The unit root tests with a break in innovation variance were discussed. It was found that an abrupt change in the innovation variance of an integrated process can generate spurious rejections of the unit root null hypothesis in routine applications of Dickey-Fuller tests. The t-ratio for testing ρ = 1 was elaborated. The modified test statistics based on unit root tests of Perron for a time series with a changing level or changing intercept was also devleoped.
All Science Journal Classification (ASJC) codes
- Economics and Econometrics