On the Value of Function Evaluation Location Information in Monte Carlo Simulation

Abstract

The point estimator used in naive Monte Carlo sampling weights all the computed function evaluations equally, and it does not take into account the precise locations at which the function evaluations are made. In this note, we show for one-dimensional integration problems that if the weights are suitably modified to reflect the location information present in the sample, then the convergence rate of the Monte Carlo estimator can be dramatically improved from order n(-1/2) to order n(-2), where is the number of function evaluations computed....Simulation, Monte Carlo methods, Numerical integration.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1992
Accession Number
ADA263662

Entities

People

  • Peter W. Glynn
  • Thomas J. Diciccio

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Convergence
  • Data Science
  • Estimators
  • Information Science
  • Measurement Transportation Algorithms
  • Military Research
  • Monte Carlo Method
  • Numerical Integration
  • Operations Research
  • Random Variables
  • Sampling
  • Simulations
  • Statistical Algorithms
  • Statistical Sampling
  • Statistics
  • Test And Evaluation

Readers

  • Computational Modeling and Simulation
  • Statistical inference.