Time series is a collection of dependent data, which, usually observed regularly. In time series analysis, there are sometimes points where the parameters of the model or the distribution of the series experience jumps or changes. From a statistical perspective, these points are referred to as change points. In practice, the number and locations of change points are unknown, and discovering and identifying them is of great importance, particularly for modeling and forecasting time series. This paper introduces the AR(2) model in the presence of change points. After that, the parameters of the AR(2) model with a known change point are estimated using the method of maximum conditional likelihood. Finally, a time series example is used to examine the parameter estimates.
Rahmanpour, A., Waghei, Y. & Gholamreza, M. B. (2024). A look at the change point in second-order autoregressive model. (e729300). Andishe_ye Amari, 29(1), e729300 https://doi.org/10.22034/jr_iss.2024.729300
MLA
Rahmanpour, A., Waghei, Y., & Gholamreza, M. B. "A look at the change point in second-order autoregressive model" .e729300 , Andishe_ye Amari, 29, 1, 2024, e729300. doi: 10.22034/jr_iss.2024.729300
HARVARD
Rahmanpour A., Waghei Y., Gholamreza M. B. (2024). 'A look at the change point in second-order autoregressive model', Andishe_ye Amari, 29(1), e729300. doi: 10.22034/jr_iss.2024.729300
CHICAGO
A. Rahmanpour, Y. Waghei & M. B. Gholamreza, "A look at the change point in second-order autoregressive model," Andishe_ye Amari, 29 1 (2024): e729300, doi: 10.22034/jr_iss.2024.729300
VANCOUVER
Rahmanpour A., Waghei Y., Gholamreza M. B. A look at the change point in second-order autoregressive model. Andishe_ye Amari. 2024;29(1):e729300 (In Persian). doi: 10.22034/jr_iss.2024.729300
