett. 46, No. 4 (2000), pp. 347-357.
• [13] W. F. Stout, Almost Sure Convergence, Academic Press, 1974.
• [14] C. Z. Wei, Asymptotic properties of least-squares estimates in stochastic regression models, Ann. Statist. 13, No. 4 (1985), pp. 1498-1508.
• [15] C. Z. Wei, Adaptative prediction by least squares predictors in stochastic regression models with applications to time series, Ann. Statist 15, No. 4 (1987), pp. 1667-1682.
• [16] C. Z. Wei, On predictive least squares principles, Ann. Statist. 20, No. 1 (1992), pp. 1-42.
• [17] J. F. Yao, On least squares estimation for stable nonlinear AR processes, Ann. Inst. Statist. Math. 52, No. 2 (2000), pp. 316-331.