This work presents empirical likelihood - a nonparametric method for constructing confidence regions and testing hypotheses. The author applies empirical likelihood on problems as simple as setting a confidence region for a univariate mean under IID sampling, to problems of statistics defined through smooth functions of means, regression models, generalized linear models, estimating equations, or kernel smooths, and to sampling with non-identically distributed data. The book includes many exercises, and demonstrates the advantages over the bootstrap in two and higher dimensional models.

This volume represents the refereed proceedings of the Eighth International C- ference on Monte Carlo and Quasi-Monte Carlo Methods in Scienti c Computing, which was held at the University of Montreal, from 6 11 July, 2008. It contains a limited selection of articles based on presentations made at the conference. The program was arranged with the help of an international committee consisting of: Ronald Cools, Katholieke Universiteit Leuven Luc Devroye, McGill University Henri Faure, CNRS Marseille Paul Glasserman, Columbia University Peter W. Glynn, Stanford University Stefan Heinrich,...