Federal Budget Projections: A Nonparametric Assessment of Bias and Efficiency
用非参数方法检验美国总统提交给国会的年度预算预测是否存在偏差以及是否充分利用了已有信息，发现支出预测有偏差，且预算预测整体未充分利用信息。
As an important initial step in the annual budget process, the President presents to Congress each January his budget with details of federal spending activity and priorities. Our paper is a statistical assessment of the merit of the budget figures submitted to Congress. We investigate the overall budget as well as several important specific accounts. An important aspect of our paper is the introduction of a nonparametric methodology which incorporates exact tests for assessing the unbiasedness, and the internal and external consistency of forecasts. The empirical evidence shows that the nonparametric results confirm the presence of bias in forecasts on the outlay side suggested by regression results, but tends to find fewer series exhibiting bias on the revenue side. On the other hand the nonparametric approach lends greater support to the conclusion that the government's budget projections do not fully exploit available information. Copyright 1995 by MIT Press.