Nearest neighbor regression estimation for null-recurrent Markov time series

Sid Yakowitz

Stochastic Processes and their Applications, 1993, vol. 48, issue 2, 311-318

Abstract: The past few years have witnessed the emergence of a vigorous literature seeking to exploit nonparametric estimation ideas in time-series contexts. As documented herein, in recent times, various mixing conditions postulated in the seminal investigations by Rosenblatt (1970) and Roussas (1969) have been relaxed. The present study assumes that the observed series is Markov with a time-invariant transition function, but does not postulate mixing conditions or that the coordinate process have a proper probability distribution. Thereby, our methodology encompasses random walks, for example. Nevertheless, a variation of the traditional nearest neighbor regression estimate is found to be pointwise consistent under useful conditional moment assumptions.

Keywords: time; series; nonparametric; estimation; Markov; sequence (search for similar items in EconPapers)
Date: 1993
References: Add references at CitEc
Citations: View citations in EconPapers (13)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/0304-4149(93)90050-E
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:spapps:v:48:y:1993:i:2:p:311-318

Ordering information: This journal article can be ordered from
http://http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Stochastic Processes and their Applications is currently edited by T. Mikosch

More articles in Stochastic Processes and their Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().