CFA Study Guide

Quantitative Methods: Statistical Concepts

There are two categories of risk measurements: Absolute and Relative. I've spoken earlier about CV and Sharpe Ratios which measure risk in relation to expected returns (risk÷return; return÷risk). As you might guess, those methods would fall under the Relative category. Absolute measures of risk don't account for any returns. The two Absolute measures are Variance and Mean Absolute Deviation and they only measure a deviation compared to the number of observations (Dev÷N **). The difference between the two is how they handle negative errors.

Variance:
Notice that the deviations from the mean (errors) are squared before summing so that no negative numbers are incorporated. This amplifies the effect of any outliers.


MAD:
Accounts only for the absolute value of the errors and keeps the dispersion results closer to the mean than variance does.

Key Point:
Variance is more sensitive to outliers in the observations.


** Please be aware of the actual equations for these two formulas. Dev÷N is an oversimplification for illustration purposes.