最新单位根检验命令
陈强老师书上说,传统的面板单位根检验并不能很好的处理不同个体扰动项相关问题。借这个问题去搜索,在stata官网上搜到这篇帖子,介绍了一些较新的面板单位根检验命令,仅列出来做个备份,供大家参考。也希望大家抛砖引玉,多介绍几个二代面板单位根检验命令。
原帖地址:https://www.stata.com/statalist/archive/2011-02/msg00671.html
[size=+1]A number of panel time series methods are now available from SSC(thanks to Kit Baum for his generous help):XTMG - Estimating panel time series models with heterogeneous slopesVersion: 1.0.1 - 8th February 2011 - in Stata: ssc install xtmgThis command implements the Pesaran and Smith (1995) Mean Group (MG)estimator, the Pesaran (2006) Common Correlated Effects Mean Group(CCEMG) estimator and the Augmented Mean Group (AMG) estimatorintroduced in Eberhardt and Teal (2010) and discussed and tested inBond and Eberhardt (2010). For these macro panel estimators thecross-panel average estimates can be reported as unweighted oroutlier-robust means, where the latter is implemented via the rregcommand. Optionally the routine reports the group-specific regressionresults and produces residuals based on these. The example in thehelpfile links to a dataset (+ related working paper) and goes throughall the options of the command.MULTIPURT - Investigating variable nonstationarity in macro panelsVersion: 1.0.1 - 8th February 2011 - in Stata: ssc install multipurtThis command runs the Maddala and Wu (1999) as well as the Pesaran(2007) panel unit root tests for multiple variables and lags. This is*not* a new command for these panel unit root tests but a convenienttool using the existing xtfisher and pescadf commands written by ScottMerryman and Piotr Lewandowski respectively (both commands need to beinstalled for multipurt to work). The example in the helpfile links toa dataset (+ related working paper) and goes through all the optionsof the command.Further routines to be posted/updated soon:XTCD - Investigating variable and residual cross-section dependence inmacro panelsVersion: 1.0.0 - 6th February 2011 - in Stata: ssc install xtcdThis command implements the Pesaran (2004) CD test for cross-sectiondependence in panel time-series data. The routine builds on the xtcsdcommand by De Hoyos and Sarafidis (2006) but is not a post-estimationcommand: xtcd can be applied to variables as well as to residuals,provided the latter have been previously computed as a separatevariable series (using for instance the xtmg command). Furthermore, inthe multipurt spirit up to 9 variable or residuals series can betested together. The example in the helpfile links to a dataset (+related working paper) and goes through all the options of thecommand. NOTE: The Mata version of this command (under construction)will reduce the matsize requirements and also correct a couple of bugsrelated to average T and panel balancedness.XTECTEST - Investigating heterogeneous panel cointegration with anerror correction testThis command implements the error correction based cointegration testby Gengenbach, Urbain and Westerlund (2009), which builds on earlierwork by Westerlund (2007). The test investigates error correction atthe group-level (e.g. country) and can account for cross-sectiondependence.Markus EberhardtESRC Post-doctoral Research Fellow, Centre for the Study of AfricanEconomies, Department of Economics, University of OxfordStipendiary Lecturer, St Catherine's College, Oxfordweb: http://sites.google.com/site/medevecon/homeemail: markus.eberhardt@economics.ox.ac.uktwitter: http://twitter.com/sjoh2052mail: Centre for the Study of African Economies, Department ofEconomics, Manor Rd, Oxford OX1 3UQ, England