A RANDOM PARAMETER LOGIT APPROACH TO THE TWO-STAGE TOURIST CHOICE PROCESS: GOING ON HOLIDAYS AND LENGTH OF STAY

This paper assumes that the decision to go on holiday and the length of stay are non independent, thus the objective of this paper is to propose a two-stage tourist choice process: going on holiday and length of stay. To do this, we rely on the Random-Parameter Logit Model, which accounts for the unobserved heterogeneity of tourists and allows representation of different correlation patterns among non independent alternatives. We propose hypotheses on the effect on the above decisions of tourist characteristics relating to the destination, personal restrictions and socio-demographic and psychographic characteristics. The empirical application, which is carried out in Spain on a sample of 3,781 individuals, evidences the proposed two-stage tourist choice process. In addition, these decisions are also explained by individual tourist characteristics.