FEDERAL-BUDGET PROJECTIONS - A NONPARAMETRIC ASSESSMENT OF BIAS AND EFFICIENCY

As an important initial step in the annual budget process, the Preside nt presents to Congress each January his budget with details of federa l spending activity and priorities. Our paper is a statistical assessm ent of the merit of the budget figures submitted to Congress. We inves tigate the overall budget as well as several important specific accoun ts. An important aspect of our paper is the introduction of a nonparam etric methodology which incorporates exact tests for assessing the unb iasedness, and the internal and external consistency of forecasts. The empirical evidence shows that the nonparametric results confirm the p resence of bias in forecasts on the outlay side suggested by regressio n results, but tends to find fewer series exhibiting bias on the reven ue side. On the other hand, the nonparametric approach lends greater s upport to the conclusion that the government's budget projections do n ot fully exploit available information.