Weak Convergence of the Hill Estimator Process

Let X 1 X 2,…, be a sequence of nonnegative i. i. d. random variables and for each n ≥ 1 let X 1, n ≤… ≤ Xn, n denote the order statistics based on the first n of these X’s. The Hill estimator is the sum of extreme values Σi≤kn )/k n , where k n → ∞ and k/ n →0, as n→ ∞. A weak convergence result is established for a process motivated by the Hill estimator, which we call the Hill estimator process.