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

If $X$ is a random variable with finite mean $\mu$ and variance $\sigma^2$, how do I show that the estimate

\begin{equation*} P[\mu − d\sigma < X < \mu + d\sigma] ≥ 1 − 1/d^2~\forall d>1 \end{equation*}

holds? I found this in a book but unable to see the proof. Note that $X$ may not be normal.

share|cite|improve this question
up vote 3 down vote accepted

This is Chebyshev's inequality, which holds for any probability distribution. There are two proofs given on the linked Wikipedia page - a measure-theoretic one, and one that uses Markov's inequality.

Your expression is in a different form, though, than the one on the Wikipedia page. To see how they are the same, observe that

$$P[\mu - d \sigma < X < \mu + d \sigma] \geq 1 - 1/d^2$$ is equivalent to $$P[|X - \mu| < d \sigma] \geq 1 - 1/d^2,$$ which is equivalent to $$P[|X - \mu| > d \sigma] \leq 1/d^2,$$

which is the one on the Wikipedia page.

share|cite|improve this answer
"which holds for any probability distribution" - this is only true of distributions whose variance is defined. – R R Feb 3 '15 at 3:06

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.