臺灣博碩士論文加值系統

汽車是石油能源消耗與移動污染源中排放二氧化碳的主要來源，也是運輸部門推動二氧化碳排放減量政策的主要對象。汽車總量事實上決定了污染程度，台灣地區汽車的持有逐年成長，二氧化碳排放問題日益嚴重。因此，就能源消耗與二氧化碳排放污染問題，由於台灣目前的機動車輛持有狀態已隨著所得之提高漸漸成為一種必需品，因此儘早掌握汽車的成長趨勢有其必要性。
本論文主要研究目的在於建立汽車持有需求之動態預測模型，首先考慮汽車持有需求此一依變數的時間記憶特性，建立納入解釋變數之ARMAX 模式；其次考慮汽車持有需求與價格變數可能同時被決定的特性，建立聯立方程模式；最後進一步考慮汽車與機車之間可能的替代關係，建立汽、機車需求與價格變數之聯立方程模式。
本研究收集的資料包括1981-2006年間台灣地區的汽車持有登記(AUTO)、機車持有登記(MOTOR)，以及總體經濟變數如交通類別之消費者物價指數(TCCPI)、人口數(POP)、就業人口數(EM)、家戶數(HOUSE)、實質國民生產毛額(GDP)、國際原油價格(OILP)等年資料以及1990-2006年間的季資料，同時以三項虛擬變數反應1999與1987年的兩次牌照管理政策與2001年台灣加入WTO事件。然而對於年資料與季資料變數的穩定性質，ADF與KPSS單根檢定分析結果顯示：季資料變數經過自然對數轉換後為不穩定，而年資料變數經過自然對數轉換則為穩定，因此在實證模式建立將係以年資料變數作為樣本。
在總體經濟變數對於汽車持有需求的領先關係上，根據 Granger因果關係檢定結果，顯示在5%的顯著水準下，交通類別之消費者物價指數(TCCPI)、人口數(POP)、就業人口數(EM)、家戶數(HOUSE)、實質國民生產毛額(GDP)、國際原油價格(OILP)的自然對數對於汽車持有需求的自然對數lnAUTO無Granger因果關係存在，不是汽車持有需求的的自然對數lnAUTO的領先指標。
模式估計結果顯示ARMA(1,1)模式為本研究 數列的最佳ARMA模式型態，而包含解釋變數的ARMAX(1,1)模式，估計結果顯示lnTCCPI、lnGDP與虛擬變數D1為ARMAX(1,1)模式的三項顯著的解釋變數，其中lnTCCPI與lnGDP的顯著之水準為1%，D1的顯著之水準為10%；在聯立方程模式A，經以3SLS法估計，對於 模式，落後依變數 為顯著，而顯著的解釋變數則為實質國民生產毛額的自然對數 以及虛擬變數D1。對於 模式而言，顯著的解釋變數為國際原油價格的自然對數 與的匯率的自然對數 ；聯立方程模式B主要是進一步考慮汽車持有需求與機車持有需求之間可能存在的替代性關係，因此不同於聯立方程模式A之處即在於聯立方程系統中再加入機車持有需求方程式以反映此種可能存在的替代關係。經以3SLS法估計，結果顯示對於 模式，另一依變數 為顯著，落後依變數 為顯著，而顯著的解釋變數則為虛擬變數D1；對於 模式，另一依變數 為顯著，落後依變數 為顯著，而顯著的解釋變數則為虛擬變數D2；而對於 模式，顯著的解釋變數為實質國民生產毛額的自然對數 與國際原油價格的自然對數 。
在模式評估方面，本研究使用平均絕對誤差(MAE)、根均方誤差(RMSE)、平均絕對百分比誤差(MAPE)與根均方百分比誤差(RMSPE) 四項評估指標進行模式評估，並分別以全樣本(1981-2006)與部分樣本(1981-2004) 的方式進行模式配適度評估與預測精確度評估。在全樣本(1981-2006)配適度評估部分，ARMAX(1,1)之配適度是最佳的，其次為聯立方程模式A；在部分樣本(1981-2004)配適度與預測精確度評估部分， ARMAX(1,1)之配適度仍是最佳的，其次為聯立方程模式A；但在樣本外的預測精確度方面，則以聯立方程模式A的精確度最高，ARMAX(1,1)模式次之。最後本研究認為由於ARMAX(1,1)的樣本外預測偏離度非常高，故在預測應用模式的選擇上，認為應用聯立方程模式A將較為適當與合理。
最後，情境預測結果指出，台灣地區如同其他開發中國家的汽車持有需求現象，經濟成長是造成汽車持有需求年平均成長率增加的主要因素，也就是汽車持有需求多由經濟成長所驅動，若每年經濟成長率增加1%時，汽車持有需求年平均成長率約增加0.53%。另一方面，原油價格與汽車持有需求年平均成長率則呈現反向關係，高油價訊息會反應於汽車持有需求成長上，模擬結果發現，當油價每年成長1%時，汽車持有需求年平均成長率約可減少至0.05%，也證實了原油價格與汽車持有需求年平均成長率之間的反向影響程度。
本研究預測台灣未來2007-2015年可能遭遇的汽車持有需求的成長現象，而為朝向永續發展的目標，本研究成果將有助於運輸部門及早思考規劃台灣地區的汽車持有的運輸管理政策，能源部門則可藉此規劃能源消費需求與二氧化碳排放評估等議題。

The dynamic characteristics of automobile demand are critical for national economic and energy prediction. Although forecasting automobile demand has been previously investigated, it has not been within such a dynamic simulation framework in Taiwan. In this study, dynamic automobile demand models are investigated. An ARMAX model and two simultaneous-equations models are constructed and evaluated, using 1981-2006 annual data.
