2
$\begingroup$

I want to find the PDF of $Z=X/(Y+c)$ where $c$ is a constant and $X,Y$ are two independent random variables. The PDFs of $X$ and $Y$ are supposed to be given. I would like to have a general form using the PDFs of $X$ and $Y$. $X\geq 0$ and $Y\geq 0$

I thought of using the CDF but I cannot write it in terms of the PDF of $Y$.

Any suggestions??

$\endgroup$
0
3
$\begingroup$

You should use a two variable transform and then marginalize out the second variable. A good resource on this kind of technique is the Casella and Berger book.

Use a two variable transform $\varphi$ as follows: $$ \begin{bmatrix} U\\ V \end{bmatrix} = \varphi(X,Y) = \begin{bmatrix} X\\ X/(Y+c) \end{bmatrix}$$ Then $\varphi$ is invertible and its inverse is $$ \begin{bmatrix} X\\ Y \end{bmatrix} = \varphi^{-1}(U,V) = \begin{bmatrix} \varphi^{-1}_1(U,V)\\ \varphi^{-1}_2(U,V) \end{bmatrix} = \begin{bmatrix} U\\ U/V - c \end{bmatrix}$$ The joint PDF of $U,V$ is $p_{U,V}(u,v) = \lvert\det\mathrm{J}_{\varphi^{-1}}(u,v)\rvert p_{X,Y}(\varphi^{-1}_1(u,v), \varphi^{-1}_2(u,v))$.

I'll let you compute the jacobian $\mathrm{J}_{\varphi^{-1}}$ and its determinant. Then you can obtain the marginal $p_V$ by marginalisation: $$p_V(v) = \int p_{U,V}(u,v)\,\mathrm{d}u$$

$\endgroup$

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.