Abstract
This paper extends the cross-sectionally augmented panel unit root test (CIPSCIPS) proposed by Pesaran (2007) to the case of a multifactor error structure, and proposes a new panel unit root test based on a simple average of cross-sectionally augmented Sargan–Bhargava statistics (CSBCSB). The basic idea is to exploit information regarding the mm unobserved factors that are shared by kk observed time series in addition to the series under consideration. Initially, we develop the tests assuming that m0m0, the true number of factors, is known and show that the limit distribution of the tests does not depend on any nuisance parameters, so long as k≥m0−1k≥m0−1. Small sample properties of the tests are investigated by Monte Carlo experiments and are shown to be satisfactory. Particularly, the proposed CIPSCIPS and CSBCSB tests have the correct size for all combinations of the cross section (NN) and time series (TT) dimensions considered. The power of both tests rises with NN and TT, although the CSBCSB test performs better than the CIPSCIPS test for smaller sample sizes. The various testing procedures are illustrated with empirical applications to real interest rates and real equity prices across countries.
| Original language | English |
|---|---|
| Pages (from-to) | 94–115 |
| Number of pages | 22 |
| Journal | Journal of Econometrics |
| Volume | 175 |
| Issue number | 2 |
| Early online date | 18 Feb 2013 |
| DOIs | |
| Publication status | Published - Aug 2013 |
Keywords
- Panel unit root tests
- Cross section dependence
- Multifactor error structure
- Fisher inflation parity
- Real equity prices