Automobile registration data is used and several economic variables including real GDP, population, employment, households, world crude oil prices, exchange rate, transportation and communication CPI and motorcycle registration data are considered. Besides, variables’ stationarity is examined by the ADF and KPSS unit root tests to avoid spurious regression.
Estimated results of ARMAX model show that quantity of automobile demand can be explained by the real GDP and Transportation and communication CPI (TCCPI), a first-order autoregressive and a stochastic movingaverage filter at lag 1.
Results of the first simultaneous-equations model (two endogenous variables, automobile demand and TCCPI) indicate that quantity of automobile demand is explained by the lagged dependent variable and the real GDP. Another endogenous variable TCCPI is explained by the world crude oil price and the exchange rate.
Results of the second simultaneous-equations model (three endogenous variables, automobile demand, motorcycle demand and TCCPI) indicate that quantity of automobile demand may be explained by the lagged dependent variable and the quantity of motorcycle demand. There is substitution relationship between automobile and motorcycle demand.
Evaluation results indicate that there is excellent model fitness for ARMAX and two simultaneous-equations models in the sample period 1981-2006. For the application of forecasting, this study considers the out-of-sample prediction accuracy. Results show that first simultaneous-equations model has the best out-of-sample prediction performance. Finally, through this model, the future quantity of automobile is forecasted and a number of simulation experiments considering various oil price and economic growth scenarios for 2007-2015 are demonstrated.

中、英文摘要 1
誌謝 6
目錄 7
表目錄 10
圖目錄 12
第一章 緒論 13
1.1 研究背景 13
1.2 研究動機 14
1.3 研究目的與方法 17
1.4 研究內容與流程 18
第二章 文獻回顧 22
2.1 汽車持有需求之個體模式 22
2.2 汽車持有需求之總體模式 24
2.3 綜合整理與汽機車替代性 27
2.3.1 綜合整理 27
2.3.2 汽機車替代關係 30
第三章 理論模式與研究方法 31
3.1 理論模式 31
3.2 單根檢定 35
3.3 Granger因果關係檢定 39
3.4 ARMAX模式 42
3.4.1 ARMA 42
3.4.2 ARMAX 44
3.5 聯立方程模式 45
第四章 實證分析模式 47
4.1 資料、穩定性質與Granger因果關係 47
4.1.1 資料來源 47
4.1.2 單根檢定結果 52
4.1.3 Granger因果關係檢定結果 54
4.2 ARMAX模式 56
4.3 聯立方程模式A 60
4.4 聯立方程模式B 62
第五章 模式評估 66
5.1 評估指標 66
5.2 全樣本估計模式之配適度評估 68
5.3 部分樣本估計模式之預測準確度評估 72
第六章 情境預測 79
6.1 情境設定 79
6.1.1 經濟成長 79
6.1.2 油價變動 80
6.1.3 匯率變動 81
6.2 預測結果 82
6.2.1 經濟成長情境預測結果 82
6.2.2 油價變動情境預測結果 84
6.2.3 匯率變動情境預測結果 85
6.3 綜合分析與經濟意涵 87
第七章 結論與建議 90
7.1 結論 90
7.2 建議 93
參考文獻 95
附錄A 季資料變數趨勢圖 102
附錄B 年資料變數趨勢圖 106

1.Abu-Eisheh, S. A. and Mannering, F. (2002) Forecasting automobile demand for economies in transition: a dynamic simultaneous-equation system approach. Transportation Planning and Technology, 25, 311-331.
