From Congressional Budget Office report, January 17, 2013, "CBO's Economic Forecasting Record: 2013 Update:"
Do CBO’s Forecasts Exhibit Notable Bias?
A simple and widely used indicator of statistical bias is the mean error—the average tendency of a forecast to be low or high over an entire period. In general, CBO’s forecasts and those by the Administration and the Blue Chip consensus have had similar mean errors. Specifically, CBO’s evaluation finds this:How Accurate Are CBO’s Forecasts?
- For CBO’s forecasts that look two years ahead, the mean errors have generally been very small. The agency’s forecasts have shown slight tendencies to overestimate future interest rates and wages and salaries.
- For CBO’s forecasts that look five years ahead, the mean errors imply a slightly stronger tendency to overestimate inflation compared with that of the agency’s two-year forecasts—which largely accounts for higher mean errors for growth in nominal output and in wages and salaries. In other respects, the mean errors generally resemble those for forecasts that look two years ahead.
Accuracy is the degree to which forecast values are dispersed around actual outcomes. One widely used measure of accuracy is the root mean square error. By that measure, the forecasts by CBO, the Administration, and the Blue Chip consensus have been about equally accurate over two-year periods as well as over five-year periods.
No comments:
Post a Comment