returns, rather than excess returns (deviations from T-bill rates), in the regressions. In this way they estimate a variant of our index model, which is   r a brM e* (10.10) instead of     r rf (rM rf ) e (10.11) To see the effect of this departure, we can rewrite equation 10.11 as r rf rM rf e rf (1 ) rM e (10.12) Comparing equations 10.10 and 10.12, you can see that if rf is constant over the sample pe- riod, both equations have the same independent variable, rM, and residual, e. Therefore, the slope coefficient will be the same in the two regressions.10 However, the intercept that Merrill Lynch calls alpha is really an estimate of rf (1 ). The apparent justification for this procedure is that, on a monthly basis, rf (1 ) is     9 Value Line is another common source of security betas. Value Line uses weekly rather than monthly data and uses the New York Stock Exchange index instead of the S&P 500 as the market proxy. 10 Actually, rf does vary over time and so should not be grouped casually with the constant term in the regression. However, vari- ations in rf are tiny compared with the swings in the market return. The actual volatility in the T-bill rate has only a small impact on the estimated value of . III. Equilibrium In Capital Markets 10. Single−Index and Multifactor Models The McGraw−Hill Companies, 2001           CHAPTER 10 Single-Index and Multifactor Models 305     Table 10.2 Market Sensitivity Statistics     June 1994 RESID Standard Error Ticker Close