2.Akal, M. (2004) Forecasting Turkey’s tourism revenues by ARMAX model. Tourism Management, 25, 565-580.
3.Balsas, C.J.L. (2003) Sustainable transportation planning on college campuses. Transport Policy, 10, 35-49
4.Barnett, S., Calika, N.N., Chua, D., Kanaan, O. and Zavadjil, M. (1998) The economy of the west bank and Gaza Strip: recent experience, perspectives, and challenges to private sector development. The Journal of Monetary Fund, Middle East Department.
5.Berkovec, J. and Rust, J. (1985) A Nested Logit Model of Automobile Holdings for One Vehicle, Households. Transportation Research, 19B, 4, 275-285.
6.Box, G.E.P. and Jenkins G.M. (1976) Time Series Analysis : Forecasting and Control. San Francisco : Holden-Day.
7.Box, D. and Pierce, A. (1970) Distribution of residual autocorrelations in auto regressive integrated moving average time series models. Journal of American Statistical Association, 65, 1509-1526.
8.Brännlund R., Ghalwash, T. and Nordström, J. (2007) Increased energy efficiency and the rebound effect: effects on consumption and emissions. Energy Economics, 29, 1-17.
9.Carlson, R. L. and Umble, M. M. (1980) Statistical demand functions for automobiles and their use for forecasting in an energy crisis. The Journal of business, 53, 2, 193-204.
10.Chen, Y.J. (2001) Modeling the Impacts of Vacancy Taxes on the Taiwan Housing Market. Proceedings of the National Science Council, Republic of China Part C: Humanities and Social Sciences, 11, 2, 148-155.
11.Chin, A. and Smith, P. (1997) Automobile Ownership and Government Policy: The Economics of Singapore’s Vehicle Quota Scheme. Transportation Research Part: A, 31, 129-140.
12.Chow, G.C. (1957) Demand for Automobiles in the United States. North Holland Publishing Company, Amsterdam.
13.Chow, G.C. (1960) Statistical demand functions for automobiles and their use for forecasting. In Arnold C. Harberger (ed.), The Demand for Durable Goods (Chicago: University of Chicago Press), 149-178.
14.Dargay, J. and Gately, D. (1999) Income’s effect on car and vehicle ownership: worldwide: 1960-2015. Transportation Research Part A, 33, 101-138.
15.Dargay, J. (2001) The Effect of Income on Car Ownership Evidence of Asymmetry. Transportation Research Part: A, 35, 807-821.
16.Darrat, A.F. (1987) Are exports an engine of growth? Another look at the evidence. Applied Economics, 19, 277-283.
17.De Jong, G.C. (1996) A disaggregate model system of vehicle holding duration, type choice and use. Transportation Research, 30B, 263-276.
18.Dickey, D.A. and Fuller, W.A. (1979) Distribution of the Estimators for Autoregressive Time Series with a Unit Root. Journal of American Statistical Association 74, 427-431.
19.Dickey, D.A. and Fuller, W.A. (1981) The likelihood ration statistics for autoregressive time series with a unit root. Econometrica, 59, 1057-1072.
20.Diebold, F.X. and Rudebusch, G. (1991) On the Power of Dickey-Fuller Tests Against Fractional Alternatives. Economics Letters, 35, 155-160.
21.Dyckman, T. R. (1966) An aggregate-demand model for automobiles, Journal of business, 38, 252-165.
22.Engle, R.F. and Granger, C.W.J. (1987) Cointegration and error-correction: representation, estimation, and testing. Econometrica, 55, 251-276.
23.Fowkes, A.S. and Button, K.J. (1997) An Evaluation of Car Ownership Forecasting Techniques. International Journal of Transport Economics, 4, 115-143.
24.Franses, P.H. (1991) Primary Demand for Beer in the Netherlands: An Application of ARMAX Model. Journal of Marketing Research, 28(2), 240-245.
