臺灣博碩士論文加值系統

台灣為一對外貿易依存度很高的小型開放經濟體系，實質有效匯率除了能夠明確表達一國貨幣在匯率上相對於其他主要貿易往來國家的變動程度，更能夠看出該國在國際中是否具有競爭力的指標。本研究分兩個研究設計來探討，研究設計一，以歷史資料，針對台灣實質有效匯率進行預測；研究設計二，以經濟基本變數來作預測，藉由七個經濟基本變數：國內外相對生產力差異、國外淨資產比例、國內外相對貿易條件、政府消費比例、國內消費比例、國內外相對經濟開放程度、國際原油價格，來對台灣實質有效匯率進行預測。
近年來，被廣為研究與討論的類神經網路資訊處理系統，因其具有網路穩定性高、良好的錯誤容忍度、歸納推廣的能力以及非線性特質等優點，因此被廣泛應用在各個領域。而在財務金融方面，以類神經網路為基礎的預測方法，已有許多成功案例。本文將以倒傳遞類神經的五種演算法進行預測。
本文實證結果，以歷史資料來作預測時，倒傳遞類神經的LM演算法預測台灣實質有效匯率的方向預測正確性效果最佳，且樣本內為選取十二個月訓練期間，是對台灣實質有效匯率的預測能力為最佳的選取範圍。 以經濟基本變數來作預測，則是以倒傳遞類神經的共軛梯度演算法的預測能力最佳。各變數對台灣實質有效匯率間之重要性與相關程度最佳的為國際原油價格；重要性與相關程度最小的為國外淨資產比例。本研究希望藉由研究結果，作為投資者進行投資及企業從事貿易之參考，來減低因匯率波動所產生之風險。

Taiwan is a small open economy with a high dependence on trade. The real effective exchange rate is able to express the degree of fluctuation in the exchange rate relative to the other major trade countries, and more can be seen in the country whether in international competitiveness indicators. The study consists of two studies designed to investigate, study design one to historical data for forecasting Taiwan''s real effective exchange rate; study design two to basic economic variables to make predictions, with seven basic economic variables: relative productivity differences, net foreign assets, the relative domestic trade, government consumption, domestic consumption, domestic relative degree of economic openness, international crude oil prices, to predict the real effective exchange rate in Taiwan. In this study, we use five algorithms of backpropagation nerual network to predict real effective exchange rate.

Recently, neural networks are a field of research which has enjoyed a rapid expansion and great popularity in both the academic and industrial research communities. Form the statistician’s point of view they are analogous to nonparametric, nonlinear regression models. This is particularly useful in financial engineering applications, where much is assumed and little is known about the nature of the processes determining asset prices.

The empirical result, use historical data to predict real effective exchange rate in Taiwan, the Levenberg-Marquardt algorithms of backpropagation neural network is best approach for Directional Change and twelve months is the best training rang. Use basic economic variables to predict real effective exchange rate in Taiwan, the conjugate gradient algorithm of backpropagation neural network is best approach. Importance and relevance of the best is the international crude oil prices; importance and relevance of the smallest is the net foreign assets. This research work supposes that the result of empirical analysis can be regard as a refrence for investing and trading in order to eliminate risks resulting form fluctuated exchange rate.

中文摘要 ………………………………………………………… i
英文摘要 ………………………………………………………… ii
誌謝 ………………………………………………………… iv
目錄 ………………………………………………………… v
表目錄 ………………………………………………………… vii
圖目錄 ………………………………………………………… viii
第一章 緒論…………………………………………………… 1
1.1 研究動機與背景……………………………………… 1
1.2 研究目的……………………………………………… 3
1.3 研究架構……………………………………………… 4
第二章 文獻探討……………………………………………… 5
2.1 實質有效匯率相關文獻……………………………… 5
2.2 實質有效匯率影響因子相關文獻…………………… 7
2.3 類神經網路相關文獻………………………………… 9
第三章 研究內容與方法……………………………………… 11
3.1 變數衡量方式與計算方法…………………………… 11
3.2 類神經網路介紹（Neural Network，NN）………… 15
3.2.1 類神經網路之基本架構……………………………… 15
3.2.2 類神經網路基本數學模式…………………………… 15
3.2.3 類神經網路之類別…………………………………… 16
3.3 倒傳遞類神經網路（Back- Propagation Network，BPN)之介紹…………………………….……………………………… 18
3.3.1 倒傳遞網路之基本架構……………………………… 18
3.3.2 倒傳遞網路訓練演算法……………………………… 20
3.3.3 評估方法……………………………………………… 24
3.4 資料來源與研究設計………………………………… 26
3.4.1 資料來源……………………………………………… 26
3.4.2 研究設計一…………………………………………… 30
3.4.3 研究設計二…………………………………………… 33
第四章 實驗結果……………………………………………… 36
4.1 研究設計一…………………………………………… 36
4.1.1 五種倒傳遞類神經演算法的預測效果……………… 37
4.1.2 不同樣本內訓練時間之預測結果…………………… 40
4.2 研究設計二…………………………………………… 42
4.2.1 VIF 多元共線性診斷………………………………… 42
4.2.2 網路模型的分析結果………………………………… 44
4.2.3 各變數預測能力結果分析…………………………… 45
第五章 結論與建議…………………………………………… 49
5.1 研究結論……………………………………………… 49
5.2 研究建議……………………………………………… 51
參考文獻 ………………………………………………………… 52
附錄一 ………………………………………………………… 56
英文論文大綱 ………………………………………………………… 57
簡歷 ………………………………………………………… 62

