Forecasting short-term freight rate cycles: do we have a more appropriate method than a normal distribution?

Abstract

General economists, as well as Maritime economists, assume that the time series they forecast follow normal distribution, and data is independently and identically distributed around the mean. This paper contests this assumption with the aid of three sets of time series: (1) The Dry Cargo Freight Index, 1741–2005: in this series the data deviate from the mean by more than three standard deviations on no fewer than six occasions, and exhibited “fat tails”; (2) The time charter freight rates for a 10-year-old, 80 000 dwt vessel from 6 January 1989 to 26 December 2008: this series also exhibits skewness and kurtosis in a leptokurtic distribution; and (3) The Dry Cargo Time Charter Index from 1971 to 2004: this series diverged from the normal distribution four times. Next, we searched more recent data for short-term cycles using the V-statistic. One cycle was found to last 4 years (2005 to 2008), which is in accordance with theory. This cycle started on 29 July 2005 and ended when it reached the (lowest) level of $4000 on 1 December 2008. A new 4-year cycle started on 1 December 2008 and is forecast to last until the end of 2010. Short-term forecasting of the cycle using V-statistic is theoretically confirmed by the theory advanced by Hampton [1990, published in 1989, ‘Analysis and shipping cycles I and II’, Seatrade Journal, 19–23. Long and Short Shipping Cycles: The Rhythms and Psychology of Shipping Markets, Monograph, 2nd ed. (Cambridge: Cambridge Academy of Transport), March, p. 66].