Synthesis of Multichannel Autoregressive Random Processes and Ergodicity Considerations

Abstract

In this paper, a method is presented for synthesizing multichannel autogressive random processes. The procedure allows for variable temporal and cross-correlation properties subject to specific constraint conditions for correlation functions. Expressions for the ergodic series are also developed providing a performance measure to specify the sample integration sizes required to achieve a specific variance of the time-averaged correlation function estimates. A unique aspect of this development is the determination of the functional dependence of the ergodic series in terms of the temporal correlation and variances of the processes. As a result, this analysis provides an analytic description which quantitatively assesses the ergodicity of the auto- and cross- correlation functions in terms of these fundamental process parameters. Thus, the variation of the process statistics based on time averages from those based on ensemble averages is given a more quantitative description than previously noted.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1990
Accession Number
ADA226493

Entities

People

  • James H. Michels

Organizations

  • Rome Laboratory

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Command And Control
  • Cross Correlation
  • Data Science
  • Delta Functions
  • Estimators
  • Frequency
  • Gaussian Quadrature
  • Information Processing
  • Information Science
  • Peak Values
  • Radar
  • Random Variables
  • Spectra
  • Stationary Processes
  • Statistical Algorithms
  • Stochastic Processes
  • Two Dimensional

Readers

  • Approximation Theory.
  • Statistical inference.
  • Systems Analysis and Design