Panel unit root tests in the presence of cross-sectional dependence: finite sample performance and an application

S. De Silva, K. Hadri, A.R. Tremayne

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)

Abstract

This paper examines the finite sample properties of three testing regimes for the null hypothesis of a panel unit root against stationary alternatives in the presence of cross-sectional correlation. The regimes of Bai and Ng (2004), Moon and Perron (2004) and Pesaran (2007) are assessed in the presence of multiple factors and also other non-standard situations. The behaviour of some information criteria used to determine the number of factors in a panel is examined and new information criteria with improved properties in small-N panels proposed. An application to the efficient markets hypothesis is also provided. The null hypothesis of a panel random walk is not rejected by any of the tests, supporting the efficient markets hypothesis in the financial services sector of the Australian Stock Exchange.
Original languageEnglish
Pages (from-to)340-366
Number of pages27
JournalEconometrics Journal
Volume12
Issue number2
DOIs
Publication statusPublished - Jul 2009

ASJC Scopus subject areas

  • Economics and Econometrics

Fingerprint

Dive into the research topics of 'Panel unit root tests in the presence of cross-sectional dependence: finite sample performance and an application'. Together they form a unique fingerprint.

Cite this