Seasonal forecasting performance considering varying income elasticities in tourism demand

Abstract

This article analyses varying tourism demand elasticities by season across business cycles based on time series in the context of forecasting performance. We compare for the first time the forecasting performance of models considering the asymmetric behavior of tourism demand with models focusing on symmetric demand behavior. For this reason, this article analyses the outbound expenditures of different source markets by quarter since 2000. The estimation results showed that it was only possible to identify asymmetric income effects. In the case of the price effects, we had to accept—based on the data set available—symmetric behavior. The general outcome of the study revealed compelling evidence that the majority of models allowing us to measure asymmetric income effects yield superior forecasting performance in comparison to models considering only the possibility of symmetric income effects across business cycles.