The Capital Asset Pricing Model (CAPM) of Sharpe (1964), Lintner (1965), and Mossin (1966) has been the dominant orthodoxy in finance. A vast amount of empirical research has been conducted to test whether the CAPM is supported by real-world data on stocks and many different regression-based tests have been proposed, e.g. Jensen et al.(1972), Fama and McBeth (1973). Fama and French (1992, 1993) identified that size (MCAP) and the ratio of BE/ME contribute significantly to variation in returns.

Required:

1. Using monthly returns of three value-weighted (V-W) SIZE (i.e. Small, Medium, Big) and three value weighted BE/ME (Low, Medium, High) and factors relating to market risk premium, size premium and value (BE/ME) premium from CRSP database from 1927 - 2016 of US listed firms and the US Treasury bill rate, test the classical CAPM. That is, for each of the V-W portfolio, estimate the beta using linear regression and compute the required return as predicted by CAPM. Evaluate the results of the V-W portfolio and compare the required returns as predicted by the CAPM with the actual historical mean returns.

2. Repeat the test by including the error variance from the first-pass regression for each V-W portfolio as an additional regressor to test the null hypothesis that non-systematic risk is not priced.

3. Using the data in part (a) and data collected on size (MCAP) and BE/ME portfolios test the Fama-French three factor model for all size and BE/ME portfolios.

4. Evaluate the performance of each portfolio using the Jensen Alpha in both CAPM and Fama-French three-factor model, Sharpe Ratio and Treynor Ratio. Discuss the view that the Sharpe-Lintner-Mossin CAPM is a special case of Ross (1976) Arbitrage Pricing Theory (APT), Breeden (1979) Consumption CAPM and Fama and Frenchs (1993, 1996) three-factor model.