Abstract
The stationarity of inflation has many important economic implications. Most panel-based empirical studies do not handle cross-sectional dependence, which will result in power distortion. This paper applies a nonlinear IV estimator to calculate the test statistic of panel unit root (Chang in J Econom 110:261-292, 2002), which accounts for general cross-sectional correlation. Using monthly inflation rates, two statistics proposed by Im et al. (J Econom 115:53-74, 2003) reject the unit root; however, the nonlinear IV statistic accepts the unit root. That is, the ignored cross-sectional correlation may lead to over-rejection of the unit root null. In a nutshell, unlike current literature, the inflation rates may accelerate after all.
Original language | English |
---|---|
Pages (from-to) | 55-64 |
Number of pages | 10 |
Journal | Empirical Economics |
Volume | 36 |
Issue number | 1 |
DOIs | |
Publication status | Published - 2009 |
Externally published | Yes |
Keywords
- Cross-sectional dependencies
- Nonlinear IV
- Panel unit root
ASJC Scopus subject areas
- Statistics and Probability
- Mathematics (miscellaneous)
- Social Sciences (miscellaneous)
- Economics and Econometrics