A SIMPLE APPROXIMATION FOR SEMIVARIANCE

Semivariance can differentiate among skewed return distributions but variance is unable to do so. Thus, semivariance has been used as a risk surrogate in portfolio analysis and capital budgeting problems. Unfortunately, semivariance analysis is relatively unknown and poses difficult analytic and computational problems. In this paper an expression is derived which very closely approximates semivariance. This expression is simple in form and uses only familiar statistics, namely, mean, variance, critical value, and cumulative probability below the critical value.