How to use SETAR models in gretl
- 335 Downloads
This paper presents a means for the diffusion of the Self-Exciting Threshold Autoregressive (SETAR) model. Based on the Hansen (Econometrica 68(3):675–603, 2000) methodology, we implement a function in gretl with which estimate a SETAR model. The function is provided with a nice graphical user interface that enables the average user to estimate a SETAR model and make inference easily. The function and its use is presented by means of a case study. In addition we show more functionalities of gretl in order to perform a preliminary analysis of the data.
KeywordsSETAR models Free and open-source software gretl
The first author gratefully acknowledges financial support from Regione Autonoma della Sardegna through Programma Master and Back. Financial support from research project ECO2010-15332 from Ministerio de Ciencia e Innovacion, and from UPV/EHU Econometrics Research Group, Basque Government grant IT-642-13, is gratefully acknowledged by the second author.
- Adkins, L. (2010). Using gretl for principles of econometrics, 3rd edition version 1.313.Google Scholar
- Cottrell, A., & Lucchetti, R. (2011). Gretl users guide gnu regression, econometrics and time-series library. Google Scholar
- Hansen, B. (1997). Inference in tar models. Studies in Nonlinear Dynamics and Econometrics, 1, 895–904.Google Scholar
- Tong, H. (1983). Threshold models in non-linear time series analysis. Lecture Notes in Statistics, No.21. Heidelberg: Springer.Google Scholar
- Tong, H. (1990). Nonlinear time series, a dynamical system approach. London: Oxford University Press.Google Scholar
- Tong, H., & Lim, K. (1980). Threshold autoregression, limit cycles and cyclical data (with discussion). Journal of the Royal Statistical Society, B42, 245–292.Google Scholar