Asymptotically Optimal Weighted Numerical Integration

We study numerical integration of H older{type functions with respect to weights on the real line. Our study extends previous work by F. Curbera, [2] and relies on a connection between this problem and the approximation of distribution functions by empirical ones. The analysis is based on a lemma which is important within the theory of optimal designs for approximating stochastic processes. As an application we reproduce a variant of the well known result for weighted integration of Brownian paths, see e.g., [8].