Statistical properties of the sample semi-variance

In finance theory the standard deviation of asset returns is almost universally recognized as a measure of risk. This universality continues to exist even in the presence of known limitations of using the standard deviation and also an extensive and growing literature on alternative risk measures. One possible reason for this persistence is that the sample properties of alternative risk measures are not well understood. This paper attempts to compare the sample distribution of the semi-variance with that of the variance. In particular, the belief that, while there are convincing theoretical reasons to use the semi-variance the volatility of the sample measure is so high as to make the measure impractical in applied work, is investigated. In addition arguments based on stochastic dominance are also used to compare the distribution of the two statistics. Conditions are developed to identify situations in which the semi-variance may be preferred to the variance. An empirical example using equity data from emerging markets demonstrates this approach