本研究結合關聯式資料庫與數量化股票投資組合理論，設計出專屬於多因子模型使用的資料庫，並依照Barra風險模型標準流程以及該系統架構為基礎，建立多因子風險模型平台， 本研究所建立的資料庫有助於快速尋找與篩選具有解釋股票報酬的要素。
資料庫的設計分三大部分。第一部分為要素計算與更新模組建置，本研究在此找出影響台灣集中市場股票報酬的48個要素；第二部分則利用實體關聯模型管理所有因子模型中所有重要的資訊；第三部分設計資料庫自動更新流程，以利即時獲取最新資訊，逐月建構最新之投資組合標的，提高本研究平台與實務操作的黏著度。
多因子風險模型的建構主要分為五大步驟：1.發展顯著要素；2.發展顯著複合因子；3.多因子報酬模型；4.多因子風險模型；5.股票分群績效回測。實證結果發現：在1998/04~2005/11建構模型期間，模型解釋能力平均達50%。本研究除了建構風險模型標準流程外，並運用因素分析法以濃縮要素個數形成共同要素，可有效減少不同群集要素產生共線性問題。為考慮因子報酬之時間衰減特性，另加入半衰期預測因子報酬參數，發現台灣股票市場以24期半衰期所創造出來的投資組合累積報酬結果最佳。

This research combines relational database framework and quantitative equity portfolio models based on the Barra Risk Model Handbook standard steps to design a database and computer platform for multi-factor risk management tasks. The multi-factor model facilitates fast search and efficient selection of descriptors with explanatory power for future stock returns.
The design of database is divided into three steps. First, descriptors are calculated and daily-update modules constructed. This study finds 48 key descriptors which play important roles in explaining stock returns of Taiwan. Second, entity relational model is applied to sort out linkages between pieces of important information in the factor model. Lastly, database auto-run procedures are setup to update the latest raw data on a monthly basis. Model parameter update and portfolio rebalancing is hence made seamless to meet practical operation demand for such a platform.
The development of the Multi-factor risk model is divided into five main steps. (1) Finding significant descriptors. (2) Forming common factors from descriptors. (3) Developing a multi-factor return model. (4) Developing a multi-factor risk model. (5) Running performance analysis and back-testing.
The empirical results show that the average adjusted R-squared of the MFM model is 0.5 during the period of 1998/04~2005/11. For combining descriptors into common factors, we run factor analysis. The multi-collinearity problem existing in the descriptors is well taken care of by such procedures. We use the exponentially weighted averaging method to compute the factor returns and forecast stock ranking. A half-life of 24 months appears to deliver the best performance in Taiwan stock market.

第一章 緒論 1
第1節 研究背景與現況 1
第2節 研究目的與動機 4
第3節 研究架構與流程 6
第二章 文獻探討 7
第1節 現代投資組合理論 7
第2節 資料模型與實體關聯模型 8
第3節 多因子模型 11
第4節 因素分析與主成份分析 12
第三章 研究方法 14
第1節 研究範圍 14
第2節 多因子資料庫 17
第3節 多因子風險模型 25
第四章 實證結果 46
第1節 有效要素挑選結果 46
第2節 主成分分析結果 49
第4節 多因子模型建構結果-報酬部份 56
第5節 多因子模型建構結果-風險部分 66
第五章 結論與後續研究建議 69
第1節 結論 69
第2節 後續研究建議 71
參考文獻： 73
附錄A: 因子資料庫之資料表綱要 75
附錄B: 要素定義表 77

1. Banz, Rolf W., (1981), The relationship between return and market value of common stock, Journal of Financial Economics 9, 3-18.
2. BARRA (1998), ─United States Equity Version 3 (E3), ─Risk Model Handbook.
3. Barry, C. B., Goldreyer, E., Lockwood, L., and Rodriguez, M. (2002), ─Robustness of Size and Value Effects in Emerging Equity Markets, 1985-2000, Emerging Markets Review, Vol. 3, No. 1, March, pp. 1-30.
4. Basu, Sanjoy, (1983), The relationship between earnings’ yield, market value and the return for NYSE common stocks: Further evidence, Journal of Financial Economics 12, this issue.
5. Chincarini, Ludwig B. and Kim, D. (2006), ─Quantitative Equity Portfolio Management: An Active Approach to Portfolio Construction and Management, McGraw-Hill.
6. Connor, G. (1995), ─The Three Types of Factor Models: A Comparison of Their Explanatory Power, Financial Analysis Journal, May/June.
7. Engle, R., V.K. Ng and M. Rothschild (1990). Asset Pricing With a Factor ARCH Covariance Structure: Empirical Estimation for Treasury Bill, Journal of Econometrics, 45, 213--237.
8. Fama, Eugene F. and French, Kenneth R. (1992), ─The Cross-Section of Expected Stock Returns, Journal of Finance, Vol. 47, No. 2, June, pp. 427-465.
9. Fama, Eugene F. and James D. MacBeth (1973), ─Risk, Return, and Equilibrium:Empirical Tests, Journal of Political Economy, Vol. 81, No. 3, May/June, pp. 607-636.
10. Francis X. Diebold and Marc Nerlove (1989). The Dynamics of Exchange Rate Volatility: A Multivariate Latent Factor Arch Model, Journal of Applied Econometrics, Vol. 4, No. 1 (Jan. - Mar., 1989), pp. 1-21
11. Grinold & Kahn (2000), Active Portfolio Management, ─A Quantitative Approach for Producing Superior Return and Controlling Risk(2th Edition), McGraw-Hill.
12. Gujarati, Damodar N. (2003), ─Basic Econometrics (4th Edition).
13. Litterman, R. and The Quantitative Resources Group of Goldman Sachs Asset Management (2003), ─Modern Investment Management: An Equilibrium Approach.
14. Peter P. Chen (1976). The Entity-Relationship Model: Toward a Uni_ed View of Data. ACM Trans. On Database Systems, Vol. 1, No. 1, pages 1-36.
15. Ross, Stephen A. (1976), ─The Arbitrage Theory of Capital Asset Pricing, Journal of Finance, Vol. 13, pp. 341-360.
16. Shyu, S., Jeng, Y., Ton, W.H., Lee, K.J. and Chuang, H.M. (2006), ─Taiwan Multi-factor Model Construction: Equity Market Neutral Strategies Application, Managerial Finance, Vol. 32, No. 11, pp. 915-947.
17. Syu, M.S. (2007) ─Stock Selection Performance Analysis using Multi-Factor Model in Taiwan. National Sun Yat-sen University, Taiwan. SYU Ton
18. Trzcinka, C. (1986), ─On the Number of Factors in the Arbitrage Pricing Model, Journal of Finance, Vol. 41, No. 2, pp. 347-368.