成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	蘇宗賢 Su, Tsung-hsien
論文名稱：	油輪租金之指數迴歸預測模型 Forecasting Tanker Freight Rate Using Exponential Regression Model
指導教授：	張瀞之 Chang, Ching-chih
學位類別：	碩士 Master
系所名稱：	管理學院 - 交通管理科學系 Department of Transportation and Communication Management Science
論文出版年：	2009
畢業學年度：	97
語文別：	英文
論文頁數：	58
中文關鍵詞：	MAPE 、X12 、HP 、MAXR 、油輪、運費指數
外文關鍵詞：	X12, MAPE, HP, MAXR, Tanker, Freight Rate
相關次數：	點閱：65 下載：2
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

世界景氣在次級房貸危機爆發之後急遽下滑，美國金融體系面臨崩壞，進而擴散到全世界，各國股市無不重挫、企業經營困難、人民消費信心跟能力都變得疲弱，但在2007年底旺盛的國際進出口貿易仍然支撐了世界的經濟成長，國際運輸事業在此艱困的時刻扮演了極為重要的角色，經濟發展需要能源支撐，因此佔整體國際運輸運量三分之一的油輪產業自有舉足輕重的地位，大部分的石化相關產業所需之能源都是採取論時傭船的方式來運輸，但油輪論時傭船租金的波動性大，所以本篇論文發展出油輪論時傭船租金的模型，供船東、投資人、銀行、業者來使用，以期降低其營運或投資風險。
本篇論文所探討的三大油輪論時傭船租金之船型分別為VLCC、Suezmax、Aframax，而使用的潛在自變數為布蘭特原油價格、不同地區之石油產量及全球油輪總船隊量，因為所使用的資料均具有時間序列之特性，因此先使用了X-12 Decomposition 及 Hodrick Prescott Filter將資料中的循環項分離出來，接著使用Maximum Rsquare Improvement 挑選出最顯著的自變數，然後利用指數迴歸模型推導出最終之油輪租金預測模型，最後再輔以Mean Absolute Percentage Error（MAPE）指標去衡量模型之配適度，結果顯示本論文三大油輪租金之最終預測模型的MAPE均小於20%，表示預測模型之配適度佳，因此，透過此預測模型之建構，有效提供使用者了解且預測未來油輪論時傭船市場之租金變動，進而降低市場參與者對於油輪租金劇烈波動下所承受之經營或投資風險。

The decline of global economy occurred after the subprime mortgage crisis broke out. The financial systems in America faced going bankrupt and that also influenced the other countries around the world. The crisis made stock markets of many countries go slump, the operating of corporations more difficult even the democratic confidence and capacity for consuming become deficient. However, in the end of 2007, GDP growth rate still remain positive that partially resulted from the strong global trade. The international transportation industries played a main role at the critical moment, therefore the tanker industry that comprised of one-third of the world total fleet is extremely important. Almost the related petroleum corporations shipped their oil by making time charter party; nevertheless, time charter rate has great volatility. Hence, this research developed the model for tanker time charter rate for the participants to lower operating or investing risks.
The three tankers of different sizes in this research are VLCC, Suezmax and Aframax; in contrast, the potential explanatory variables are Brent oil price, oil productions from different areas and world total tanker fleet. This research used the X-12 Decomposition method and the Hodrick-Prescott filter method to get the cyclical components. The Maximum Rsquare Improvement method was applied to selecting the significant variable. This research developed final predictive models from the exponential model and checked them by Mean Absolute Percentage Error (MAPE). All the estimated MAPEs of final predictive models are less than 20%, which means they are sorted as good models. Hence, the predictive models could effectively offer the user to realize and forecast the fluctuation of the time charter rate to reduce the risks.

