Finitesample distribution of a recursively meanadjusted panel data unit root test
(2007) In Journal of Statistical Computation and Simulation 77(4). p.293303 Abstract
 In this paper, we investigate the finitesample distribution of the recursively meanadjusted panel data unit root test of Shin et al. [Shin, D. W., Kang, S. and Oh, M.S., 2004, Recursive mean adjustment for panel unit root tests. Economics Letters, 84, 433439.]. More precisely, we provide response surface parameters that can be used to calculate smallsample critical values for the test. Furthermore, we supply standardizing moments that can be used to calculate a test statistic that has an asymptotic standard normal distribution. The asymptotic standard normal distribution, which follows when the crosssectional dimension increases, enables easy calculation of critical values and pvalues. Hence, it is of interest to study how large the... (More)
 In this paper, we investigate the finitesample distribution of the recursively meanadjusted panel data unit root test of Shin et al. [Shin, D. W., Kang, S. and Oh, M.S., 2004, Recursive mean adjustment for panel unit root tests. Economics Letters, 84, 433439.]. More precisely, we provide response surface parameters that can be used to calculate smallsample critical values for the test. Furthermore, we supply standardizing moments that can be used to calculate a test statistic that has an asymptotic standard normal distribution. The asymptotic standard normal distribution, which follows when the crosssectional dimension increases, enables easy calculation of critical values and pvalues. Hence, it is of interest to study how large the crosssectional dimension has to be in order for the normal approximation to be valid for inference. By performing a Monte Carlo simulation, we find that the normal approximation works well, at conventional significance levels, even when the crosssectional dimension is as small as 2. We also supply critical values and moments for the panel unit root test that can be used when the baseline model is augmented to account for serially correlated disturbances. Finally, we investigate the finitesample size and power properties of the test and find that the test performs well even when disturbances display serial correlation. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/record/671618
 author
 Jönsson, Kristian ^{LU}
 organization
 publishing date
 2007
 type
 Contribution to journal
 publication status
 published
 subject
 keywords
 recursive mean adjustment, serial, Monte Carlo simulation, correlation, panel data, unit root test
 in
 Journal of Statistical Computation and Simulation
 volume
 77
 issue
 4
 pages
 293  303
 publisher
 Taylor & Francis
 external identifiers

 wos:000245077400002
 scopus:33947432343
 ISSN
 15635163
 DOI
 10.1080/10629360600570988
 language
 English
 LU publication?
 yes
 id
 8fe2621272c849f496758de22df7def0 (old id 671618)
 date added to LUP
 20071212 16:27:16
 date last changed
 20180529 09:32:58
@article{8fe2621272c849f496758de22df7def0, abstract = {In this paper, we investigate the finitesample distribution of the recursively meanadjusted panel data unit root test of Shin et al. [Shin, D. W., Kang, S. and Oh, M.S., 2004, Recursive mean adjustment for panel unit root tests. Economics Letters, 84, 433439.]. More precisely, we provide response surface parameters that can be used to calculate smallsample critical values for the test. Furthermore, we supply standardizing moments that can be used to calculate a test statistic that has an asymptotic standard normal distribution. The asymptotic standard normal distribution, which follows when the crosssectional dimension increases, enables easy calculation of critical values and pvalues. Hence, it is of interest to study how large the crosssectional dimension has to be in order for the normal approximation to be valid for inference. By performing a Monte Carlo simulation, we find that the normal approximation works well, at conventional significance levels, even when the crosssectional dimension is as small as 2. We also supply critical values and moments for the panel unit root test that can be used when the baseline model is augmented to account for serially correlated disturbances. Finally, we investigate the finitesample size and power properties of the test and find that the test performs well even when disturbances display serial correlation.}, author = {Jönsson, Kristian}, issn = {15635163}, keyword = {recursive mean adjustment,serial,Monte Carlo simulation,correlation,panel data,unit root test}, language = {eng}, number = {4}, pages = {293303}, publisher = {Taylor & Francis}, series = {Journal of Statistical Computation and Simulation}, title = {Finitesample distribution of a recursively meanadjusted panel data unit root test}, url = {http://dx.doi.org/10.1080/10629360600570988}, volume = {77}, year = {2007}, }