Abstract
We propose a new and simple parametrization of the so-called speed of transition parameter of the logistic smooth transition autoregressive (LSTAR) model.
The new parametrization highlights that a consequence of the well-known identification problem of the speed of transition parameter is that the threshold autoregression (TAR) is a limiting case of the LSTAR process. We demonstrate how this fact impedes numerical optimization of the original parametrization, whereas this is not the case for the new parametrization. Next, we show that information criteria provide a tool to choose between an LSTAR model and a TAR model; a choice previously basedsolely on economic theory. Reestimation of two published applications illustrate the usefulness of our findings.
The new parametrization highlights that a consequence of the well-known identification problem of the speed of transition parameter is that the threshold autoregression (TAR) is a limiting case of the LSTAR process. We demonstrate how this fact impedes numerical optimization of the original parametrization, whereas this is not the case for the new parametrization. Next, we show that information criteria provide a tool to choose between an LSTAR model and a TAR model; a choice previously basedsolely on economic theory. Reestimation of two published applications illustrate the usefulness of our findings.
| Original language | English |
|---|---|
| Place of Publication | Kbh. |
| Publisher | Økonomisk institut, Københavns Universitet |
| Number of pages | 22 |
| Publication status | Published - 2013 |
| Series | University of Copenhagen. Institute of Economics. Discussion Papers (Online) |
|---|---|
| Number | 7 |
| Volume | 13 |
| ISSN | 1601-2461 |