## In Practice Estimating only downside risk

The variance of a return distribution measures the deviation of actual returns from the expected return. In estimating the variance, we consider not only actual returns that fall below the average return (downside risk) but also those that lie above it (upside risk). As investors, it is the downside that we generally consider as risk. There is an alternative measure called the semi-variance that considers only downside risk. To estimate the semi-variance, we calculate the deviations of actual returns from the average return only if the actual return is less than the expected return; we ignore actual returns that are higher than the average return.

Semi-variance = #

' n (Rt-Average Return)2

/-i n n = number of periods where actual return < Average return

With a normal distribution, the semi-variance will generate a value identical to the variance, but for any non-symmetric distribution, the semi-variance will yield different values than the variance. In general, a stock that generates small positive returns in most periods but very large negative returns in a few periods will have a semi-variance that is much higher than the variance.

## Lessons From The Intelligent Investor

If you're like a lot of people watching the recession unfold, you have likely started to look at your finances under a microscope. Perhaps you have started saving the annual savings rate by people has started to recover a bit.

## Post a comment