Home | Contents | Submissions, editors, etc. | Login | Search | EJP
 Electronic Communications in Probability > Vol. 15(2010) > Paper 44 open journal systems 


Deviation inequalities for sums of weakly dependent time series

Wintenberger Olivier, CEREMADE


Abstract
In this paper we give new deviation inequalities for the partial sums of weakly dependent data. The loss from the independent case is studied carefully. We give examples of non mixing time series such that dynamical systems and Bernoulli shifts for whom such deviation inequality holds. The proofs are based on the blocks technique and different coupling arguments.


Full text: PDF

Pages: 489-503

Published on: October 19, 2010
Bibliography
  1. Adamczak, Radosław. A tail inequality for suprema of unbounded empirical processes with applications to Markov chains. Electron. J. Probab. 13 (2008), no. 34, 1000--1034. MR2424985 (2009j:60032)
  2. Bennett, G. Probability inequalities for the sum of independant random variables. Journal of the American Statistician Association 57, 33--45.
  3. Bertail, P., and Clémençon, S. Sharp bounds for the tail of functionals of Markov chains. Theory Probab. Appl. 54 (2010) 505--515.
  4. Catoni, Olivier. Statistical learning theory and stochastic optimization.Lecture notes from the 31st Summer School on Probability Theory held in Saint-Flour, July 8–25, 2001.Lecture Notes in Mathematics, 1851. Springer-Verlag, Berlin, 2004. viii+272 pp. ISBN: 3-540-22572-2 MR2163920 (2006d:62004)
  5. Collet, P., Martinez, S., and Schmitt, B. Exponential inequalities for dynamical measures of expanding maps of the interval. Probability Theory and Related Fields 123, 301--322.
  6. Dedecker, Jérôme; Doukhan, Paul; Lang, Gabriel; León R., José Rafael; Louhichi, Sana; Prieur, Clémentine. Weak dependence: with examples and applications.Lecture Notes in Statistics, 190. Springer, New York, 2007. xiv+318 pp. ISBN: 978-0-387-69951-6 MR2338725 (2009a:62009)
  7. Dedecker, Jérôme; Prieur, Clémentine. New dependence coefficients. Examples and applications to statistics. Probab. Theory Related Fields 132 (2005), no. 2, 203--236. MR2199291 (2007b:62081)
  8. Dedecker, Jérôme; Prieur, Clémentine; Raynaud De Fitte, Paul. Parametrized Kantorovich-Rubinštein theorem and application to the coupling of random variables. Dependence in probability and statistics, 105--121, Lecture Notes in Statist., 187, Springer, New York, 2006. MR2283252 (2008c:60002)
  9. Doukhan, Paul. Mixing.Properties and examples.Lecture Notes in Statistics, 85. Springer-Verlag, New York, 1994. xii+142 pp. ISBN: 0-387-94214-9 MR1312160 (96b:60090)
  10. Doukhan, Paul; Louhichi, Sana. A new weak dependence condition and applications to moment inequalities. Stochastic Process. Appl. 84 (1999), no. 2, 313--342. MR1719345 (2001j:60033)
  11. Doukhan, P., and Neumann, M. A Bernstein type inequality for times series. Stoch. Proc. Appl. 117-7, 878--903.
  12. Doukhan, Paul; Wintenberger, Olivier. Weakly dependent chains with infinite memory. Stochastic Process. Appl. 118 (2008), no. 11, 1997--2013. MR2462284 (2010c:62281)
  13. Ibragimov, I. A. Some limit theorems for stationary processes.(Russian) Teor. Verojatnost. i Primenen. 7 1962 361--392. MR0148125 (26 #5634)
  14. Ibragimov, I. A.; Linnik, Yu. V. Independent and stationary sequences of random variables.With a supplementary chapter by I. A. Ibragimov and V. V. Petrov.Translation from the Russian edited by J. F. C. Kingman.Wolters-Noordhoff Publishing, Groningen, 1971. 443 pp. MR0322926 (48 #1287)
  15. Joulin, A., and Ollivier, Y. Curvature, concentration, and error estimates for Markov chain Monte Carlo. Ann. Probab. 38, 2418--2442.
  16. Lezaud, Pascal. Chernoff-type bound for finite Markov chains. Ann. Appl. Probab. 8 (1998), no. 3, 849--867. MR1627795 (99f:60061)
  17. Massart, Pascal. Concentration inequalities and model selection.Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour, July 6–23, 2003.With a foreword by Jean Picard.Lecture Notes in Mathematics, 1896. Springer, Berlin, 2007. xiv+337 pp. ISBN: 978-3-540-48497-4; 3-540-48497-3 MR2319879 (2010a:62008)
  18. Merlevede, F., Peligrad, M., and Rio, E. Bernstein inequality and moderate deviations under strong mixing conditions. In High Dimensional Probability V: The Luminy Volume (Beachwood, Ohio, USA: IMS, 2009) C. Houdré, V. Koltchinskii, D.M. Mason and M. Peligrad, Eds., 273--292..
  19. Merlevede, F., Peligrad, M., and Rio, E. A Bernstein type inequality and moderate deviations for weakly dependent sequences. Probab. Theory Related Fields DOI: 10.1007/s00440-010-0304-9.
  20. Nummelin, E. A splitting technique for Harris recurrent Markov chains. Z. Wahrsch. Verw. Gebiete 43 (1978), no. 4, 309--318. MR0501353 (58 #18732)
  21. Rio, Emmanuel. Sur le théorème de Berry-Esseen pour les suites faiblement dépendantes.(French) [The Berry-Esseen theorem for weakly dependent sequences] Probab. Theory Related Fields 104 (1996), no. 2, 255--282. MR1373378 (96k:60061)
  22. Rio, Emmanuel. Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes.(French) [Hoeffding inequalities for Lipschitz functions of dependent sequences] C. R. Acad. Sci. Paris Sér. I Math. 330 (2000), no. 10, 905--908. MR1771956 (2001c:60034)
  23. Samson, Paul-Marie. Concentration of measure inequalities for Markov chains and $Phi$-mixing processes. Ann. Probab. 28 (2000), no. 1, 416--461. MR1756011 (2001d:60015)
  24. Viennet, Gabrielle. Inequalities for absolutely regular sequences: application to density estimation. Probab. Theory Related Fields 107 (1997), no. 4, 467--492. MR1440142 (98f:62113)
  25. Walters, Peter. An introduction to ergodic theory.Graduate Texts in Mathematics, 79. Springer-Verlag, New York-Berlin, 1982. ix+250 pp. ISBN: 0-387-90599-5 MR0648108 (84e:28017)













Research
Support Tool
Capture Cite
View Metadata
Printer Friendly
Context
Author Address
Action
Email Author
Email Others


Home | Contents | Submissions, editors, etc. | Login | Search | EJP

Electronic Communications in Probability. ISSN: 1083-589X