Forecasting the future: pitfalls in controlling for uncertainty

Whatever the specific definition, the common denominator of any kind of for ecast is a reference to the future. This implies that all sources of uncert ainty associated with describing present and past must also be associated w ith forecasting-and one more: the specification error inherent in the futur e dimension. In particular, this error should be associated with the distin ction between causality and correlation, i.e, the understanding of behaviou r, the necessary prerequisite for prediction. Thus, the key representationa l problem, the gap between model and reality, and the conditions for contro lling that gap, becomes particularly evident in forecasting. This article i s an attempt at clarifying some of the uncertainties most prevalent in fore casting, as a means to show with what respect they must be treated. The dis cussion relates to forecasting in general, but with some special references to air traffic. (C) 1999 Elsevier Science Ltd. All rights reserved.