1
$\begingroup$

Have this question I think I'm doing right, but I am unsure:

Let $(X,Y)$ be a random vector characterized as follows. The marginal density $f_X(x)=2x$ for $0 \le X \le 1$ and the conditional distribution of Y given X=x is uniformly distributed in [0,x]. Find the joint pdf f(x,y) and marginal density $f_Y$.

From this, I took the conditional probability to be $$ f_{Y|X}(y|x)=\frac{1}{x} $$ for $0 \le y \le x$ and from there calculated $$ f_{XY}(x,y) = f_{Y|X}(y|x)*f_X(x)=\frac{1}{x}*2x=2 $$ I know pdfs can have values greater than 1, but this seems off to me.

For the marginal distribution of y, I know to integrate the pdf over all values of x, so I did this: $$ f_Y(y)=\int_0^y 2dx = 2y $$ for $0 \le y \le 1$. I can't imagine that this is correct. Thank you for your help!

$\endgroup$
1
$\begingroup$

The joint density looks like this:

enter image description here

So, the marginal distribution of $Y$ is given by the following integral

$$\int_y^1 2 \ dx=2(1-y)$$

if $0\leq y\leq 1$.

$\endgroup$
1
$\begingroup$

Your work is correct except for forgetting to indicate the regions where the pdf is zero, for example by noting, $$ f_{Y|X}(y|x)=\frac{1}{x}\mathbf{1}_{0\le y\le x} $$ then, $$ f_{XY}(x,y) = f_{Y|X}(y|x)*f_X(x)=\frac{1}{x}\mathbf{1}_{0\le y\le x}\,\cdot\,2x\mathbf{1}_{0\le x\le 1}=2\cdot\mathbf{1}_{0\le x\le 1}\cdot\mathbf{1}_{0\le y\le x} $$ As a check, integrate this over all $x,y$ and you will find that it comes out to $1$ as required. The range of integration you used to calculate the marginal $f_Y(y)$ is incorrect. $$f_Y(y)=\int_0^1f_{XY}(x,y)dx = \int_y^12dx =2(1-y)$$ since the pdf is zero for $x<y$.

$\endgroup$

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.