Permuted derivative and importance-sampling estimators for regenerative simulations

Document Type

Article

Publication Date

7-16-2004

Abstract

In a previous paper we introduced a new variance-reduction technique for regenerative simulations based on permuting regeneration cycles. In this paper we apply this idea to new classes of estimators. In particular, we derive permuted versions of likelihood-ratio derivative estimators for steady-state performance measures, importance-sampling estimators of the mean cumulative reward until hitting a set of states, and Tin estimators for steady-state ratio formulas. Empirical results are presented showing that modest to significant variance reductions can be obtained. © 2003 Elsevier B.V. All rights reserved.

Identifier

1442356721 (Scopus)

Publication Title

European Journal of Operational Research

External Full Text Location

https://doi.org/10.1016/S0377-2217(03)00070-5

ISSN

03772217

First Page

390

Last Page

414

Issue

2

Volume

156

Grant

DMI-9500173

Fund Ref

National Science Foundation

This document is currently not available here.

Share

COinS