CONTENTS	  I
LIST OF TABLES    II
LIST OF FIGURES     III
CHAPTER 1 Introduction   1 
1.1 Research Background and Motivation   1
1.2 Research Scope   2
1.3 Research Objective    3 
1.4 Flow Chart    4
CHAPTER 2 Literature Review  	6
2.1 Seasonal Adjustment Method and Hodrick-Prescott Filter (HP)  6
2.2 Maximum R-square Improvement (MAXR)  8
2.3 Mean Absolute Percentage Error (MAPE)  9
CHPATER 3 Methodology	11
3.1 Data Collection	11
3.2 Time Series Data	13
3.3 X-12-AMIRA Decomposition	14
3.4 Hodrick-Prescott Filter (HP)	15
3.5 Maximum R-square Improvement (MAXR)	16
3.6 The Exponential Model and the Predictive Model	17
3.7 Mean Absolute Percentage Error (MAPE)	22
3.8 Summary	23
CHPATER 4 Empirical Analysis	24
4.1 Descriptive Analysis	24
4.2 Seasonal Adjustment and The Hodrick-Prescott Filter	29
4.3 Variable Selection	32
4.4 Predictive Model	33
4.5 Forecasting Analysis	40
4.6 Discussion	42
4.7 Summary	45
CHPATER 5 Conclusions and Suggestions	46
Reference 	48
Table 3.1 The Unit and Definition of the Response Variables	12
Table 3.2 The Unit and Definition of the Potential Explanatory Variables	12
Table 3.3 The Criterion for the MAPE	23
Table 4.1 Descriptive Analysis of VLCC, Suzemax and Aframax	25
Table 4.2 Descriptive Analysis of the Potential Explanatory Variables	26
Table 4.3 The R-Square of Regression Equations of VLCC, Suezmax and Aframax	32
Table 4.4 OPEC’s Oil Production (OPEC) and Global Oil Production (Global)	43
Table 3.1 The Unit and Definition of the Response Variables	12
Table 3.2 The Unit and Definition of the Potential Explanatory Variables	12
Table 3.3 The Criterion for the MAPE	23
Table 4.1 Descriptive Analysis of VLCC, Suzemax and Aframax	25
Table 4.2 Descriptive Analysis of the Potential Explanatory Variables	26
Table 4.3 The R-Square of Regression Equations of VLCC, Suezmax and Aframax	32
Table 4.4 OPEC’s Oil Production (OPEC) and Global Oil Production (Global)	43
Figure 1.1 Research flow chart	5
Figure 3.1 The Example for Nonlinear Model	17
Figure 3.2 The Pattern of Different Sum of c and α	20
Figure 3.3 The Pattern of Different  	20
Figure 3.4 The Pattern of Different  	21
Figure 4.1 The Trend of VLCC, Suezmax and Aframax	27
Figure 4.2 The Trend of NOWP, OPEC and WWOP	28
Figure 4.3 The Trend of BCOP and TOTF	28
Figure 4.4 Trend&Cycle (TC), Trend, and Cycle of Brent Crude Oil Price	29
Figure 4.5 Trend&Cycle (TC), Trend, and Cycle of OPEC Crude Oil Production	30
Figure 4.6 Trend&Cycle (TC), Trend, and Cycle of W. World Oil Production	30
Figure 4.7 Trend&Cycle (TC), Trend, and Cycle of Non OPEC-WWOP Production	31
Figure 4.8 Trend&Cycle (TC), Trend, and Cycle of Total Tanker Fleet Development	31
Figure 4.9 The Actual Value of OPEC (OPEC) and the Predictive Value of OPEC	33
Figure 4.10 The Actual Value of VLCC and the Predictive Value of VLCC	34
Figure 4.11 The Actual Value of VLCC and the Predictive Value of VLCC	35
Figure 4.12 The Actual Value of Suezmax and the Predictive Value of Suezmax	37
Figure 4.13 The Actual Value of Suezmax and the Predictive Value of Suezmax	38
Figure 4.14 The Actual Value of Aframax and the Predictive Value of Aframax	39
Figure 4.15 The Actual Value of Aframax and the Predictive Value of Aframax	40
Figure 4.16 The Actual Value of VLCC and the Predictive Value of VLCC	41
Figure 4.17 The Actual Value of Suezmax and the Predictive Value of Suezmax	41
Figure 4.18 The Actual Value of Aframax and the Predictive Value of Aframax	42
                                    

Adhikari, M., Paudel, K., Paudel, L., & Bukenya, J. (2007). Modelling swine supply response using a structural time series approach. Applied Economics Letters, 14(7-9), 467-472.

Amornthum, S. (2002). Japan's Potential Growth : An Hp Filter Approach. Reasearch Paper for Econ 614 Economic Development of Japan.

Bae, S. C, & Duvall, G. J.(1996) An Empirical Analysis of Market and Industry Factors In Stock Returns of U.S. AEROSPACE Industry. Journal Of Financial And Strategic Decision , 9(2),85-94.

Bera, A. K., & Jarque, C. M. (1981). Efficient tests for normality, heteroscedasticity and serial independence of regression residuals: Monte Carlo evidence. Economic Letters, 7, 313-318.

Bowerman, L., & O'Connell, T. (1987). Time Series Forecasting: Unified Concepts and Computer Implementation 2nd edition.

Bruce, A. G., & Jurke, S. R. (1996). Non-Gaussian Seasonal Adjustment: X-12-ARIMA Versus Robust Structural Models. Journal of Forecasting, 15, 305-327.

Christian, M. D., Henrik, H., & John, S. (2005). The cyclical component factor model. Econometric Links of the Econometrics Journal.

Clarkson Research Limited Services. (2008).Shipping Sector Report.