[1]陳昭南，1973，“國際貨幣制度的癥結與改革”，經濟論文，1，頁183-202。
[2]曹添旺、賴景昌、鍾俊文，郭炳伸與蔡文禎，2002，“新台幣實質有效匯率之動態分析”，台灣經濟預測與政策，32，頁93-130。
[3]吳中書，1999，“台幣匯率與資本移動關連性之探討”，中央銀行季刊，21卷，2期，頁48-63。
[4]方文碩、吳政勳、方以唐，2002，“實質有效匯率探討”，貨幣市場，6卷，5期，頁1-20。
[5]陳佩玗、田慧琦，2012，“影響中長期新台幣實質有效匯率因素的探討”，中央銀行季刊，34卷，2期，頁43-83.
[6]葉怡成，2001，應用類神經網路，儒林書局，臺北市。
[7]羅華強，2005，類神經網路；MATLAB的應用，高立圖書有限公司，臺北縣。
[8]鐘明宏，2001，“實質匯率非線性調整之實證研究”，國立中正大學國際經濟研究所碩士論文。
[9]王欣容，2006，“實質有效匯率之非線性模型研究-新台幣、人民幣及日圓模型之建立”，朝陽科技大學財務金融系碩士論文。
[10]廖元宏，2002，“以STAR模型研究新台幣實質有效匯率”，國立中山大學財務管理研究所碩士論文。
[11]林芙歆，2009，“以非線性STAR-GARCH模型預測實質有效匯率指數”，國立台北商業技術學院財務金融研究所碩士學位論文。
[12]萬怡如，2012，“實質匯率預測力-以台灣為例”，國立中正大學國際經濟學博士學位論文。
[13]施向陽，2001，“匯率變動預測模式之研究”，私立大葉大學事業經營研究所碩士論文。
[14]邱至中，2003，“長短期匯率預測模式績效之比較”，國立成功大學財務金融研究所，碩士論文。
[15]柏婉貞，2010，“油價可以解釋實質匯率走勢嗎？亞洲新興國家之驗證”，東吳經紀商學學報，69期，頁29-46，6月。
[16]呂佳芹，2009，“應用時間序列、演化式類神經網路與灰預測方法在匯率預測績效之比較”，朝陽科技大學財務金融系碩士論文。
[17]Bayoumi, T., J. Lee and S. Jayanthi, 2005, “New Rates from New Weights,” IMF Working Paper, No. WP/05/99.
[18]Candelon B., C. Kool, Raae, and T. Veen, 2007, “Long-Run Real Exchange Rate Determinants: Evidence form Eight New EU Member States, 1993-2003,” Journal of Comparative Economics, 35, 1, pp. 87-107.
[19]Cheung Y., M.D. Chinn and E. Fujii, 2007, “The Overvaluation of Renminbi Undervaluation,” Journal of International Money and Finance, 26, 5, pp. 762-785.
[20]Chen, S. S. and H. C. Chen, 2007, “Oil prices and real exchange rates.” Energy Economics, 29, pp. 390-404.
[21]Clark, P.B. and R. MacDonald, “Exchange Rates and Economic Fundamentals: A Methodological Comparison of BEERs and FEERs,” in MacDonald, R. and J. Stein (ed.), Equilibrium Exchange Rates, Amsterdam: Kluwer, 1999.
[22]DeCoster, G. P. and D. W. Mitchell, 1991, “Nonlinear Monetary Dynamics,” Journal of Business and Economic Statistics, 9, pp. 455-461.
[23]Dornbusch and Rudiger, 1976, “Expectations and exchange rate dynamics”, Journal of Political Economy, 84, pp. 1161-76.
[24]Engel, C., N.C. Mark and K.D. West, 2007, “Exchange Rate Models Are Not as Bad as You Think,” 8th Jacques Polak Annual Research Conference, the International Monetary Fund, Washington, DC, Nov. 15-16, 2007.
[25]Frankel, Jeffrey, 1979, “On the mark: A theory of floating exchange rates based on real interest differentials”, American Economic Review, 69 (Sep- tember): 610-22.
[26]Jongwanich, J., 2009, “Equilibrium Real Exchange Rate, Misalignment, and Export erformance in Developing Asia,” ADB Economics Working Paper Series, No. 151, Asian Development Bank, Manila, Philippines.
[27]Kinkyo, T., 2008, “Disorderly Adjustments to the Misalignments in the Korean Won,” Cambridge Journal of Economics, 32, 1, pp. 111-124.
[28]Kilian, L., Taylor, M.P., 2003, “Why Is It So Difficult to Beat the Random Walk Forecast of Exchange Rates?” Journal of International Economics, 60, 1, pp. 85-107.
[29]Kimoto, T., Asakawa, K., Yoda, M., and Takeoka, M., 1990, “Stock market prediction system with modular neural network”, Proceedings of the International Joint Conference on Neural Networks (IJCNN1990), 1, San Diego, USA, 1-6.
