#### You've reached the end of your free preview.

Want to read the whole page?

**Unformatted text preview: **What the above demonstrates is two basic rules for expectations operators regardless of whether random variables are discrete or continuous: 1) E(a) = a “The expected value of a constant is a constant” 2) E(bX) = bE(X) “The expected value of a constant times a random variable is equal to the constant times the expected value of the random variable” More generally let X Y and Z be three random variables eanch with their own density functions
and let W = aX + bY + cZ, then E(W) = aE(X) + bE(Y) + cE(Z). 2. g(X) = (Ii-EGO)i i = 2, .. Functions of this form yield “i’th moments about the mean”. The metric here is the i’th power of
that of the original distribution so that if f(x) relates to incomes measured in $US then the i’th
moment about the mean is measured in ($US)i. Sometimes the i’th root of g(X) is employed
since it yields a measure of the appropriate characteristic in terms of the original units of the
distribution. Furthermore to make distributions measured under different metrics comparable the
ﬁlnction g(X) deﬂated by the appropriate power of E(X) (provided it is not 0) is considered,
providing a metric free comparator. The second moment (i = 2) is of particular interest1 since as
the variance (frequently represented as 02 or V(X), its square root 0 is referred to as the standard deviation) it provides a measure of how spread out a distribution is. Of particular interest here is ...

View
Full Document

- Spring '14
- Schmid
- Economics, Standard Deviation, Variance, Probability theory, probability density function