Application of Smooth Transition autoregressive (STAR) models for Exchange Rate

Abstract

This study evaluates the suitability of the Smooth transition autoregressive (STAR) models specification for real exchange rate Modeling. Our paper investigates the stationarity of real exchange rates which assume linearity in it; we also apply the tests to check stationarity that assume nonlinearity in a particular time series. The focus of this study is to explain the simple matter of time series stationarity or non-stationarity regarding modeling; its principle aim is application of logistic Smooth transition autoregressive (LSTAR) and exponential Smooth transition autoregressive (ESTAR) modeling to Exchange rate series to find the model which better explain its deviation from mean. We found ESTAR adjustment for our data series.