Minimum LM Unit Root Test with One Structural Break
Abstract
In this paper, we propose a minimum LM unit root test that endogenously determines a structural break in intercept and trend. Critical values are provided, and size and power properties are compared to the endogenous one-break unit root test of Zivot and Andrews (1992). Nunes, Newbold, and Kuan (1997) and Lee and Strazicich (2001) previously demonstrated that the Zivot and Andrews test exhibits size distortions in the presence of a break under the null. In contrast, the one-break minimum LM unit root test exhibits no size distortions in the presence of a break under the null. As such, rejection of the null unambiguously implies a trend stationary process.
Citation impact
629
total citations
- FWCI
- 11.21
- Percentile
- 100%
- References
- 12
Citations per year
Authors
2Topics & keywords
Topics
Keywords
- Unit root
- Null (SQL)
- Structural break
- Unit root test
- Mathematics
- Null hypothesis
- Statistics
- Computer science
No related works found for this paper.