Conditionally Heteroscedastic Autoregressions.

Abstract

Two conditionally heteroscedastic autoregressions are considered. It is shown that under suitable conditions, the processes are stationary and ergodic, and that the stationary initial distribution can be represented by a nonlinear function of independent, identically distributed standard Normal random variables. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1984
Accession Number
ADA147168

Entities

People

  • A. F. L. Nemec

Organizations

  • University of Washington

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Data Science
  • Equations
  • Ergodic Processes
  • Information Science
  • Integral Equations
  • Markov Processes
  • Nonlinear Dynamics
  • Numbers
  • Polynomials
  • Power Series
  • Random Variables
  • Standards
  • Stationary
  • Stations
  • Statistics
  • Stochastic Processes

Fields of Study

  • Mathematics

Readers

  • Logistics and Supply Chain Management.
  • Mathematical Modeling and Probability Theory.