WIAS Preprint No. 436, (1998)

Importance sampling for large and moderate large deviation simulation of tests and estimators



Authors

  • Ermakov, Michael

2010 Mathematics Subject Classification

  • 62E25 60F10 65C05

Keywords

  • Importance sampling, Large deviations, Empirical measure, Hadamard-type derivative, Statistical simulation

Abstract

We find the effective importance sampling procedures for the simulation of large and moderate large deviations of tests and estimators. The computational burden of these effective procedures has no exponential rate as in the direct simulation. The results are applied to the simulation of large and moderate large deviations of L,M,R-statistics and omega-square tests.

Download Documents