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

Is it possible to have values greater than 1 in a covariance matrix? Actually, I created a precision matrix Q and then inverted it to get the covariance matrix. And I have values greater than 1. Is it normal? Actually, I created a precision matrix of size 100x100 considering I have values for the neighboring points and zero for the non neighboring points. I added a small delta to make the matrix diagonal dominant such that is is positive definite and its inverse exists

Then I calculate the covariance matrix taking its inverse. I can see some values greater than 1. So any suggestions?

share|cite|improve this question
5  
The usual variance $E(X^2) - E(X)^2$ is a $1 \times 1$ covariance matrix. So, no, there's no reason why entries should be bounded by any number. Any positive semi-definite symmetric matrix can appear as a covariance matrix. – WimC May 19 '12 at 14:43

Your Answer

 
discard

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

Browse other questions tagged or ask your own question.