To aggregate, pool, or neither: Testing the Rational Expectations Hypothesis using survey data

It is well known that even if all forecasters are rational, estimated coeffi-cients in unbiasedness regressions using consensus forecasts are inconsistent because forecasters have private information. However, if all forecasters face a common realization, pooled estimators are also inconsistent. In contrast, we show that when predictions and realizations are integrated and cointe-grated, micro-homogeneity ensures that consensus and pooled estimators are consistent. Therefore, contrary to claims in the literature, in the absence of micro-homogeneity, pooling is not a solution to the aggregation problem. We reject micro-homogeneity for a number of forecasts from the Survey of Pro-fessional Forecasters. Therefore, for these variables unbiasedness can only be tested at the individual level