Predictions vs preliminary sample estimates

In general, rational economic agents are not in the position to wait for the statistical agencies disseminate the final results of the relevant surveys before making a decision, and have to make use of some model based predictions, even when agents are not assumedly forward looking. Thus, from the viewpoint of agents, predictions and preliminary results from surveys often compete against each other. Agents are aware to incur in a loss basing their decisions on predictions instead of sound statistical data, but the loss could be smaller than the one related to waiting for the dissemination of final data. Comparing the loss attached to predictions, on the one hand, and to possible preliminary estimate from incomplete samples, on the other, provides a broad guidance in deciding if and when statistical agencies should release preliminary and final estimates of the key variables. The main result of the analysis is that, in general, preliminary sample estimates are useful for the users only if they come from unexpectedly large sub-samples, even when the predictability of relevant variables is scarce. Nevertheless, the cost of delaying decisions for many economic agents may support the dissemination of early estimates of the main economic aggregates even if their accuracy is not fully satisfactory from a strict statistical viewpoint.