本文旨在探究油輪運費率的長期記憶現象。運用GPH、GSP檢定及HYGARCH、FIEGARCH長期記憶 GARCH模型來檢視。研究結果顯示，採用偏態t分配的長期記憶GARCH模型可能對於油輪運費率較 能精確估計，並且提升長期預測與定價的精確性。因此，對於油輪運費率的風險估計，應將其長期 記憶現象納入考量，同時所採用的GARCH模型應能一併考量波動的叢聚現象、不對稱性、厚尾及 長期記憶等因素。這些結果可以應用在實務界從事油輪運費市場之風險管理。

This study aims to investigate the features of tanker freight rates when there is a long memory effect. We employed the GPH test, the GSP test, the HYGARCH and the FIEGARCH models for the long memory test and estimation. Our results suggest that precise estimates of tanker freight rates may be acquired from a long memory in volatility models with the skewed Student-t distribution. Such models improve the long-term volatility forecast and produce more precise pricing of tanker freight contracts. Moreover, for the appropriate risk evaluation of tanker freight rates, the degree of persistence should be examined and modelling that includes volatility clustering, asymmetry, leptokurtosis and long range dependence should be considered. Therefore, we could extend these findings to risk management in the tanker freight markets.