A generalized nonlinear IV unit root test for panel data with cross-sectional dependence

2010 ◽  
Vol 157 (1) ◽  
pp. 101-109 ◽  
Author(s):  
Shaoping Wang ◽  
Peng Wang ◽  
Jisheng Yang ◽  
Zinai Li
2021 ◽  
pp. 1-35
Author(s):  
SAKIRU ADEBOLA SOLARIN ◽  
CHRIS STEWART

To avoid spurious inferences, researchers analyzing the dimensions of uncertainty need to determine whether it is nonstationary. The degree of persistence of uncertainty also indicates the duration of the negative impact of an uncertainty shock on the economy. We use a new panel residual augmented least squares unit root test that allows for heterogeneous structural breaks in both intercepts and slopes of a series to determine the degree of persistence of the reports-based measure of uncertainty and whether it is nonstationary for 143 countries. This group of countries accounts for 99% of the world’s gross domestic product (GDP). To assess the robustness of our results, we also use recently developed univariate time-series unit root tests that allow for structural breaks and panel unit root tests that accommodate cross-sectional dependence and nonlinearity. Furthermore, an autoregressive wild bootstrap approach is utilized to examine the stationarity of the series. The results are virtually unambiguous in indicating that the reports-based measure of uncertainty is stationary in all countries considered. The results also suggest that uncertainty has a negative impact on the growth rate of GDP. The policy implications of the results are also discussed.


Sign in / Sign up

Export Citation Format

Share Document