Forecasting tourism demand: A comparison of the accuracy of several quantitative methods

Forecasting accuracy is examined in the context of international tourism demand. Seven quantitative forecasting methods are used to generate out of sample forecasts for tourist flows across twenty-four origin-destination pairs, and two forecasting horizons. Two alternative accuracy measures are used to evaluate forecasting performance. Statistically significant differences in forecasting accuracy are identified using the ANOVA and Scheffé tests. Several of the simple forecasting methods produce more accurate forecasts than econometric forecasts. As expected, one-year-ahead forecasts are more accurate than two-years-ahead forecasts. Aggregation of data series appears to reduce forecasting accuracy slightly.