很多相關文獻指出股票市場報酬為非線性，而非線性的原因是因為股票市場存在波動不對稱的現象。因此若要探討股票與總體變數之間的影響，就要以非線性的模型去分析，否則會發生模型設定之問題。而在這我採用門檻自我迴歸(Threshold Autoregression)去分析ETF報酬與匯率跟經濟成長之間的關係。本研究以ETF報酬率為門檻變數。首先，先以線性檢定裡的重新安排迴歸(Arrang Regression)跟F統計量檢測是否有非線性效果，再以格點搜尋的方式尋找殘差平方和最小，決定最適的門檻落後期和門檻值。找出門檻值後，估計一個兩狀態模型，分析在正負報酬下，匯率與ETF報酬之間的相關性是否可以用外溢效果去解釋，而經濟成長對於ETF報酬又是如何影響，接著，將資料繪製成格點圖，尋找可能的結構轉變點個數，最後再根據Tsay提供的AIC公式，計算兩狀態跟三狀態模型AIC的值，數值最小的就是本研究最適的模型。

A lot of relevant literature indicates that stock market returns for the non-linear because the stock market is volatility asymmetry. To explore the impact between the stock and macroeconomic variables, it is necessary to analyze by nonlinear model, otherwise they will be a model set of problems. I adopt a threshold autoregressive modle to analyze the relationship between the ETF return on the exchange rate and economic growth. In this study, the ETF return is the threshold variable. First, in order to rearrange the linear test regression (Arrang Regression) with the F-statistic testing whether the nonlinear effect of the grid search to find the residual sum of squares, determine the optimal threshold of backward and thresholds value. To identify the threshold, it is estimated a two-regime model analysis in positive and negative reward, the correlation between exchange rate and ETF returns Spillover effect to explain economic growth for the ETF returns and how it affects, then the data drawn into a grid map, find the number of possible structural transition point, and finally AIC formula to calculate the value of the two -regime with the three-regime model of AIC and the minimum value is the optimal model.

論文審定書…………………………………………………………….……………………………………………i
謝詞……………………………………………………………………………………………………………………. ii
中文摘要………………………………………………………….………………………………………………….iii
Abstract………………………………………..…………………………………………………………………… iv
第一章 緒論……………………....................................................................................1
第一節 研究動機與目的……....................................................................................1
第二節 論文架構與流程.........................................................................................2
第二章 文獻回顧...................................................................................................3
第三章 研究方法...................................................................................................7
第一節 單根檢定.....................................................................................................7
第二節 最適落後其決定.........................................................................................9
第三節 門檻自我迴歸模型...................................................................................10
第四章 實證結果與分析.....................................................................................15
第一節 資料來源與定義.......................................................................................15
第二節 單根檢定結果...........................................................................................16
第三節 最適落後期選取.......................................................................................17
第四節 線性檢定與估計.......................................................................................18
第五章 結論與建議.............................................................................................26
參考文獻..............................................................................................................27

中文部分:
1.陳仕偉、陳俊偉(2006)，「台灣股票及外匯市場價量非線性因果關係之探討」，經濟與管理論叢，第二卷第一期，頁21-51。
2.吳宗隆、徐清俊(2003)，「台股市場與外匯市場報酬與波動關聯性研究－雙變量GJR-GARCH(1,1)-M模型之應用」，遠東學報，第二十卷第四期，頁799-816。
3.洪萬吉、陳進士、王天福(2007)，「匯率波動對台灣股票市場報酬不對稱性之研究：雙門檻-GARCH 模型之應用」，美和技術學院學報 第二十六卷第一期。
4.謝文馨 (2008)，「總體經濟變數與股價指數之關聯性研究─以台灣為例」，國立成功大學企業管理學系碩士論文。
5.翁小蘅 (2009)，「新臺幣匯率、利率與股價報酬率關聯性之研究」，國立臺北大學國際財務金融系碩士論文。
6. 王冠閔、黃柏農(2004)，「台灣股匯市與美國股市關聯性探討」，台灣經濟預測與政策，第34 卷，第2 期，頁31-72。
7. 李源明 (2006)，「股價報酬(波動)與產出成長(波動)之間關係的探討」，國立中正大學國際經濟研究所博士論文
英文部分:
1. Black, F. (1986). “Noise”. Journal of Finance ,41,p. 529-543
2. Craig Hiemstra and Jonathan D.Jones(1994), “Testing for Linear and
Nonlinear Granger Causality in the Stock Price-Volume Relation” ,The Journal
of Finance , pp.1639-1664
3. Christopher Gan, Minsoo Lee, Hua Hwa Au Yong, Jun Zhang, (2006), " Macroeconomic Variables and Stock Market Interactions: NEW ZEALAND Evidence" Investment Management and Financial Innovations, Volume 3, Issue 4,
- 28 -
2006.
4. Cheung, Y. W. and L. K. Ng (1992), “Stock Price Dynamics and Firm Size: An Empirical Investigation, ” Journal of Finance, 47,p. 1985-1997.
5. David G McMillan(2002), “Non-Linear Predictability of UK Stock Market Returns, ” Oxford Bulletin of Economics and Statistics, 2003.
6. D Domian, D Louton(1997), “A threshold autoregresive analysis of stock returns and real economic activity” International Review of Economics and Finance, 6, p. 167–179
7. De Bondt and Thaler(1985), “Does the stock market overreact? ” Journal of Finance ,40,p. 793–808
8. Hartmann, Daniel and Pierdzioch, Christian(2006), “Nonlinear Links between Stock Returns and Exchange Rate Movements,” Munich Personal RePEc Archive,p. 2918
9.Huang, B.N. and Yang, C.W. (2004), “Industrial Output and Stock Price Revisited：An Application of the Multivariate Indirect Causality Model,” The Manchester School,72, 347-362.
10.Jegadeesh, N., and S. Titman(1993), "Returns to buying winners and selling losers: Implications for stock market efficiency," Journal of Finance 48, 65-9 1.
11. Kenneth R. French, G. William Schwert, and Robert F. Stambaugh(1987),
- 29 -
“Expected stock returns and volatility, ” Journal of financial Economics
12.Kanas Angelos, 2000, “Volatility Spillovers between Stock Returns and Exchange Rate Changes: International Evidence”, Journal of Business Finance & Accounting ,27, p.447-468.
13.Sims, Christopher A. (1980). “Macroeconomics and Reality,” Econometrica. 48, pp. 1-48.
14. Sheng Guo and Umut Unal(2011) "VAR Estimates of the Housing and Stock Wealth Effects: Cross-country Evidence," Working Papers
15. Sarantis, N. (2001), “Nonlinearities, Cyclical Behavior and Predictability in Stock
Markets: International Evidence,” International Journal of Forecasting,17,p.459-482.
16. Tsay, R.S.(1989), “Testing and Modeling Threshold Autogressive Processes,” Journal of American Statistical Association, 84, p.231-40.
17. Tsay, R.S. (1998), “Testing and modelling multivariate threshold models,” Jouranl of the American Statistical Association, 93, p.1188-1202.
18. Wan Mahmood and Nazihah Mohd Dinniah(2009), “Stock Returns and Macroeconomic Influences: Evidence from the Six Asian-Pacific Countries,” Financial Economics and Futures Market Research Paper