A Forecasting Model of Federal Purchases of Goods and Services

Abstract

The principal assumption underlying the model is that Presidential budget recommendations [only for goods and services] are an adequate approximation to Congressional appropriations. This implies that Federal purchases depend on the past stream of budget recommendations. It is suggested that the time shape of this past stream be represented by Koyck and/or Pascal distributed lags. Our best forecasting system, which combines Koyck and Pascal distributions, results in forecast errors of −2.03 per cent for fiscal 1960 and 1.10 per cent for fiscal 1961. We conclude that a distributed lag in budget recommendations for goods and services is extremely useful for forecasting Federal purchases.