On this page
What this lesson covers
Semi-deviation measures variability below the mean; target downside deviation measures shortfalls relative to a chosen minimum acceptable return.
Compare funds whose equal standard deviations conceal different downside risks. Compute sample downside measures using all observations in the n − 1 divisor, even when only some returns contribute squared shortfalls.
How do you calculate semi deviation?
Sum squared shortfalls below the mean or at or below the target, divide by the full sample size minus one and take the square root.
Sample semi-variance = sum of squared deviations below the mean / (n − 1); semi-deviation = square root of semi-variance
- Observation and sample mean
- Full sample size
Target downside deviation = square root of [sum of (return − target)^2 for returns at or below target / (n − 1)]
- Target return
- Full sample size
For example, Kellbrook’s shortfalls at a 7% target have squared values totaling 962 in percent squared; with eight years, target downside deviation is √(962 / 7) ≈ 11.72%.
Common mistakes
- Dividing by the number of observations at or below the target uses the wrong denominator because the calculation requires the full sample size minus one.
- Comparing semi-variance directly with variance, as if the two measured the same thing.
Try a practice question
Choose an answer, then check it to read the explanation for every option.
Continue studying in Quizara
In Quizara the lesson comes with more practice questions on the topic, explanations for every option and an AI tutor for your follow-up questions.
Written by the Quizara Editorial Team under our editorial standards.