Premium
Are Real GDP Levels Trend, Difference, or Regime‐Wise Trend Stationary? Evidence from Panel Data Tests Incorporating Structural Change
Author(s) -
Hegwood Natalie,
Papell David H.
Publication year - 2007
Publication title -
southern economic journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.762
H-Index - 58
eISSN - 2325-8012
pISSN - 0038-4038
DOI - 10.1002/j.2325-8012.2007.tb00829.x
Subject(s) - unit root , econometrics , panel data , economics , structural break , unit root test , null hypothesis , per capita , structural change , real gross domestic product , horizon , mathematics , statistics , cointegration , macroeconomics , demography , population , geometry , sociology
The unit root hypothesis for international real GDP and real GDP per capita has been the subject of extensive investigation. Using panel methods that incorporate structural change, we reject the unit root null in favor of the alternative of trend stationarity, with one or two changes in the slope for two panels with postwar data and one or two changes in both the slope and the intercept for a panel with long‐horizon data. We conclude that real GDP levels are better characterized as regime‐wise trend stationary than as either trend stationary without structural change or difference stationary with unit roots.