Dagum, E. B. (1980). The X11-Arima Seasonal Adjustment Method. Ottawa:Statistics Canada, Catalogue, No. 12-564E.

Dagum, E. B. (1988). The X11-Arima/88 Seasonal Adjustment Methods -Foundations and User's Manual. Ottawa: Statistics Canada.

Dosse, J., & Planas, C. (1996). Revisions in Seasonal Adjustment Methods: an Empirical Comparison of X-12-ARIMA & SEATS. L – 2920 Luxembourg.

Drezner, Z., Marcoulides, G. A., & Stohs, M. H. (2001). Financial Applications of a Tabu Search Variable Selection Model. Journal of Applied Mathematics & Decision Sciences, 5(4), 215.

Findley, D. F., Monsell, B. C., Bell, W. R., Otto, M. C., & Chen, B. C. (1998). New Capabilities and Methods of the X-12-ARIMA Seasonal-Adjustment Program. Journal of Business & Economic Statistics, 16(2), 127-152.

Fischer, B. (1995). Decomposition of Time Series-Comparing Different Methods in Theory and Practice. Eurostat Working Paper.

Gallego, F.A., &Johnson, C.A.(2005) Building Confidence Intervals for the Band-Pass and Hodrick-Prescott Filters: An Application using bootstrapping. Applied Economics, 37, 741-749.

Ghysels, E., Granger, C. W. J., & Siklos, P. L. (1996). Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process? Journal of Business & Economic Statistics, 14(3), 374-386.

Glen, D.R., & Martin, B.T. (1998). Conditional modelling of tanker market risk usingroute specific freight rates. Maritime Policy & Management, 25(2), 117-128.

Granger, C.W.J., & Terasvirta, T.(1993).Modeling Nonlinear Economic Relationships.

Hodrick, R. J., & Prescott, E. C. (1980). Postwar U.S. Business Cycle: An Empirical Investigation. Working Paper, Carnegie-Mellon University.

Hodrick, R. J., & Prescott, E. C. (1997). Postwar U.S. Business Cycles: An Empirical Investigation. Journal of Money, Credit and Banking, 29(1), 1-16.

Johnson, M., Hood, C., Monsell, C., & Li, C. (2007). Comparing Automatic ModelingProcedures of TRAMO and X-12-ARIMA, an Update. U. S. Census Bureau1.

Kavussanos, M.G. (2003). Time Varying Risks Among Segments of the Tanker Freight Markets Maritime Economics & Logistics, 5(3), 227-250.

Koushki, P.A., Smith, R.L., & Barry, Z.A. (1992) A Paratransit Maintenance Cost-Allocation Model.

Lackman, C. L. (2007). Forecasting sales for a B2B product category: case of auto component product.Journal of Business & Industrial Marketing, 22(4-5), 228-235.

Lewis, C.D. (1982). Industrial and Business Forecasting Method. London: Butterworth Scientific Publishers.

Lyridis, DV., Zachcrioudakis, P., Mitrou, P., & Mylonas, A. (2004). Forecasting Tanker Market Using Artificial Neural Networks. Maritime Economics & Logistics, 6, 93-108.

Min, Q. (1999). Nonlinear Predictability of Stock Returns Using Financial andEconomic Variables. Journal of Business & Economic Statistics, 17(4).

Ming, Z, & Qin, S. (2007). Econometric Modeling of Second-hand Tanker Prices. Proceedings of the IEEE International Conference on Automation and Logistics, 709-713.

Neter, & Kutner,. (1996). Applied Linear Statistical Model.

Ni, D., & Wang, H. (2008).Trajectory Reconstruction for Travel Time Estimation Journal of Intelligent Transportation Systems, 12(3), 113–125.

Ratkowsky, D.A.(1989).Handbook of Nonlinear Regression Models.

Razzak, W. (1997). The Hodrick-Prescott technique: A smoother versus a filter: An application to New Zealand GDP. Economics Letters, 57(2), 163-168.SAS User’s Guide.

Shiskin, J., Young, A. H., & Musgrave, J. C. (1967). The X-11 Variant Of the Census Method II Seasonal Adjustment Program. Technical Paper 15, Washington, D.C.: Bureau of the Census

United Nations. (2008).Review of Maritime Transport 2008.

Watson, M. W. (1996). Is Seasonal Adjustment a Linear or Nonlinear Data-Filtering Process? Comment. Journal of Business & Economic Statistics, 14(3), 394-396.

Wynne, M.A.., & Vega, J.L. (2003). A First Assessment of Some Measures of Core Inflation for the Euro Area. German Economic Review, 4(3), 269-306.

校內：2011-07-07公開
校外：2011-07-07公開

簡易檢索 / 詳目顯示

相關論文