Forecasting Stock Prices by Using Alternative Time Series Models

The purpose of this paper is to compare the forecast performance of alternative time series models, namely VAR in levels, stochastic seasonal models (SSM) and error correction models (ECM) at the Istanbul Stock Exchange (ISE). Considering the emerging market characteristic of the ISE, stock prices are estimated by using, money supply, inflation rate, interest rates, exchange rates and budget deficits. Then, in an out-of-sample forecasting exercise from January 1995 through December 1995, comparisons will be given as to the performance of alternative forecasting models at different forecast horizons of short, medium and long terms, respectively. Empirical results showed that ECM captures market movements much better.