0
$\begingroup$

I am confused about what is means to take the expected value of a CDF.

Let $X$ be a random variable with cdf $F_x(x)$, and assume that $X$ is a continuous random variable. What is $E[F_x(X)]$ and $var(F_x(X))$.

I assume this is similar to just taking the expectation of a function of a random variable, so I get something like this to start out.

$E[F_x(X)] = \int F_x(x)f_x(x)dx$

where $f_x(x)$ is the pdf of $X$, but I am not sure what this even means or where to go next. I understand expected value of a random variable, but what does it mean to take the expected value of a CDF. I am sorry if this has been answered, but I am not able to find help on this anywhere.

$\endgroup$

1 Answer 1

1
$\begingroup$

We make the substitution $F_x(u)=t$. Then $f_x(u)du=dt$. Note $t$ ranges from $0$ to $1$ $$E[F_x(X)] = \int_{-\infty}^{\infty} F_x(u)f_x(u)du= \int_0^1 t dt =\frac12$$ Similarly $$E[F_x(X)^2] = \int_{-\infty}^{\infty} F_x(u)^2f_x(u)du= \int_0^1 t^2 dt =\frac13$$ Hence $Var[F_x(X)]=\frac1{12}$.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.