Resumen
This paper presents a method to build up a confidence interval for the evolution of traffic in motorway concessions, based on a univariate time-series model. The main advantage of this method, compared to traditional traffic models, is that it allows to avoid the error in the prediction of the explanatory variables. The results obtained show that the use of a time-series model represents a feasible alternative to assess traffic uncertainty in existing concessions, when long series of traffic data are available.