Measuring Uncertainty and Disagreement in the European Survey and Professional Forecasters

Survey data on expectations and economic forecasts play an important role in providing better insights into how economic agents make their own forecasts, what factors do affect the accuracy of these forecasts and why agents disagree in making them. Uncertainty is also important for better understanding many areas of economic behavior. Several approaches to measure uncertainty and disagreement have been proposed but a lack of direct observations and information on uncertainty and disagreement lead to ambiguous definitions of these two concepts. Using data from the European Survey of Professional Forecasters (SPF), which provide forecast point estimates and probability density forecasts, we consider several measures of uncertainty and disagreement at both aggregate and individual level. We overcome the problem associated with distributional assumptions of probability density forecasts by using an approach that does not assume any functional form for the individual probability densities but just approximating the histogram by a piecewise linear function. We extend earlier works to the European context for the three macroeconomic variables: GDP, inflation and unemployment. Moreover, we analyze how these measures perform with respect to different forecasting horizons. Looking at point estimates and disregarding the individual probability information provides misestimates of disagreement and uncertainty. Comparing the three macroeconomic variables of interest, uncertainty and disagreement are higher for GDP and inflation than unemployment, at short and long horizons. Besides this, it is difficult to find a common behavior between uncertainty and disagreement among the variables: results do not support evidence that, if uncertainty or disagreement are relatively high for one of the variable than it is the same for the others