Vector Autoregression Modelling and Forecasting Growth of South Korea

In this paper we have estimated Vector Autoregression (VAR), Bayesian VAR and Vector Error Correction models (VECMs) using annual time series data of SOuth Korea for 1950-1994. We find evidence supporting the view that growth of real per capita income has been aided by income, investment and export growth and government spending and exchange rate policies. VECMs provide better forecasts of growth than the VAR and BVAR models for both short-period and long-period ahead forecasts.