An examination of tourist arrivals dynamics using short-term time series data: a space–time cluster approach.

Abstract

The purpose of this study is to examine the development of Italian tourist areas (circoscrizioni turistiche) through a cluster analysis of short time series. The technique is an adaptation of the functional data analysis approach developed by Abraham et al (2003), which combines spline interpolation with k-means clustering. The findings indicate the presence of two patterns (increasing and stable) averagely characterizing groups of territories. Moreover, tests of spatial contiguity suggest the presence of 'space-time clusters'; that is, areas in the same 'time cluster' are also spatially contiguous. These findings appear to be more robust in particular for those series characterized by an increasing trend.