臺灣博碩士論文加值系統

本文以Banerjee,Marcellino,and Masten (2014)擴充因子向量誤差修正模型(Factor-augmented Error Correction Model，FECM)為架構，探討台灣股價加權指數、匯率、利率、貨幣供給間的共整合關係。
FECM模型有許多優點，其解決了Sims (1980)提出的VAR模型 (Vector Autoregression model，VAR)、Engle and Granger (1987)提出的ECM模型 (Error Correction model，ECM) 無法容納過多變數的問題，及Bernanke, Boivin, and Eliasz (2004)的FAVAR模型 (Factor-Augmented Vector Autoregressive, FAVAR) 變數須為定態變數的條件導致變數間長、短期關係的損失，FECM模型利用因子萃取的方式納入眾多重要變數以增加資訊並且不需為定態變數的設定以保留長、短期關係。
本研究對資料期間為1996年1月至2015年12月共計240期月資料，主要變數為台灣加權股價指數、利率、匯率以及貨幣供給進行共整合檢定，發現變數間具有共整合關係並採用了FECM模型進行估計以及預測且給出了樣本內預測值，並在與ECM模型的比較圖中發現FECM模型較靠近實際值，且藉由評估預測力的三個指標發現FECM模型樣本內預測較ECM模型準確，最後給出了樣本外預測值做預期的參考。

This thesis adopts FECM(Factor-augemented Error Correction Model), which was provided by Banerjee and Marcellino in 2014, as framework, and inquires into the Cointegrations in TAIEX, exchange rate, interest rate, and money supply.
FECM has many merits; for example, it solves the problem that VAR and ECM do not accommodate a large set of variables; FAVAR incorporates loss in long and short run relation on the condition of stationary variables, but FECM uses another way to extract factors to accommodate many significant variables, adding information, but not to maintain long and short run relations due to stationary variables.
This thesis uses data during the time from January of 1996 to December of 2015, and it would integrate the main variables, such as TAIEX, exchange rate, interest rate, and money supply. Based on my study, I find there is relationship of integration between variables. Secondly, I will adopt FECM to provide assessment and predictions in and outside the specimens. I maintain that FECM is closer to actual value in the chart of comparison with ECM, and that the specimens in FECM are more accurate than the ones in ECM according to the assessment at the three indexes of power of prediction. In the final section, I provide the predictive value outside the specimens as references of anticipations.

目錄
審定書................................................................................................. i
誌謝..................................................................................................... ii
摘要..................................................................................................... iii
Abstract .............................................................................................. iv
1 緒論..................................................................................................... 1
1.1 研究動機............................................................................... 1
1.2 研究目的............................................................................... 1
1.3 研究架構............................................................................... 2
2 文獻回顧.............................................................................................. 3
2.1 國外股價指數預測相關文獻.................................................. 3
2.2 國內股價指數預測相關文獻.................................................. 3
3 研究方法.............................................................................................. 5
3.1單根檢定š............................................................................... 5
3.2 共整合.................................................................................. 6
3.2.1共整合關係 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3.2.2 Johanson 共整合檢定š . . . . . . . . . . . . . . . . . . . 7
3.3 最適落後期數的選取:............................................................ 9
3.4 因子擴充誤差修正模型‹(FECM) ........................................... 10
3.5因子萃取法........................................................................... 12
3.6 預測能力評估....................................................................... 13
3.6.1 預測力指標› . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.6.2 Diebold-Mariano Test . . . . . . . . . . . . . . . . . . . . 14
4 實證研究............................................................................................. 15
4.1 資料處理 ............................................................................... 15
4.1.1資料來源與選取 . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.1.2因子萃取及萃取因子個數選取 . . . . . . . . .. . . . . 15
4.2 共整合 ................................................................................... 15
4.2.1 落後期數的選擇 . . . . . . . . . . . . . . . . . . . . .. . . . 15
4.2.2 共整合檢定. . . . . . . . . . . . . . . . . . . . . . .. . . . . . 16
4.3 FECM模型估計 ...................................................................... 17
4.4 預測....................................................................................... 19
4.4.1 台灣加權股價指數,樣本內預測 . . . . . . . . . . . . . . . . 19
4.4.2 台灣美元兌新台幣匯率,樣本內預測 . . . . . . . . . . . . 20
4.4.3 台灣隔夜拆款利率,樣本內預測 . . . . . . . . . . . . . . . . 21
4.4.4 貨幣供給,樣本內預測 . . . .... . . . . . . . . . . . . . . . . . 22
4.4.5 樣本內預測準確率評估與比較 . . .. . . . . . . . . . . . . . 23
4.4.6 樣本外預測 . . . . . . . . .. . . . . . . . ...... . . . . . . . . . . . 24
5 結論..................................................................................................... 27
參考文獻............................................................................................. 29
附錄..................................................................................................... 32

