Applications to risk theory of a Monte Carlo multiple integration method

Evaluation of multiple integrals is a commonly encountered problem in risk theory, specially in ruin probability. Using Monte Carlo simulation we obtain an unbiased and consistent point estimator, and also confidence intervals as approximations of a special case of multiple integral frequently used in risk theory. The variance reduction achieved compared to straight simulation and some specific properties make this approach interesting when approximating ruin probabilities. (C) 1998 Elsevier Science B.V.