"Government statistical agencies commonly report official economic statistics as point estimates. Agency documents describing data and methods may acknowledge that estimates are subject to error, but they typically do not quantify error magnitudes. News releases present estimates with little if any mention of potential error.In the absence of agency guidance, users of official statistics may misinterpret the information that the statistics provide. I urge statistical agencies to measure uncertainty and report it in their news releases and technical publications. [...]I have suggested ways to measure the transitory statistical uncertainty in estimates of official statistics based on incomplete data and the permanent statistical uncertainty stemming from survey non-response. I have also called attention to the conceptual uncertainty in seasonal adjustment. Statistical agencies would better inform policymakers and the public if they were to measure and communicate these and other significant uncertainties in official statistics. I urge them to do so.An open question is how communication of uncertainty would affect policymaking and private decision making. We now have little understanding of the ways that users of official statistics interpret them. Nor do we know how decision making would change if statistical agencies were to communicate uncertainty regularly and transparently. I urge behavioural and social scientists to initiate empirical studies that would shed light on these matters."
In der Tat sehen Prognosefehler für manche Variablen gar nicht mehr soooo groß aus, wenn man sie ins Verhältnis zur Höhe der nachträglichen Datenrevisionen der statistischen Ämter setzt.