Physics Stack Exchange is a question and answer site for active researchers, academics and students of physics. 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

I am studying Statistical Mechanics and Thermodynamics from a book that i am not sure who has written it, because of its cover is not present.

There is a section that i can not understand:


$S= \sum_{j=1}^{N} F_{j}$

$<S>=< \sum_{j=1}^{N} F_{j}> = \sum_{j=1}^{N} <F_{j}>$

$\sigma^{2}_{S} =<S^{2}>-<S>^{2}$

line a:

$=\sum_{j=1}^{N}\sum_{k=1}^{N} <F_{j}F_{k}> - \sum_{j=1}^{N} <F_{j}>\sum_{k=1}^{N}<F_{k}>$

I can not understand why these terms are different

First term is:


Second term is


I can see they are same.

But as you can see above it is different, how? Where am i wrong?

The question Math for Thermodynamics Basics 's answer have some clue but i could not understand exactly. Thanks.


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

The average/expected value of a product is in general not the same as the product of expected values. (The "mean value" function is linear though: a sum of mean values is equal to the mean value of the sum.)

The product of the sum and sum of product are related by the covariance: $cov(X,Y) = <XY> - <X><Y>$, as you stated yourself.

I hope this helps.


share|cite|improve this answer
How can this be then $=\sum_{j=1}^{N}\sum_{k=1}^{N} <F_{j}F_{k}>$ $=\sum_{j=1}^{N}\sum_{k=1(k\neq j))}^{N} <F_{j}><F_{k}> +\sum_{j=1}^{N} <F_{j}^{2}>$ ? As i understood $=\sum_{j=1}^{N}\sum_{k=1}^{N} <F_{j}F_{k}>$ $=\sum_{j=1}^{N}\sum_{k=1(k\neq j))}^{N} <F_{j}F_{k}> +\sum_{j=1}^{N} <F_{j}^{2}>$ – merveotesi Jun 18 '13 at 13:47
What do you mean bij "this"? Your first equation is correct if $F_j$ and $F_k$ aren't related for $j\neq k$ (then the covariance equals zero), your second equation is generally true. – BNJMNDDNN Jun 18 '13 at 14:28
Is following: $=\sum_{j=1}^{N}\sum_{k=1(k\neq j))}^{N} <F_{j}><F_{k}>$ equal to $=\sum_{j=1}^{N}\sum_{k=1(k\neq j))}^{N} <F_{j}F_{k}>$ because k different from j? Am i right? If it is right, why? – merveotesi Jun 18 '13 at 15:09
No, since $< F_j F_k > = < F_j >< F_k > + cov(F_j,F_k)$. If the covariance equals zero - which means $F_j$ and $F_k$ aren't related, they are independant - your equation is true. So you just have to determine whether your variables are dependant of each other or not. – BNJMNDDNN Jun 18 '13 at 15:20

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.