Minimum Variance Importance Sampling via Population Monte Carlo

Preprint

1 January 2005

preprint

Published in RePEc

Abstract

Variance reduction has always been a central issue in Monte Carlo experiments.Population Monte Carlo can be used to this effect, in that a mixture of importancefunctions, called a D-kernel, can be iteratively optimised to achieve the minimumasymptotic variance for a function of interest among all possible mixtures. Theimplementation of this iterative scheme is illustrated for the computation of theprice of a European option in the Cox-Ingersoll-Ross model,

Keywords

VARIANCE IMPORTANCE
IMPORTANCE SAMPLING
VARIANCE REDUCTION
POPULATION MONTE
MINIMUM VARIANCE
CARLO VARIANCE
MONTE CARLO
ITERATIVE
COX

All Related Versions

Version 1, 2005-01-01, RePEc

This publication has 0 references indexed in Scilit: