Document details

This paper employs count data models to estimate the determinants of length of stay, as count data models naturally lend themselves to overcome the censoring and truncation data issues associated with the non-negative, integer nature of length of stay. This paper employs a rich micro data set gathered through questionnaires ministered to a representative sample of tourists departing from the Azores: the fastest growing touristic region in Portugal. It is found that sociodemographic profiles, such as nationality and Azorean ascendancy, and trip attributes, such as repeat visitation rates and type of flight, are important determinants of length of stay. In addition, it is found that destination image and attitudes regarding environmental initiatives, constructed from a factor analysis exercise, also influence length of stay. In particular, the results suggest that marketing strategies that promote the Azores for its nature, landscape, remoteness, weather and safety may increase length of stay, whereas cultural heritage has the opposite effect.