A new adaptive rule selects the number k of extreme observations for the Hill estimator with finite-sample guarantees under only regular variation, and near-minimax rates under von Mises conditions.
Uniform concentration bounds for frequencies of rare events
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
New Vapnik and Chervonenkis type concentration inequalities are derived for the empirical distribution of an independent random sample. Focus is on the maximal deviation over classes of Borel sets within a low probability region. The constants are explicit, enabling numerical comparisons.
fields
stat.OT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive tail index estimation: minimal assumptions and non-asymptotic guarantees
A new adaptive rule selects the number k of extreme observations for the Hill estimator with finite-sample guarantees under only regular variation, and near-minimax rates under von Mises conditions.