Estimating the Asymptotic Variance with Batch Means

Abstract

In this paper it is shown that there does not exist a procedure to consistently estimate the asymptotic variance constant in a stochastic simulation using batch means when the number of batches is held fixed as the run length increases. Thus, if consistency is desired, then the number of batches must increase as the run length increases. To be precise, we must first specify what we mean by an estimation procedure. To be interesting, an estimation procedure should apply to a large family of stochastic processes.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1990
Accession Number
ADA228293

Entities

People

  • Peter W. Glynn
  • Ward Whitt

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Brownian Motion
  • Consistency
  • Convergence
  • Diffusion Coefficient
  • Estimators
  • Intervals
  • Military Research
  • Normal Distribution
  • Operations Research
  • Probability
  • Random Variables
  • Standards
  • Statistical Tests
  • Stochastic Processes
  • Weak Convergence

Fields of Study

  • Mathematics

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Systems Analysis and Design