投资金融学方面的书籍foassetpricing--appendix.pdfVIP

Mathematical Appendix A. SECOND MOMENTS Many of the asset pricing relationships include the second statistical moment between two random variables. Thus, we will look here at different ways of expressing the second moment: variance and covariance, correlation coefficient, and beta. We will also derive a linearity rule of manipulating covariances and consider some other convenient properties of covariances. Covariance and Related Definitions Consider two random variables, X and Y, with means (or “expected values” or “first moments”) of µ and µ . X Y Then the Covariance between X and Y is given by: (A1) Cov(X , Y) / F / E [(X µ ) ( Y µ )] . XY X Y The Variance of a random variable X , Var (X ), is a special case of the covariance, in which the random variables, here X and Y, are identical. The Standard Deviation is simply the square root of the variance. Thus: (A2) F / [ Var(X )]1/ 2 / [E (X µ )2 ]1/ 2 . x X To normalize the covariance such that its value must lie between -1 and +1, we define the Correlation Coefficient between X and Y as: F XY (A3) D . XY F F X Y Another concept related to the covariance is that of the slope of a simple OLS regression line Y = + $ X : F (A4) $ / $ XY . XY 2