Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

When applying the Empirical formula on a data set, for example calculating 1, 2 or 3 standard deviations below and above the mean of a data set, for some cases, this might not make sense. For example, when dealing with data of time, is it acceptable to say:

$mean - (2 * s.d.) = -5$ hours?

Or does this truncate to $0$ hours?

Thanks for any insight!

share|cite|improve this question
Occasionally when a quantity, say time $t$, is constrained to be positive, it might make more sense to talk about the standard deviation of $\log t$. Then this would give you confidence intervals in the region $t > 0$. – Trevor Wilson Sep 5 '12 at 2:34
up vote 1 down vote accepted

The empirical rule applies to the normal distribution and not generally. It can be a useful approximate rule for distributions whose shape is close to the normal. But it would not apply to highly skewed or very heavytailed distributions. The Chebyshev inequality provides general bounds that apply to all distributions with finite variances.

share|cite|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.