Testing for a unit root in time series with trend breaks
Article Abstract:
An analysis of the possibility of multiple trend breaks and their impact on inferences of the unit-root behavior of some post-World War II macroeconomic time series shows that eight out of the 17 series considered were found to have a breaking trend. Conditional on a one-time trend break, the no-break unit-root null for five series is rejeted in the augmented Dickey-Fuller test. Moreover, allowing an additional break does not provide additional evidence against the unit-root null hypothesis in any of the four series. Recursive tests offer stronger evidence against the null than sequential tests, while providing weaker evidence on Phillips-Peron statistics instead of augmented Dickey-Fuller data.
Publication Name: Journal of Macroeconomics
Subject: Economics
ISSN: 0164-0704
Year: 1996
User Contributions:
Comment about this article or add new information about this topic:
Near observational equivalence and fractionally integrated processes
Article Abstract:
Unit root literature has long established that near observational equivalence causes very significant size distortions in the customary unit root and cointegration tests. A study demonstrates how these identification problems can also influence the class of fractionally integrated processes, both at a theoretical level and through Monte Carlo simulations. It shows the considerable importance of carefully considering the specific nature of the short-run components of the processes of interest.
Publication Name: Oxford Bulletin of Economics & Statistics
Subject: Economics
ISSN: 0305-9049
Year: 1999
User Contributions:
Comment about this article or add new information about this topic:
An integrated analysis of Turkish inflation
Article Abstract:
A multivariate cointegration model is used to analyze the inflation process in Turkey. Excess demand in the monetary, government, international and labor sectors is examined. The study focuses on the period 1950-88 during which three relatively high inflationary episodes occurred. Results show that inflation is caused mainly by excess demand in the government sector.
Publication Name: Oxford Bulletin of Economics & Statistics
Subject: Economics
ISSN: 0305-9049
Year: 1995
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Intriguing pendula: founding metaphors in the analysis of economic fluctuations. Economic geography: the great half-century
- Abstracts: The Main Street program in Mississippi. A regional incubator program: the case of the Northeast Mississippi business incubation system
- Abstracts: Contagion: macroeconomic models with multiple equilibria. European monetary integration and the demand for money
- Abstracts: The decomposition of risk in denumerable populations with ex ante identical individuals. Relative risk aversion, relative prudence and comparative statics under uncertainty: The case of (mu,theta )preferences
- Abstracts: Medicare reform: obstacles and options. Canadian national health insurance and infant health. Making the transition to prepaid Medicare