Forecasting Inflation in Emerging Markets by Using the Phillips Curve and Alternative Time Series Models

The aim of this paper is to investigate the performance of the Phillips curve to forecast inflation in a high inflation emerging market country by taking Turkey as a case. For this purpose, we compare the forecasting performance of the Phillips curve with alternative time series models, namely, the univariate ARIMA model, vector autoregression and vector error correction model, and a naive no-change model. The data pertains to the quarterly inflation rate in Turkey for the 1987-2001 period. The results show that inflation forecasts obtained from the Phillips curve are found to be more accurate than forecasts based on other macroeconomic variables. The remaining models outperform the "no-change model" in most of the cases.