A unit root test based on the modified least squares estimator

A unit root test based on the modified least squares (MLS) estimator for first-order autoregressive process is proposed and compared with unit root tests based on the ordinary least squares (OLS), the weighted symmetric (WS) and the modified weighted symmetric (MWS) estimators. The percentiles of th...

Full description

Saved in:
Bibliographic Details
Main Author: Wararit Panichkitkosolkul
Format: Article
Language:English
Published: Universiti Kebangsaan Malaysia 2014
Online Access:http://journalarticle.ukm.my/7826/1/20_Wararit.pdf
http://journalarticle.ukm.my/7826/
http://www.ukm.my/jsm/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Kebangsaan Malaysia
Language: English
id my-ukm.journal.7826
record_format eprints
spelling my-ukm.journal.78262016-12-14T06:45:19Z http://journalarticle.ukm.my/7826/ A unit root test based on the modified least squares estimator Wararit Panichkitkosolkul, A unit root test based on the modified least squares (MLS) estimator for first-order autoregressive process is proposed and compared with unit root tests based on the ordinary least squares (OLS), the weighted symmetric (WS) and the modified weighted symmetric (MWS) estimators. The percentiles of the null distributions of the unit root test are also reported. The empirical probabilities of type I error and powers of the unit root tests were estimated via Monte Carlo simulation. The simulation results showed that all unit root tests can control the probability of type I error for all situations. The empirical power of the test is higher than the other unit root tests, and Apart from that, the and tests also provide the highest empirical power. As an illustration, the monthly series of U.S. nominal interest rates on three-month treasury bills is analyzed. Universiti Kebangsaan Malaysia 2014-10 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/7826/1/20_Wararit.pdf Wararit Panichkitkosolkul, (2014) A unit root test based on the modified least squares estimator. Sains Malaysiana, 43 (10). pp. 1623-1633. ISSN 0126-6039 http://www.ukm.my/jsm/
institution Universiti Kebangsaan Malaysia
building Perpustakaan Tun Sri Lanang Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Kebangsaan Malaysia
content_source UKM Journal Article Repository
url_provider http://journalarticle.ukm.my/
language English
description A unit root test based on the modified least squares (MLS) estimator for first-order autoregressive process is proposed and compared with unit root tests based on the ordinary least squares (OLS), the weighted symmetric (WS) and the modified weighted symmetric (MWS) estimators. The percentiles of the null distributions of the unit root test are also reported. The empirical probabilities of type I error and powers of the unit root tests were estimated via Monte Carlo simulation. The simulation results showed that all unit root tests can control the probability of type I error for all situations. The empirical power of the test is higher than the other unit root tests, and Apart from that, the and tests also provide the highest empirical power. As an illustration, the monthly series of U.S. nominal interest rates on three-month treasury bills is analyzed.
format Article
author Wararit Panichkitkosolkul,
spellingShingle Wararit Panichkitkosolkul,
A unit root test based on the modified least squares estimator
author_facet Wararit Panichkitkosolkul,
author_sort Wararit Panichkitkosolkul,
title A unit root test based on the modified least squares estimator
title_short A unit root test based on the modified least squares estimator
title_full A unit root test based on the modified least squares estimator
title_fullStr A unit root test based on the modified least squares estimator
title_full_unstemmed A unit root test based on the modified least squares estimator
title_sort unit root test based on the modified least squares estimator
publisher Universiti Kebangsaan Malaysia
publishDate 2014
url http://journalarticle.ukm.my/7826/1/20_Wararit.pdf
http://journalarticle.ukm.my/7826/
http://www.ukm.my/jsm/
_version_ 1643737258828759040