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

Assuming I have a huge data set and the only attribute I know about it is the Variance (or SD since SD = $\sqrt{\text{Variance}}$). What conclusions can I make about the set with reasonable certainty?

I don't know the mean, median, mode, presence of outliers or any other information.

Can I make any conclusions beyond How much the values deviate from the mean?

share|cite|improve this question
See the chebyshev inequality. – PeterR Jul 17 '12 at 14:37
up vote 1 down vote accepted

The Chebyshev inequality tells you how much probability content is guaranteed to be within k standard deviations of the mean for any distribution with a finite variance. The bound ie 1-1/k$^2$. So for k <=1 to 1 nothing is guaranteed. for k=2 it guarantees 0.75 and for k=3, 0.89 approximately (actually 8/9). This can be contrasted to the normal distribution which includes probability 0.68 within 1 standard deviation and 0.954 for 2 standard deviations and more 0.9973 for 3 standard deviations. Chebyshev will always give less than or equal to the actual probability of any particular distribution because it has to hold for every distribution with finite variance.

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.