A time series model for the long-term forecast of ports' container handling : the case of the port of Piraeus

Abstract

The purpose of this study is to investigate the future demand of ports’ container handling and to propose a model to forecast this demand using annual data from the Piraeus Port Authority for the period 1980 to 2005. The variables used refer to the GDP, the population of the country, the gross investments of fixed capital of the transport sector, the weighted mean of price of container handling, the unemployment rate, the gross domestic product of the maritime transport sector in current prices, and a dummy variable. The empirical evidence refers to the port of Piraeus; the computations were run using the statistical package SAS and the results are consistent with the theory. The proposed methodology may be used for long run forecasts at any other similar situation.