Advanced

On the Choice of Test for a Unit Root when the Errors are Conditionally Heteroskedastic

Westerlund, Joakim LU (2014) In Computational Statistics & Data Analysis 69(January). p.40-53
Abstract
It is well known that in the context of the classical regression model with heteroskedastic errors, while ordinary least squares (OLS) is not efficient, the weighted least squares (WLS) and quasi-maximum likelihood (QML) estimators that utilize the information contained in the heteroskedasticity are. In the context of unit root testing with conditional heteroskedasticity, while intuition suggests that a similar result should apply, the relative performance of the tests associated with the OLS, WLS and QML estimators is not well understood. In particular, while QML has been shown to be able to generate more powerful tests than OLS, not much is known regarding the relative performance of the WLS-based test. By providing an in-depth... (More)
It is well known that in the context of the classical regression model with heteroskedastic errors, while ordinary least squares (OLS) is not efficient, the weighted least squares (WLS) and quasi-maximum likelihood (QML) estimators that utilize the information contained in the heteroskedasticity are. In the context of unit root testing with conditional heteroskedasticity, while intuition suggests that a similar result should apply, the relative performance of the tests associated with the OLS, WLS and QML estimators is not well understood. In particular, while QML has been shown to be able to generate more powerful tests than OLS, not much is known regarding the relative performance of the WLS-based test. By providing an in-depth comparison of the tests, the current paper fills this gap in the literature. (Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Unit root test, Conditional heteroskedasticity, ARCH
in
Computational Statistics & Data Analysis
volume
69
issue
January
pages
40 - 53
publisher
Elsevier
external identifiers
  • scopus:84881278307
ISSN
0167-9473
DOI
10.1016/j.csda.2013.07.022
language
English
LU publication?
no
id
66fdf7ec-c54e-4f2c-9cc5-452082435a24 (old id 4588889)
date added to LUP
2014-08-19 15:40:38
date last changed
2017-01-01 03:35:52
@article{66fdf7ec-c54e-4f2c-9cc5-452082435a24,
  abstract     = {It is well known that in the context of the classical regression model with heteroskedastic errors, while ordinary least squares (OLS) is not efficient, the weighted least squares (WLS) and quasi-maximum likelihood (QML) estimators that utilize the information contained in the heteroskedasticity are. In the context of unit root testing with conditional heteroskedasticity, while intuition suggests that a similar result should apply, the relative performance of the tests associated with the OLS, WLS and QML estimators is not well understood. In particular, while QML has been shown to be able to generate more powerful tests than OLS, not much is known regarding the relative performance of the WLS-based test. By providing an in-depth comparison of the tests, the current paper fills this gap in the literature.},
  author       = {Westerlund, Joakim},
  issn         = {0167-9473},
  keyword      = {Unit root test,Conditional heteroskedasticity,ARCH},
  language     = {eng},
  number       = {January},
  pages        = {40--53},
  publisher    = {Elsevier},
  series       = {Computational Statistics & Data Analysis},
  title        = {On the Choice of Test for a Unit Root when the Errors are Conditionally Heteroskedastic},
  url          = {http://dx.doi.org/10.1016/j.csda.2013.07.022},
  volume       = {69},
  year         = {2014},
}