This paper considers tests of parameters instability and structural change with known, unknown or multiple breakpoints. The results apply to a wide class of parametric models that are suitable for estimation by strong rules for detecting the number of breaks in a time series. For that, we use Chow, CUSUM, CUSUM of squares, Wald, likelihood ratio and Lagrange multiplier tests. Each test implicitly uses an estimate of a change point. We conclude with an empirical analysis on two different models (ARMA model and simple linear regression model).
Other ID | JA89MA25ZS |
---|---|
Journal Section | Research Article |
Authors | |
Publication Date | September 1, 2012 |
Published in Issue | Year 2012 Volume: 2 Issue: 3 |