散裝航運市場近趨於完全競爭市場,市場運價具有高度不確定性,因此對於營運者而言存在著巨大的市場營運風險。波羅的海運價综合指數為散裝船業者與相關產業掌握散裝海運市場運價變化之主要參考指標,船東、傭船人如能掌握未來的運價趨勢,將能有效降低航運市場風險,對其投資營運將有很大的幫助。由於散裝海運市場運價是由船噸供給與需求決定,事故自2003年起中國經濟建設蓬勃發展,帶動國際海運需求增加。散裝船主要運送工業原物料為主,所以本研究對散裝波羅的海運價综合指數與全球鋼價指數做關聯性的分析並建構波羅的海運價综合指數之預測模型。研究方法採用時間數列自我迴歸平均整合模型與多變量向量自我迴歸模型為主,資料選取期間為2000年6月至2008年5月之週資料。實證結果顯示波羅的海運價综合指數與全球鋼價指數呈現單向影響關係,波羅的海運價综合指數以全球鋼價指數為領先的指標。當鋼品價格上漲時,將會帶動海運市場運價指數的上漲,即符合海運運輸需求為經濟發展之引申需求條件。在預測波羅的海運價综合指數趨勢方面,本研究最適之單變量模型ARIMA(3,0,1)與多變量模型VAR(6)之均方根百分比誤差分別為4.7294%, 3.9127%。多變量模型VAR(6)有較佳的預測效果。此研究結果,將可以提供海運市場參與者決策之參考。
It is close to perfect competitive market for bulk shipping market and freight rate and charter hire are uncertainty of shipping market so that shipowners and charterers encounter extreme high investment risk. The Baltic Dry Index is the bulk shipping and the correlation industry grasp the main index. The shipowners and charterers can forecast and analyze Baltic Dry Index in order to effectively reduce shipping market risks and increase shipping profitability. The freight rate of dry-bulk shipping is determined by vessel supply and vessel demand. Recent infrastructure construction development in China has boosted strong demand on the volume of the seaborne trade and transportation damand, especially for the industrial raw materials delivered by bulk carrier market. This article explores the relationships between Baltic Dry Index and steel price index, to construct Baltic Dry Index forecast model for bulk shipping service, and discuss its accuracy. The relationships between the variables by using Autoregressive Integrated Moving Average Model and Vector Autoregressive Model. The data employed in this research covers from Jnne 2000 and May 2008 on the weekly basis. The result of this study shows Baltic Dry Index and steel price index exhibiting significant influence, and steel price index is the leading index to Baltic Dry Index. It shows that the price of steel rise will driving the freight rate of dry-bulk shipping. That is accord with the demand of economic development derive the demand of transportation. The RMSPE of the in-sample price forecasts of the best fit model ARIMA(3,0,1) and VAR(6) is 4.7294% and 3.9127%, respectively. The VAR model performed best in forecasting.The results of this paper can provide shipowners and charterers as references for chartering decision-making on shipping investment.