Testing for unit roots in panel data using a GMM approach |
| |
Authors: | Jörg Breitung |
| |
Institution: | 1. Institut für Statistik und ?konometrie, Humboldt Universit?t zu Berlin, Spandauer Stra?e 1, D-10178, Berlin, FRG
|
| |
Abstract: | For aggregated time series unit root tests are routinely applied to choose among trend and difference stationary models. Recent
work demonstrates that such test can also be applied for testing panel data. However, it is well known that disaggregated
data often exhibit a considerable amount of heterogeneity so that standard tests may perform poorly. To account for the heterogeneity
in the data we allow for individual specific deterministics, that is, we let the time trends vary across the cross section
units. It is shown that standard GMM estimators suggested for the dynamic panel data model may fail to give a valid test procedure.
To overcome this difficulty, a modified GMM estimator is suggested. In a Monte Carlo study the finite sample properties of
the alternative tests are compared. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|