In this paper, a vector autoregressive model is developed for a sample of ocean dry bulk freight rates. Although the series of freight rates are themselves found to be non-stationary, thus precluding the use of many modelling methodologies, evidence provided by cointegration tests points to the existence of stable long-term relationships between the series. An assessment of the forecasts derived from the model suggests that the specification of these long-term relationships does not improve the accuracy of short- or long-term forecasts. These results are interpreted as a corroboration of the efficient market hypothesis.

Additional Metadata
Keywords autoregressive models, cointegration models, forecasting, shipping sector
Persistent URL dx.doi.org/10.1016/S0965-8564(97)00002-5, hdl.handle.net/1765/2106
Citation
Franses, Ph.H.B.F., & Veenstra, A.W.. (1997). A cointegration approach to forecasting freight rates in the dry bulk shipping sector. Transportation Research. Part A: Policy & Practice, 447–458. doi:10.1016/S0965-8564(97)00002-5