Exchange Rate Forecasting Based on Fundamental Macroeconomic Variables in a Floating Exchange Rate Regime: Evidence from an Emerging Economy

2. Literature Review

The Meese and Rogoff (1983) study is one of the most important articles on the topic of exchange rate forecasting in the literature. On the basis of empirical evidence, Meese and Rogoff concluded that random walk model is a successful forecasting model for exchange rates.

Following Meese and Rogoff, results of the studies of Somanath -1986; Alexander and Thomas – 1987; Boothe and Glassman – 1987; Wolff – 1987 and 1988 suggest that econometric forecasting models of exchange rates failed to outperform the random walk model in forecasting variations in exchange rates.

There are also studies which contradict the earlier findings. Results of the studies of Woo (1985), Schinasi and Swami (1989), Kuan and Liu (1995), Brooks (1997), Gencay (1999), Hogan et al. (2001), Cuaresma et al. (2004), Kumar and Thenmozhi (2004, 2005), Hongxing et al. (2007), and Chen et al. (2008), show that their models outperform the random walk model for certain time periods and currencies. These studies conclude that the presence of nonlinearity, volatility, non-stationarity in the exchange rates was not handled properly in previous empirical models. This resulted in the random walk scoring over other models.