本文以台灣五十成分股為研究標的，從作多角度進行相對強弱指標(RSI)策略之回測。研究期間設定為2007/8/27至2015/2/4，資料頻率以日為單位，藉子期間的選擇去除趨勢後，探討下列策略於台灣五十成分股之績效。
一、 上界(超買)＝80、下界(超賣)＝20
以每日收盤價計算而成之6日RSI突破產生進出場訊號。
二、 上界(超買)＝80、下界(超賣)＝20
以每日收盤價計算而成之12日RSI突破產生進出場訊號。
三、 當6日RSI由下往上突破12日RSI產生進場訊號。
當6日RSI由上往下突破12日RSI產生出場訊號。
上述三種策略進行敏感度分析挑出最佳策略，並觀察最佳策略下成分股報酬率與股價波動度是否存在關係。附錄揭露最佳策略下報酬率最佳的五檔個股及報酬率最差的五檔個股之報酬結構與股價走勢。本研究得到以下結論：
一、 原12日RSI策略績效較原6日RSI策略佳，經過參數調整後，本文定義的單線RSI策略對台灣五十成分股回測能獲得良好的績效，且具備統計上顯著。而雙線RSI交叉原策略表現不佳，成分股皆為負報酬，但加入上下界參數組合後，報酬率顯著提升且更穩定。以週資料或月資料為單位應能改善RSI過於敏感之特性。
二、 進出場條件越嚴格，報酬率普遍越高。經敏感度分析後，最佳策略為:上界＝90、下界＝10，以每日收盤價計算而成之6日RSI突破產生進出場訊號。
三、 在最佳策略下，成分股之報酬表現與股價波動度呈低度相關。以區間波動來看，績效最佳之五檔個股，股價波動度普遍偏高(僅一檔排名中位數之後)，績效最差之五檔個股，股價波動度普遍偏低(僅一檔排名中位數之前)。

This study backtest trading strategies about relative strength index (RSI) for constituent stocks in Taiwan top 50. The data period is from 2007/8/27 to 2015/2/4 with date frequency. We detrended the data by way of selecting sub period. We defined three strategies with different structure and executed sensitivity analysis to find the best strategy.
1. Upper boundary(Overbought) = 80 / Lower boundary(Oversold) = 20
Signal occurs when six-day RSI breakout the range.
2. Upper boundary(Overbought) = 80 / Lower boundary(Oversold) = 20
Signal occurs when twelve-day RSI breakout the range.
3. Buy signal occurs when six-day RSI breakout twelve-day RSI from downside.
Sell signal occurs when six-day RSI breakout twelve-day RSI from upside.
We selected the best strategy to check whether there exist a relationship between returns and volatility of prices. The appendix shows return patterns for five stocks with the highest total return and five stocks with the lowest total return. The empirical findings are summarized as follows:
1. Original twelve-day RSI strategy performed better than original six-day RSI strategy. After adjusting parameters of upper and lower boundary, the performance of simple RSI strategies we defined are good and statistically significant during the research period. The original double RSI crossover stragy have negative total return, but after adding boundary parameters, the total return increase significantly and be more stable. Using weekly or monthly data for unit should be able to modify the sensitive property of RSI.
2. The total return would usually be higher if the term of buy signal or sell signal was stricter. The best strategy we found is:
Upper boundary = 90 / Lower boundary = 10
Signal occurs when six-day RSI breakout the range.
