Persistence, long memory and seasonality in Kenyan tourism series

Abstract

This article investigates the statistical properties of the total number of arrivals and departures in Kenya for the time period 1975Q1–2011Q4 by looking at the degree of persistence of the series. We use long range dependence techniques and given the quarterly nature of the series seasonality is also taken into account. Moreover, the potential presence of breaks is also considered. The tourism sector in Kenya is especially sensitive to political shocks, and this is particularly exemplified by the shocks in 1992Q4 and 2008Q1 that were associated with crucial election periods in Kenya. Our results, however, show that the series are fractionally integrated with orders of integration strictly below 1. Thus, shocks are expected to be transitory and disappearing relatively quickly.