On this page
What this lesson covers
Kurtosis measures the combined weight of a distribution’s tails relative to the rest of the distribution; excess kurtosis subtracts the normal distribution’s value of three.
Raise standardized deviations to the fourth power and distinguish kurtosis from excess kurtosis. Kellbrook’s fat tails illustrate why a normal model can understate the frequency of extreme return outcomes.
How do you calculate kurtosis?
Average fourth powers of standardized deviations and subtract three for excess kurtosis; the lesson uses this sample approximation for at least 100 observations.
Large-sample excess kurtosis = (1 / n) × sum of [(observation − sample mean) / sample standard deviation]^4 − 3
- Observation, sample mean and sample standard deviation
- Sample size, at least 100 for this lesson’s approximation
For example, Kellbrook’s kurtosis of about 8.46 gives excess kurtosis of 8.46 − 3 = 5.46; the positive excess identifies fat tails relative to a normal distribution.
Common mistakes
- Reading excess kurtosis against three instead of zero uses the wrong benchmark.
- Judging kurtosis only by the central peak overlooks the fat tails far out at the extremes.
- Using a normal model for fat-tailed returns underestimates the likelihood of extreme outcomes.
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.