On the Sample Mean and Variance of a Long Memory Process.

Abstract

Some properties of the sample mean and sample variance of a long memory process are described. It is shown that for a particular class of long memory process the asymptotic relative efficiency of the k- decimated sample mean x bar sub n (K) (formed by taking the mean of every k -th observation) with respect to the sample mean x bar sub n of all n observations is 1, but that the deficiency (as defined by Hodges and Lehmann) of x bar sub n (K) with respect to x bar sub n is infinite. It is also shown that the sample variance S sub n to the 2nd power of a long memory process can be badly biased toward O: for any integer N and every epsilon > O there exists a long memory process with population variance such that Es sub n to the 2nd power < ep silon population variance for all sample sizes n < or = N. These properties of the sample mean and variance are not shared by ordinary stationary processes such as ARMA processes.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1985
Accession Number
ADA176221

Entities

People

  • Donald B. Percival

Organizations

  • University of Washington

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Covariance
  • Data Science
  • Deficiencies
  • Distribution Functions
  • Efficiency
  • Equations
  • Estimators
  • Fourier Analysis
  • Fourier Series
  • Gaussian Processes
  • Information Science
  • Observation
  • Stationary
  • Stationary Processes
  • Statistical Analysis
  • Statistics
  • White Noise

Fields of Study

  • Mathematics

Readers

  • Statistical inference.
  • Systems Analysis and Design