3. There is a modest correlation between returns and volatility of prices under the best strategy.

一、 中文部分
1. 王端儀(2012) 投資組合的績效:以F_SCORE為衡量基準，國立高雄第一科技大學金融研究所碩士論文。
2. 牟聖遠(2013) 台灣股市技術分析實證─以KD指標、RSI指標、MACD指標、DMI指標為例，義守大學資訊管理研究所碩士論文。
3. 江俊良(2011) 移動平均法和相對強弱指標在台灣股市之投資績效，明志科技大學工業工程與管理研究所碩士論文。
4. 杜金龍(2008) 最新技術指標在台灣股市應用的訣竅，財訊出版。
5. 邱一平(2008) 技術分析首部曲，寰宇技術分析出版。
6. 林宗永(1989) 技術分析指標獲利性之實證研究，國立政治大學企業管理研究所碩士論文。
7. 周賓凰 池祥萱 周冠男 龔怡霖(2002) 行為財務學-文獻回顧與展望，證券市場發展季刊，Volume14，No.2：1-46.(TSSCI)。
8. 祖維龍(2011) 通道突破系統在台指期貨市場的實證研究，東海大學財務金融學系碩士在職專班論文。
9. 徐瑞隆(1989) 技術分析之收益性與市場之有效性之研究，國立成功大學工業管理研究所碩士論文。
10. 張哲維(2013) 「賺大賠小」傾向之探討─以台灣期貨之交易為例，國立臺灣科技大學財務金融研究所碩士論文。
11. 陳玟志(2013) RSI與威廉指標於台灣加權指數操作績效實證，天主教輔仁大學金融與國際企業學系金融碩士在職專班碩士論文。
12. 莊蕙謙(2005) 影響金融商品投資意願之研究-以定錨和私房錢效果為例，國立高雄第一科技大學金融營運所碩士論文。
13. 許仁安(2014) 法人買超股與技術指標操作之績效，國立中正大學財務金融研究所碩士論文。
14. 湯承庭(2012) 行為財務學處分效果與過度自信實證分析，國立政治大學金融研究所碩士論文。
15. 楊基鴻(2013) 股票操作大全，楊基鴻出版。
16. 蔡依玲(2001) 台灣股票市場報酬率之研究，國立成功大學統計學研究所碩士論文。
17. 賴裕盛(2008) 台指期貨籌碼分析與模組研究，國立政治大學經營管理碩士學程(EMBA)。
二、 英文部分
1. Alexander, S.S.(1961), “Price Movements in Speculative Markets: Trends or Random Walks.” Industrial Management Review, II No 2 May.
2. Aronson, David(2007), Evidence-Based Technical Analysis: Applying the Scientific Method and Statistical Inference to Trading Signals, Wiley Trading.
3. Bohan, J.(1981), “Relative strength: further positive evidence.” Journal of Portfolio Management ,Vol. 7, No. 3.
4. De Bondt, W. F. M. and R. H. Thaler.(1995), “Financial decision-making in markets and firms: A behavioral perspective.” Robert A. Jarrow, V. Maksimovic, and W. Z. Ziemba, ed.: Finance, Handbooks in Operations Research and Management Science 9, 385-410 (Amsterdam: North Holland).
5. Fama, Eugene F.(1970) , ”Efficient Capital Markets: A Review of Theory and Empirical Work.” Journal of Finance ,Vol. 25, No. 2.
6. J, Wells Wilder(1978), “New Concepts in Technical Trading Systems.” Trend Research.
7. Jensen, M. C. and Benington, G. A.(1970), “Random Walks and Technical Theories: Some Additional Evidence.” Journal of Finance ,Vol. 25.
8. Kahneman, D., & A. Tversky(1979), “Prospect theory: An analysis of decision under risk,” Econometrica, Vol. 47, No. 2. (Mar., 1979), pp. 263-292.
9. Kenstner, Lars(2003), Quantitative Trading Strategies: harnessing the power of quantitative techniques to create a winning trading program, McGraw-Hill Education.
10. Lento, Camillo(2014), Handbook of Asian Finance: REITs, Trading, and Fund Performance, P255-265.
11. Levy, R. A.(1967), “Relative Strength as a Criterion for Investment Selecton.” Journal of Finance ,Vol. 22, No. 6.
12. Piotroski, J.(2000), ‘‘Value Investing: The Use of Historical Financial Statement Information to Separate Winners from Losers.’’ Journal of Accounting Research 38, 1–41.
13. Reilly and Brown(2005), Essentials of Investment Analysis and Portfolio Management, THOMSON.
14. Reilly, Frank K.& Keith C. Brown(2005), Investment Analysis and Portfolio Management, SouthWesternCollege; 8th edition (2005).
15. Shefrin and Statman(1985), Explaining investor preference for cash dividends, Journal of Financial Economics.
16. Shefrin, H. and M. Statman(1985),“The disposition to sell winners too early and ride losers too long: Theory and evidence,” Journal of Finance 40, 777-790.
17. Thaler, R.H., and E. J. Johnson(1990),“Gambling with the house money and trying to break even: The effects of prior outcomes on risky choice,” Management Science 36, 643-660.