Large deviations of the empirical characteristic function

From MaRDI portal





Let \(X_ 1,X_ 2,..\). be a sequence of independent and identically distributed random variables with common characteristic function c(t), \(t\in {\mathbb{R}}\). Let \(c_ n(t)=n^{-1}\sum^{n}_{j=1}e^{itX_ j}\) be the n-th empirical characteristic function and for \(S\subset {\mathbb{R}}\) set \[ T_ n=\sup \{| c_ n(t)-c(t)|:t\in S\}. \] Theorems on probabilities of large deviations are derived for the sequence of statistics \(T_ 1,T_ 2,..\).. Asymptotic expansions of these probabilities are presented, which can be used for the computation of the relative asymptotic Bahadur efficiency.











This page was built for publication: Large deviations of the empirical characteristic function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3797957)