Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

Suppose you want to find $E(X)$ for a non-negative random variable $X$. So you can use $\int_{0}^{\infty} [1-F(x)] \ dx$. To get $1-F(x)$, all you have to do is integrate as follows: $\int_{x}^{\infty} f(t) \ dt$? In other words, instead of integrating from $t=0$ to $t= x$, we can just integrate from $t = x$ to $t = \infty$?

share|improve this question
    
Whatever you have written is right. What is your question though? –  user17762 Nov 19 '10 at 6:27
2  
Yes, since $1 - \int_0^x {f(t){\rm d}t} = \int_x^\infty {f(t){\rm d}t} $. –  Shai Covo Nov 19 '10 at 10:57
add comment

1 Answer 1

up vote 2 down vote accepted

I guess your question is: Why is $E(X)=\int_0^\infty 1-F(x) dx$?

The answer is as follows: By definition $$E(X)=\int_0^\infty tf(t) dt.$$ Now \begin{eqnarray*} & & \int_0^\infty tf(t) dt\ &=&\int_0^\infty f(t)\int_0^t 1 dx dt\ &=&\int_0^\infty\int_0^t f(t) dx dt\ &=&\int_0^\infty\int_x^\infty f(t) dt dx \ &=&\int_0^\infty 1-F(x) dx. \end{eqnarray*}

share|improve this answer
add comment

Your Answer

 
discard

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.