• Media type: E-Article
  • Title: Gaussian Characterization of Uniform Donsker Classes of Functions
  • Contributor: Gine, Evarist; Zinn, Joel
  • imprint: Institute of Mathematical Statistics, 1991
  • Published in: The Annals of Probability
  • Language: English
  • ISSN: 0091-1798
  • Origination:
  • Footnote:
  • Description: <p>It is proved that, for classes of functions F satisfying some measurability, the empirical processes indexed by F and based on P ∈ P(S) satisfy the central limit theorem uniformly in P ∈ P(S) if and only if the P-Brownian bridges G<sub>p</sub>indexed by F are sample bounded and ρ<sub>p</sub>uniformly continuous uniformly in P ∈ P(S). Uniform exponential bounds for empirical processes indexed by universal bounded Donsker and uniform Donsker classes of functions are also obtained.</p>
  • Access State: Open Access