A Berry-Esseen Bound for Nonlinear Statistics with Bounded Differences
Abstract
In this paper, we obtain an explicit Berry-Esseen bound in the central limit theorem for nonlinear statistics with bounded differences. Some examples are provided as well.References
V. Bentkus, F. Gotze, A. Tikhomirov, Berry-Esseen bounds for statistics of weakly dependent samples. Bernoulli 3 (1997), no. 3, 329–349.
I. Berkes, W. Philipp, Approximation theorems for independent and weakly dependent random vectors. Ann. Probab. 7 (1979), no. 1, 29–54.
S. Boucheron, G. Lugosi, P. Massart, Concentration inequalities. A nonasymptotic theory of independence. With a foreword by Michel Ledoux. Oxford University Press, Oxford, 2013.
S. Chatterjee, A new method of normal approximation. Ann. Probab. 36 (2008), no. 4, 1584–1610.
S. Chatterjee, P. Diaconis, A central limit theorem for a new statistic on permutations. Indian J. Pure Appl. Math. 48 (2017), no. 4, 561–573.
L. H. Y. Chen, Q.-M. Shao, Normal approximation for nonlinear statistics using a concentration inequality approach. Bernoulli 13 (2007), no. 2, 581–599.
L. H. Y. Chen, L. Goldstein, Q.-M. Shao, Normal approximation by Stein’s method. Probability and its Applications (New York). Springer, Heidelberg, 2011.
N. T. Dung, Explicit rates of convergence in the multivariate CLT for nonlinear statistics. Acta Math. Hungar. 158 (2019), no. 1, 173–201.
K. O. Friedrich, A Berry-Esseen bound for functions of independent random variables. Ann. Statist. 17 (1989), no. 1, 170–183.
F. Gotze, On the rate of convergence in the multivariate CLT. Ann. Probab. 19 (1991), no. 2, 724–739.
C. Houdre, U. Is¸lak, A Central limit theorem for the length of the longest common subsequences in random words. arXiv:1408.1559v4, 2017.
A. Maurer, M. Pontil, Empirical bounds for functions with weak interactions. Proceedings of Machine Learning Research vol 75:1–24, 2018
R. L-Rey, G. Peccati, New Berry-Esseen bounds for functionals of binomial point processes. Ann. Appl. Probab. 27 (2017), no. 4, 1992–2031.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
