Fuzzy Models and Cointegration Analysis for the Forecast of Tourist Demand

In this paper a fuzzy and cointegration analysis are used to forecast tourist demand in Greece. In the first part, Johansen’s maximum likelihood techniques are applied to estimate the long-run relationships for the principal five tourist generating countries in Greece. In the second part, the estimated error correction terms are introduced to the first difference models to estimate the five short-run relationships (ECMs). In the third part, fuzzy regression models are suggested based on the results given by the ECMs and then compared in order to provide the forecasting ability of both techniques (Fuzzy and ECMs). Finally, for the evaluation of forecasting performance, the U-Theil statistic and Root Mean Square Error ware applied