方法对比

	资本资产定价模型 (CAPM)	多因子风险模型（Fama-French, APT）	普通最小二乘法 (OLS) 回归
领域	金融学	金融学	计量经济学
方法族	Regression model	Regression model	Regression model
起源年份	1964	1993	2019
提出者	William F. Sharpe & John Lintner	Fama & French (factor model); Ross (Arbitrage Pricing Theory)	Wooldridge (textbook treatment); classical least squares
类型	Equilibrium asset-pricing model	Multi-factor linear regression model	Linear regression
开创性文献	Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance, 19(3), 425–442.	Fama, E. F., & French, K. R. (1993). Common Risk Factors in the Returns on Stocks and Bonds. Journal of Financial Economics, 33(1), 3-56.	Wooldridge, J. M. (2019). Introductory Econometrics: A Modern Approach (7th ed.). Cengage Learning. ISBN: 978-1337558860
别名	Capital Asset Pricing Model, Sharpe-Lintner CAPM, security market line, Sermaye Varlıkları Fiyatlama Modeli	Fama-French model, Fama-French three-factor model, Fama-French five-factor model, arbitrage pricing theory	ordinary least squares, classical linear regression, linear regression, en küçük kareler regresyonu
相关	2	5	5
摘要	The Capital Asset Pricing Model (CAPM), developed by William Sharpe and John Lintner in the mid-1960s, links the expected return of an asset to its systematic risk, measured by beta. It states that in equilibrium investors are rewarded only for risk that cannot be diversified away: the expected excess return of an asset is proportional to the expected excess return of the market, with beta as the constant of proportionality. CAPM underpins the cost of equity, performance benchmarking, and a vast body of asset-pricing research.	A factor risk model is a multi-factor framework that links asset returns to systematic risk factors such as the market, value, size, and momentum. The Fama-French three- and five-factor models (1993) and Ross's Arbitrage Pricing Theory (1976) decompose portfolio risk and detect alpha.	Ordinary Least Squares is the classical linear regression method that explains a continuous outcome as a linear combination of predictors. It estimates the coefficients by minimising the sum of squared residuals, and under the Gauss-Markov assumptions these estimates are the best linear unbiased estimator (BLUE).