FORECASTING GROWTH WITH TIME-SERIES MODELS

This paper compares the structure of three models for estimating futur e growth in a time series. It is shown that a regression model gives m inimum weight to the last observed growth and maximum weight to the ob served growth in the middle of the sample period. A first-order integr ated ARIMA model, or I(1) model, gives uniform weights to all observed growths. Finally, a second-order integrated ARIMA model gives maximum weights to the last observed growth and minimum weights to the observ ed growths at the beginning of the sample period. The forecasting perf ormance of these models is compared using annual output growth rates f or seven countries.