Forecasting Performance of Exponential Smooth Transition Autoregressive Exchange Rate Models

Abstract

This paper compares the forecasting performance of the Smooth Transition Autoregressive (STAR) model with the conventional linear Autoregressive (AR) and Simple Random Walk (SRW) models. The empirical analysis was conducted using quarterly data for the yen-based currencies of six major East Asian countries. We discovered strong evidence on nonlinear mean reversion in deviation from purchasing power parity (PPP). The results suggest that both the STAR and AR models outperform or at least match the performance of the SRW model. The results also show that the STAR model outperforms the AR model, its linear competitor in a 14-quarter forecast horizon. This finding is consistent with the emerging line of research that emphasizes the importance of allowing nonlinearity in the adjustment of exchange rate.Since the establishment of the free float regime in March 1973, exchange rate forecasting has been an important research issue in exchange rate study. However, previous findings generally cannot negate over the fact that exchange rate models forecast no better than the random walk, the so-called "model of no change '' (Meese and Rogoff, 1983a,b; Diebold and Nason, 1990; Meese and Rose, 1991; Lin and Chen, 1998; Kilian and Taylor, 2001). Several authors have argued that this forecast failure is due to the fact that exchange rate models ignore nonlinearity adjustments to their equilibrium values (e.g.

Purchasing Power Parity in Less‐developed and Transition Economies: A Review Paper

“…Paya and Peel (2005) test an ESTAR model on the high‐inflation countries of Argentina, Brazil, Israel and Colombia, and find that their results fit the model. Baharumshah and Liew (2006) demonstrate stronger nonlinear mean reversion for six East Asian economies compared to other models using a STAR methodology. Holmes and Wang (2006) conclude that deviations behave asymmetrically for nine Asian countries, including Japan.…”

Linearity and Stationarity of G7 Government Bond Returns

“…Recently, there has been empirical evidence (for example, van Dijk and Franses (2000), Sarno (2000), Baum et al (2001), Kapetanios et al (2003), Liew et al (2003), Shively (2005), Baharumshah and Liew (2006), and Baillie and Kilic (2006)) that shows that financial time series are mostly nonlinear in nature. To cater for nonlinearity, Kapetanios et al (2003) propose to first estimate the following nonlinear autoregressive process: …”

Modelling Ireland's Exchange Rates: From EMS to EMU

“…The reason for this choice is that it is felt that the movement of the real exchange rate is symmetrical. However others, such as Baharumshah and Liew (2006), argue that the asymmetric logistic function (and hence the Lstar model) should also be considered, i.e.,…”