[30]Leung, F. and P. Ng, 2007, “Is the Hong Kong Dollar Real Exchange Rate Misaligned?” HKMA Working Paper No. 21/2007, Hong Kong Monetary Authority, Hong Kong, China.
[31]Leung, M. T., Chen, A. S., and Daouk H., 2000, “Forecasting exchange rates using general regression neural networks”, Computers and Operations research, 27, pp.1093-1110.
[32]MacDonald, R., 2001, “Modelling the Long-Run Real Effective Exchange Rate of the New Zealand Dollar,” Reserve Bank of New Zealand, Discussion Paper No. DP2002/02.
[33]MacDonald, R., 2004, “The Long-Run Real Effective Exchange Rate of Singapore: A Behavioural Approach,” MAS Staff Paper, No. 36.
[34]Maeso-Fernandez, F., C. Osbat, and B. Schnatz, 2001, “Determinants of the Euro Real Effective Exchange Rate: A BEER/PEER Approach,” ECB Working Paper, No. 85.
[35]Mark, N.C., 1995, “ Exchange Rates and Fundamentals : Evidence on Long-horizon Predictability,” American Economic Review, 85, 1, pp. 201-218.
[36]Meese, R.A. and Rogoff, K., 1983, “Empirical Exchange Rate Models of the Seventies : Do They Fit Out-of-Sampl?”, Journal of International Economics, 14 ,1-2, pp. 3-24.
[37]Michael, P., Nobay, A. R. and Peel, D. A., 1997, “Transactions costs and nonlinear adjustment in real exchange rates: and empirical investigation,” The Journal of Political Economy, 105, pp. 862-879.
[38]Rauscher, F. A., 1997, Exchange rate forecasting: a neural VEC approach ti non-linear time series analysis, Journal of Time Series Analysis, 9, pp. 461-471.
[39]Rhomberg, R. R., 1976, “Indices of Effective Exchange Rates.” IMF Staff Papers, 23, 1, pp. 88-122.
[40]Rumelhart, D. E., Hinton, G. E. and Williams, R. J. in Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1: Foundations (eds Rumelhart, D. E. & McClelland, J. L.) 318−362 (MIT, Cambridge, 1986).
[41]Sarantis, N., 1999, “Modeling non-linearities in real effective exchange rates,” Journal of International Money and Finance, 18, 1, pp.27-45.
[42]Song, O. and V.L.C. Seng, 2002, “Determination of Equilibrium Real Exchange Rate in Selected SEACEN Countries,” The South East Asian Central Banks (SEACEN) Staff Paper, No. 66.
[43]Taylor, M. and Peel, D. A., 2000, “Nonlinear adjustment, long-run equilibrium and exchange rate fundamentals,” Journal of International Money and Finance, 19, pp.33-53.
[44]Jongwanich, J., 2009, “Equilibrium Real Exchange Rate, Misalignment, and Export Performance in Developing Asia,” ADB Economics Working Paper Series, 151, Asian Development Bank, Manila, Philippines.
[45]Verkooijen, W., 1996. “A neural network approach to long-run exchange rate prediction”, Computational Economics, 9, pp.51-65.
[46]Villavicencio, A.L., 2008, “Nonlinearities or Outliers in Real Exchange Rate,” Economic Modelling, 25, 4, pp. 714-730.
[47]Yan, H. and C. Yang, 2010, “Undervalued Currency and Economic Growth: the Case of Taiwan,” 2nd Conference of the European Asian Economics, Finance &Accounting and Econometric Association, Beijing, Park Plaza Science Beijing Hotel, September.