參考文獻
中文部分
1. 李慶男 (2006)，「時間序列講義」，chapter 21-24，國立中山大學經濟學研究所。
2. 陳旭昇 (2013)，「時間序列分析:總體經濟與財務金融之應用」，二版 東華書局。
3. 楊奕農 (2009)，「時間序列分析:經濟與財務上之應用」，二版 雙葉書局。
4. 李偉銘、吳淑貞 (2015)，「總體經濟變數對臺灣股市之大盤及類股熊市預測表現之探討」，《經濟研究》，51:2，頁171-224。
5. 劉祥熹、涂登才(2012)，「美國股市及其總體經濟變數間關連性與波動性之研究─ VEC GJR DCC-GARCH-M 之模型應用」，《經濟研究》，48:1，頁139-189。
6. 王怡文 (2010)，「總體經濟指標對股市及共同基金相關性之研究-以台灣股市為例」，碩士論文，國立高雄應用科技大學商務經營研究所。
7. 劉欣姿 (2012)，「領先之標預測能力之研究」，《國家發展委員會經濟研究年刊期刊論文》，第13 期，行政院經建會。
8. 高崇傑 (2000)，「台灣股價與景氣循環關係之研究」，碩士論文，國立政治大學財政研究所。
英文部分
1. Abdullah, D. A., & Hayworth, S. C. (1993). Macroeconometrics of stock price uctuations. Quarterly Journal of Business and Economics, 50-67.
2. Bai, J., & Ng, S. (2002). Determining the number of factors in approximate factor models.Econometrica, 70 (1), 191-221.
3. Bai, J., & Ng, S. (2004). A panic attack on unit roots and cointegration. Econometrica,72 (4), 1127-1177.
4. Banerjee, A., Marcellino, M., & Masten, I. (2014). Forecasting with factoraugmented error correction models. International Journal of Forecasting,30 (3),589-612
5. Bernanke, B. S., Boivin, J., & Eliasz, P. (2004). Measuring the effects of monetary
policy: a factor-augmented vector autoregressive (favar) approach(Tech.Rep.). National Bureau of Economic Research.
6. Engle, R. F., & Granger, C. W. (1987). Co-integration and error correction: representation,estimation, and testing. Econometrica: Journal of the EconometricSociety, 251-276.
7. Granger, C. W., & Newbold, P. (1974). Spurious regressions in econometrics.Journal of Econometrics, 2 (2), 111-120.
8. Hjalmarsson, E. (2010). Predicting global stock returns. Journal of Financial and Quantitative Analysis, 45 (1), 49-80.
9. Johansen, S. (1988). Statistical analysis of cointegration vectors. Journal of Economic Dynamics and Control , 12 (2), 231-254.
10. Kim, K.-h. (2003). Dollar exchange rate and stock price: evidence from multivariate
cointegration and error correction model. Review of Financial Economics,12 (3), 301-313.
11. Lee, U. (1994). The impact of financial deregulation on the relationship between
stock prices and monetary policy. Quarterly Journal of Business and Economics,37-50.
12. Mookerjee, R., & Yu, Q. (1997). Macroeconomic variables and stock prices in a
small open economy: The case of singapore. Pacific-Basin Finance Journal,5(3), 377-388.
13. Rapach, D. E. (2001). Macro shocks and real stock prices. Journal of Economics
and Business, 53 (1), 5-26.
14. Said, S. E., & Dickey, D. A. (1984). Testing for unit roots in autoregressivemoving
average models of unknown order. Biometrika, 71 (3), 599-607.
15. Sims, C. A. (1980). Macroeconomics and reality. Econometrica: Journal of the Econometric Society, 1-48.
16. Stock, J. H., & Watson, M. W. (2002). Forecasting using principal components from a large number of predictors.Journal of the American Statistical Association,97 (460), 1167-1179.