Limit theorems for empirical processes
- 1 January 1981
- journal article
- Published by Springer Science and Business Media LLC in Probability Theory and Related Fields
- Vol. 57 (2), 181-195
- https://doi.org/10.1007/bf00535488
Abstract
The empirical measure P n for iid sampling on a distribution P is formed by placing mass n −1 at each of the first n observations. Generalizations of the classical Glivenko-Cantelli theorem for empirical measures have been proved by Vapnik and červonenkis using combinatorial methods. They found simple conditions on a class C to ensure that sup {|P n (C) − P(C)|: C ∈ C} converges in probability to zero. They used a randomization device that reduced the problem to finding exponential bounds on the tails of a hypergeometric distribution. In this paper an alternative randomization is proposed. The role of the hypergeometric distribution is thereby taken over by the binomial distribution, for which the elementary Bernstein inequalities provide exponential boundson the tails. This leads to easier proofs of both the basic results of Vapnik-červonenkis and the extensions due to Steele. A similar simplification is made in the proof of Dudley's central limit theorem forn 1/2(P P n −P)— a result that generalizes Donsker's functional central limit theorem for empirical distribution functions.Keywords
This publication has 6 references indexed in Scilit:
- Beyond the heuristic approach to Kolmogorov-Smirnov theoremsJournal of Applied Probability, 1982
- Central Limit Theorems for Empirical MeasuresThe Annals of Probability, 1978
- Empirical Discrepancies and Subadditive ProcessesThe Annals of Probability, 1978
- On the Uniform Convergence of Relative Frequencies of Events to Their ProbabilitiesTheory of Probability and Its Applications, 1971
- measures on non-separable metric spacesIllinois Journal of Mathematics, 1967
- Weak convergence of probabilities on nonseparable metric spaces and empirical measures on Euclidean spacesIllinois Journal of Mathematics, 1966