I'm trying to find the expected value of a random variable using its marginal pdf.

Suppose the joint pdf of $X$ and $Y$ is $$f_{XY}(x,y) = \begin{cases}1 && 0<x<1, x<y<x+1\\0 && otherwise\end{cases}$$ Find E(X) and E(Y).

Here's my process for finding $E(X)$

$$f_x = \int_{-\infty}^{\infty}f_{XY}dy = \int_{0}^{1}1dy + \int_{1}^{x+1}1dy\\=1 + x\\ $$


$$f_y = \int_{-\infty}^{\infty}f_{XY}dx = \int_{0}^{y}1dy + \int_{0}^{1}1dy\\=y + 1\\ $$


$$E(X)=\int_{-\infty}^{\infty}xf_{X}dx = \int_{0}^{y}x(1+x)dx + \int_{0}^{1}x(1+x)dx$$

In which the final answer will be a function of $y$, hence I stopped. The book's answer is $1/2$.

Can you point out where did I go wrong?

  • $\begingroup$ Using indicator functions to express densities would save you, nolens volens... $\endgroup$ – Did Oct 18 '17 at 16:02

\begin{eqnarray} E(X) &=& \int_{-\infty}^{+\infty}{\rm d}x \int_{-\infty}^{+\infty}{\rm d}y ~ xf_{XY}(x,y) \\ &=& \int_{0}^1{\rm d}x \int_{x}^{x+1}{\rm d}y~ xf_{XY}(x,y) \\ &=& \int_{0}^1{\rm d}x ~x \underbrace{\color{\red}{\left(\int_{x}^{x+1}{\rm d}y~ f_{XY}(x,y)\right)}}_{f_X(x)}\\ &=& \int_0^1{\rm d}x ~x\color{red}{1} = \left.\frac{1}{2}x^2\right|_0^1 \\ &=& \frac{1}{2} \end{eqnarray}


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.