MHB Finding Marginal PDFs: Need Help With Integrating Complex Expressions?

  • Thread starter Thread starter nacho-man
  • Start date Start date
  • Tags Tags
    Marginal
Click For Summary
To compute marginal PDFs from a joint PDF, integrate the joint PDF with respect to the other variable, specifically integrating f_{X,Y}(x,y) with respect to y to find f_X(x). This process can result in complex integrals, but techniques such as completing the square and variable substitution can simplify the calculations. For example, substituting w = y + (1/2)x√2 can help in evaluating the integral. Utilizing the standard integral of a normal distribution is also beneficial in this context. Proper application of these methods can lead to a clearer solution for the marginal PDFs.
nacho-man
Messages
166
Reaction score
0
Please see the attached image for my question. I don't understand how to compute the integral, is there some trick?
I do believe that
to find fx(x) I integrate the joint pdf, with respect to x with the bounds set as the range of Y. But this leaves me with a very complex integration
Similarly for fy(y). Is there some trick?

Any help is greatly appreciated.
 

Attachments

  • pdf q.jpg
    pdf q.jpg
    23.7 KB · Views: 99
Last edited by a moderator:
Physics news on Phys.org
nacho said:
Please see the attached image for my question. I don't understand how to compute the integral, is there some trick?
I do believe that
to find fx(x) I integrate the joint pdf, with respect to x with the bounds set as the range of Y. But this leaves me with a very complex integration
Similarly for fy(y). Is there some trick?

Any help is greatly appreciated.
Hi nacho!

To find $f_X(x)$ you need to integrate $f_{X,Y}(x,y)$ with respect to y.

That is:
$$f_X(x) = \int_{-\infty}^{+\infty} f_{X,Y}(x,y) dy$$

The problem is of course that exponent, but you can complete the square, do a substitution, and use the standard integral of a normal distribution.

That is:
$$f_X(x) = \int_{-\infty}^{+\infty} f_{X,Y}(x,y) dy
= \int_{-\infty}^{+\infty} \frac{1}{\pi\sqrt 2} \exp\left(-(y + \frac 1 2 x \sqrt 2)^2 - \frac 1 2 x^2\right) dy$$

Can you substitute $w = y + \frac 1 2 x \sqrt 2$?

And use that $$\int_{-\infty}^{+\infty} \exp\left(-\frac 1 2 u^2\right) du = \sqrt{2\pi}$$?
 
Hello, I'm joining this forum to ask two questions which have nagged me for some time. They both are presumed obvious, yet don't make sense to me. Nobody will explain their positions, which is...uh...aka science. I also have a thread for the other question. But this one involves probability, known as the Monty Hall Problem. Please see any number of YouTube videos on this for an explanation, I'll leave it to them to explain it. I question the predicate of all those who answer this...

Similar threads