25.Ghartey, E.E. (1993) Causal relationship between exports and economic growth: some empirical evidences in Taiwan, Japan and the US. Applied Economics, 25, 1145-1152.
26.Golob, T.F., Bunch, D. S. and Brownstone, D. (1997) A Vehicle Forecasting Model Based on Revealed and Stated Vehicle Type Choice and Utilisation Data. Journal of Transport Economics, 31, 69-92.
27.Granger, C.W.J. and Newbold, P. (1974) Spurious Regressions in Econometrics. Journal of Econometrica, 2, 111-120.
28.Granger, C.W.J. (1969) Investigating causal relations by econometric models and cross-spectral methods. Economics, 37, 424-438.
29.Granger, C.W.J. (1988) Some recent development in a concept of causality. Journal of Econometrics, 39, 199-211.
30.Greene, D. L. and Hu, P. S. (1984) The influence of the price of gasoline on vehicle use in multi-vehicle household. Transportation Research Record, 988, 19-24.
31.Greene, W. H. (2003) Econometric Analysis, 5th edition, Prentice Hall.
32.Hamilton, J.D. (1994) Time Series Analysis, Princeton University Press.
33.Hannan, E.J. (1980) The estimation of the order of an ARMA process. Annals of Statistics, 8, 1071-1081.
34.Harvey, A.C. (1990) The econometric analysis of time-series. Cambridge, MA: MIT Press.
35.Hassler, U. and Wolter, J., (1994) On the Power of Unit Root Tests Against Fractional Alternatives. Economics Letters, 45, pp. 1-5.
36.Jansson, J.O. (1989) Car demand modeling and forecasting: A new approach. Journal of Transport Economics and Policy, 125-139.
37.Johansen, S. (1991) Estimation and hypothesis testing of cointegration vectors in Gaussian vector autoregressive models. Econometrica, 59, 1551-1580.
38.Johansen, S. (1988) Statistical analysis of cointegration vectors. Journal of Economic Dynamics and Control, 12, 231-254.
39.Jung, W.S. and Marshall, P.J. (1985) Exports, growth and causality in developing countries. Journal of Development Economics, 1-12.
40.Kayser, H.A. (2000) Gasoline demand and car choice: estimating gasoline demand using household information. Energy Economics, 22, 331-348.
41.Kishi, L. and Satoh, K. (2005) Evaluation of willingness to buy a low-pollution car in Japan. Journal of the Eastern Asia Society for Transportation Studies, 6, 3121-3134.
42.Kwiatkowski, D., Phillips, P.C.B., Schmidt, P., and Shin, Y., (1992), Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series have a unit root?. Journal of Econometrics 54, pp. 159-178.
43.Lee, D. and Schmidt, P. (1996) On the power of the KPSS test of stationarity against fractionally integrated alternatives. Journal of Econometrics, 73, 285-302.
44.Lewis, C.D. (1982) Industrial and business forecasting methods: A Radical guide to exponential smoothing and curve fitting. London; Boston: Butterworth Scientific.
45.Ljung, G.M. and Box, G.E.P. (1978) On a measure of lack of fit in time series models. Biometrica, 65, 297-303.
46.Litman, T. (2000) The costs of automobile dependency and benefits of transport diversity. VTPI.
47.Mannering, F. (1983) An econometric analysis of vehicle use in multi-vehicle household. Transportation Research, 17A, 3, 183-189.
48.Mannering, F. (1998) Modeling driver decision-making: a review of methodological alternatives. In: Barfield, W. and Dingus, T. (Eds.), Human Factors in Intelligent Transportation systems, Lawrence Erlbaum, Mahwah, NJ.
49.Martin, C.A and Witt, S.F. (1989) Accuracy of econometric forecasts of tourism. Annals of Tourism Research, 16, 3, 407-430.
50.Nerlove, M. (1957) A note on long-run automobile demand. Journal of Marketing, 22, 1, 57-64.
51.Newman, P. and Kenworthy, J. (1999) Sustainability and cities– overcoming automobile dependency. Island Press, Washington, DC.
52.Park, J.H. and Prime, P.B. (1997) Export performance and growth in China: a cross-provincial analysis. Applied Economics, 29, 1353-1363.
53.Phillips, P. and Perron P. (1988) Testing for a unit root in time series regression. Biometrica 75, 335-346.
54.Ralph, G. (1999) Urban mobility in the developing world, Transportation Research Part A. 33, 671-689.
