Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Likelihood Ratio Tests for a Unit Root in Panels with Random Effects

Larsson, Rolf ; Lyhagen, Johan and Westerlund, Joakim LU (2017) In Statistics 51(3). p.627-654
Abstract
Because of the fixed heterogeneity of their models, most panel unit root tests impose restrictions on the rate at which the number of time periods, T, and the number of cross-section units, N, go to infinity. A common example of such a restriction is
N/T→0
, which in practice means that T≫N
, a condition that is not always met. In the current paper the heterogeneity is given a parsimonious random effects specification, which is used as a basis for developing a new likelihood ratio test for a unit root. The asymptotic analysis shows that the new test is valid for all (N,T)
expansion paths satisfying N/T5→0
, which represents a substantial improvement when compared to the existing fixed effects literature.
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Statistics
volume
51
issue
3
pages
627 - 654
publisher
Taylor & Francis
external identifiers
  • scopus:85006127548
  • wos:000399481400009
ISSN
0233-1888
DOI
10.1080/02331888.2016.1266630
language
English
LU publication?
yes
id
6a66decd-4c85-4f0e-b029-36bb924f6a80
date added to LUP
2016-10-28 11:52:41
date last changed
2022-03-08 21:49:11
@article{6a66decd-4c85-4f0e-b029-36bb924f6a80,
  abstract     = {{Because of the fixed heterogeneity of their models, most panel unit root tests impose restrictions on the rate at which the number of time periods, T, and the number of cross-section units, N, go to infinity. A common example of such a restriction is<br/>N/T→0<br/>, which in practice means that T≫N<br/>, a condition that is not always met. In the current paper the heterogeneity is given a parsimonious random effects specification, which is used as a basis for developing a new likelihood ratio test for a unit root. The asymptotic analysis shows that the new test is valid for all (N,T)<br/>expansion paths satisfying N/T5→0<br/>, which represents a substantial improvement when compared to the existing fixed effects literature.}},
  author       = {{Larsson, Rolf and Lyhagen, Johan and Westerlund, Joakim}},
  issn         = {{0233-1888}},
  language     = {{eng}},
  month        = {{05}},
  number       = {{3}},
  pages        = {{627--654}},
  publisher    = {{Taylor & Francis}},
  series       = {{Statistics}},
  title        = {{Likelihood Ratio Tests for a Unit Root in Panels with Random Effects}},
  url          = {{http://dx.doi.org/10.1080/02331888.2016.1266630}},
  doi          = {{10.1080/02331888.2016.1266630}},
  volume       = {{51}},
  year         = {{2017}},
}