Recurrence and transience for autoregressive nonlinear time series /

It is a known fact that drift criteria can be used to study autoregressive nonlinear time series. In fact, they have been applied to some special cases and satisfactory results are obtained. We extend the results to general AR(1) nonlinear processes [ ] where [alpha] is a nonlinear locally boun...

Full description

Bibliographic Details
Main Author: Pu, Huay-Min Huoh
Format: Thesis Book
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1995.
Subjects:
Online Access:Link to OAKTrust copy
http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=742536371&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD
Description
Summary:It is a known fact that drift criteria can be used to study autoregressive nonlinear time series. In fact, they have been applied to some special cases and satisfactory results are obtained. We extend the results to general AR(1) nonlinear processes [ ] where [alpha] is a nonlinear locally bounded function from [ ] is a sequence of i.i.d. random variables with density function f positive on [ ] and [ ] if I is a compact interval. [ ] We refine the results for the special case when [ ] is of one sign for large x [ ] We pay special attention to the case [ ] and obtain conditions for erogodicity and null recurrence. We also illustrate our results by examples.
Item Description:Vita.
"Major Subject: Statistics".
Physical Description:vi, 114 leaves ; 28 cm.
Issued also on microfiche from University Microfilms Inc.
Bibliography:Includes bibliographical references.