publication . Preprint . Article . 2016

On the rate of convergence in de Finetti’s representation theorem

Mijoule, Guillaume; Peccati, Giovanni; Swan, Yvik;
Open Access French
  • Published: 25 Jan 2016
A consequence of de Finetti's representation theorem is that for every infinite sequence of exchangeable 0-1 random variables $(X_k)_{k\geq1}$, there exists a probability measure $\mu$ on the Borel sets of $[0,1]$ such that $\bar X_n = n^{-1} \sum_{i=1}^n X_i$ converges weakly to $\mu$. For a wide class of probability measures $\mu$ having smooth density on $(0,1)$, we give bounds of order $1/n$ with explicit constants for the Wasserstein distance between the law of $\bar X_n$ and $\mu$. This extends a recent result {by} Goldstein and Reinert \cite{goldstein2013stein} regarding the distance between the scaled number of white balls drawn in a P\'olya-Eggenberger ...
free text keywords: Probabilités, Mathematics - Probability, Statistique mathématique
21 references, page 1 of 2

[1] David J Aldous. Exchangeability and related topics. Springer, 1985.

[2] Tim Austin. On exchangeable random variables and the statistics of large graphs and hypergraphs. Probability Surveys, 5:80{145, 2008. [OpenAIRE]

[3] Louis HY Chen, Larry Goldstein, and Qi-Man Shao. Normal approximation by Stein's method. Springer Science & Business Media, 2010.

[4] Bruno De Finetti. Foresight: Its logical laws, its subjective sources (1937). Studies in subjective probability, 55{118, 1980.

[5] Persi Diaconis and David Freedman. Finite exchangeable sequences. The Annals of Probability, 745{764, 1980. [OpenAIRE]

[6] Christian Dobler. Stein's method of exchangeable pairs for the Beta distribution and generalizations. Electron. J. Probab., 20:no. 109, 1{34, 2015.

[7] Omar El-Dakkak and Giovanni Peccati. Hoe ding decompositions and urn sequences. Ann. Probab., 36(6):2280{2310, 2008.

[8] Omar El-Dakkak, Giovanni Peccati, and Igor Prunster. Exchangeable Hoe ding-decomposition over nite sets: a characterization and counterexamples. Journal of Multivariate Analysis, 131:51{64, 2014.

[9] Alison L. Gibbs and Francis Edward Su. On choosing and bounding probability metrics. International statistical review, 70(3):419{435, 2002.

[10] Larry Goldstein and Gesine Reinert. Stein's method for the Beta distribution and the PolyaEggenberger urn. Journal of Applied Probability, 50(4):1187{1205, 2013.

[11] David L. Hanson and Lambert H. Koopmans. Convergence rates for the law of large numbers for linear combinations of exchangeable and -mixing stochastic processes. Ann. Math. Statist., 36:1840{1852, 1965.

[12] Maxime Hauray and Stephane Mischler. On Kac's chaos and related problems. Journal of Functional Analysis, 266(10):6055{6157, 2014.

[13] Edwin Hewitt and Leonard J Savage. Symmetric measures on Cartesian products. Transactions of the American Mathematical Society, 470{501, 1955.

[14] Bruce M. Hill, David Lane, and William Sudderth. Exchangeable urn processes. Ann. Probab., 15(4):1586{1592, 1987.

[15] Hiroshi Inoue and Robert Lee Taylor. Laws of large numbers for exchangeable random sets in Kuratowski-Mosco sense. Stoch. Anal. Appl., 24(2):263{275, 2006.

21 references, page 1 of 2
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue
publication . Preprint . Article . 2016

On the rate of convergence in de Finetti’s representation theorem

Mijoule, Guillaume; Peccati, Giovanni; Swan, Yvik;