Abstract #300731

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2002 Program page
JSM 2002 Abstract #300731
Activity Number: 65
Type: Topic Contributed
Date/Time: Monday, August 12, 2002 : 8:30 AM to 10:20 AM
Sponsor: Business & Economics Statistics Section*
Abstract - #300731
Title: An Autoregressive Order 1 Process with Time Varying Coefficient
Author(s): David Dickey*+
Affiliation(s): North Carolina State University
Address: Box 8203, NCSU, Raleigh, North Carolina, 27695, USA
Keywords: Autoregressive ; Nonlinear
Abstract:

The traditional autoregressive order 1 process expresses an observation at time t as a constant multiple, r, of the previous observation plus an innovation with mean 0 and constant variance. The constant r is often assumed to have magnitude less than 1, so the series is stationary. If r is replaced by an inverse logistic transformation of some polynomial in the previous observation(s), then r will be held between 0 and 1 and 2r-1 between -1 and 1. This paper investigates the behavior of series in which r is replaced by such a function. Such processes can exhibit ARCH-like behavior and unit root-like behavior depending on the choice of polynomial parameters.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2002 program

JSM 2002

For information, contact meetings@amstat.org or phone (703) 684-1221.

If you have questions about the Continuing Education program, please contact the Education Department.

Revised March 2002