Take the 2-minute tour ×
MathOverflow is a question and answer site for professional mathematicians. It's 100% free, no registration required.

Hi all, Just a quick question - I want to make sure I'm not missing anything obvious here! I'm trying to evaluate $E(S^2 \mid \bar{X} = \bar{x})$, where $X_1,\ldots,X_n$ are i.i.d. Normal($\mu, \sigma ^2$) random variables, $\bar{X}$ is the sample mean ($\frac{\sum{X_i}}{n})$ and $S^2$ is the sample variance ($\frac{1}{n-1}\sum{(X_i-\bar{X})^2}$).

As far as I can tell, this should just be $\sigma^2$, which is the expected value for sample variance (since its an unbiased estimator). Am I missing something though? Does the $\bar{X}=\bar{x}$ condition have some effect that I've not noticed?

Thank you for your help!

share|improve this question
2  
This is not a research-level question, please direct it to math.stackexchange.com . –  Brendan McKay Feb 19 '13 at 7:13
    
This is not research level. Nevertheless, under your assumptions, the empirical mean and variance are independent so that $E(S^2|\bar{X}=\bar{x})=E(s^2)$. –  Jochen Wengenroth Feb 19 '13 at 7:14
    
Apologies! Got mixed up with my sites - I'm not sure how to delete the question, sorry! (And Jochen, thank you for the clarification - glad to know I was right :) ) –  JessieY Feb 19 '13 at 7:19
add comment

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.