The New ASA-NBER Survey of Forecasts by Economic Statisticians

Economic forecasts from competent sources are newsworthy events. Men involved in research and planning for government and business use them to check on their own projections and to gauge the general climate of expectations; investors speculate about their probable impact upon industry, trade, and finance; and many just take notice of how the "experts" assess the economy's prospects. But this attention, although nowadays widespread, is typically short-lived. Few bother to keep track of what was predicted and when, how it was done, or how the forecasts turned out. No comprehensive record of forecasts existed until the National Bureau of Economic Research, a few years ago, begani compiling and analyzing such data for short-teri aggregative predictions. While it is certainly desirable that forecasters maintain and study their own records, this is not enough. To provide the corrective information and discipline that are needed, forecast evaluation must be conducted on a much broader, more objective and systematic basis. Reliable information about the limitations of forecasts can be built up in this way, and a basis for improvement in methodology provided.