55.Romilly, P., Song, H. and Liu, X. (1998) Modelling and forecasting car ownership in Britain. Transport Economics and Policy, 32, 2, 165-185.
56.Rudebusch, G. (1993) The uncertain unit root in real GDP. American Economic Review, 83,264-271.
57.Said, S. and Dickey, D. (1984) Testing for Unit Roots in Autoregressive-Moving Average Model of Unknown Order. Biometrica, 71, 599-607.
58.Sims, C.A. (1980) Macroeconomics and reality. Econometrica, 48, 1, 1-48.
59.Sowell, F. (1990) Maximum likelihood estimation of stationary univariate fractionally Integrated time series models. Journal of Econometrics, 53, 165-188.
60.Tanner, C. F. (1978) Long term forecasting of vehicle ownership and road traffic. Journal of the Royal Statistical Society, 141A, 14-63.
61.Train, K. (1986) Qualitative choice analysis: theory, econometrics and an application to automobile demand. Cambridge, M.I.T. Press.
62.Vasconcellos, E.A. (1997) The demand for cars in developing countries. Transportation Research part A, 31, 3, 245-258.
63.Wong, K.D.F. (1997) The relevance of business cycles in forecasting international tourist arrivals. Tourism Management, 18, 8, 581-586.
64.Yang, Z. and Feng, T. (2005) Maximizing car ownership under constraints of environment sustainability in a city. Journal of the Eastern Asia Society for Transportation Studies, 6, 3077-3089.
65.李治綱、蕭銘雄、嵇允嬋(1992)，“機動車輛持有之時間序列模式”，《運輸計劃季刊》，21，1，1-22。
66.周榮昌、翁美娟 ( 2001 )，“家戶小客車持有與使用模式之建立”，《運輸學刊》， 13: 3，99-120。
67.周榮昌、陳志成 ( 2003 )，“台中市家戶機動車輛需求模式之研究─間斷性╱連續性混合模式之應用”，《運輸計劃季刊》，32: 2，319-340。
68.周榮昌、劉佑興與王薇晴 ( 2004a )，“家戶機動車輛持有狀態與使用需求模式之研究”，《運輸計劃季刊》，33: 1，83-114。
69.周榮昌、陳志成與翁美娟 ( 2004b )，“台灣地區家戶汽機車相互持有與使用間的關係-Ordered Bivariate Probit與SURE模式之應用”，《運輸計劃季刊》，33: 4，625-648。
70.周鳳瑛、劉曦敏、柏雲昌 ( 1998 )，“經濟衝擊對長期能源需求的影響-政策模擬之研究”，《經濟研究》，32:2，139-162。
71.姜渝生、廖仁哲(1998)，“家戶同一效用最大化之小汽車持有與使用、工作運具混合需求模型之研究－臺灣地區之實證研究”，《運輸計畫季刊》，27，4，543-582。
72.姜渝生、賴文泰、王小娥(1999)，“通勤距離與小客車持有混合需求模式之研究”， 《運輸學刊》，11 ，3。
73.張新立 (2003)，《環境變遷下家戶持有汽機車決策歷程之研究》，行政院國家科學委員會NSC92-2211-E009-051。
74.徐之強 (2001)，“多次結構變動下趨勢穩定與差分穩定之認定-台灣總體資料實證研究”，《經濟論文》，29，3，321-339。
75.黃台心 (2002)，“出口與經濟成長的因果關係:台灣的實證研究”，《經濟論文叢刊》，3，4。
76.黃書禮、劉錦添、駱尚廉、李玲玲、王俊秀、蔡慧敏、施文真 (2003)，「建立永續臺灣評量指標系統實際應用之研究」，《全球變遷通訊雜誌》，38，1-10。
77.葉國宏 (1996)，《小客車成長預測之研究》，碩士論文，國立交通大學交通運輸工程研究所。
78.蔡佳佳 (2005)，《機車持有預測模式之研究》，碩士論文，臺灣大學土木工程學研究所。
79.賴文泰 (1999)，《家戶通勤行為、小客車持有與使用混合需求模型之研究》，博士論文，國立成功大學交通管理科學研究所。
80.賴文泰、呂錦隆、姜渝生 (2006)，“臺灣地區多車輛家戶小客車、機車持有與使用實證模型之研究”，《運輸計劃季刊》，35: 3，309-336。