Assume two random variables X and Y are not independent,

if P(X), P(Y) and P(Y|X) are all normal, then does P(X|Y) also can only be normal or not necessarily?

thanks.

Printable View

- October 19th 2012, 11:08 PMsimon999conditional normal distribution
Assume two random variables X and Y are not independent,

if P(X), P(Y) and P(Y|X) are all normal, then does P(X|Y) also can only be normal or not necessarily?

thanks. - October 19th 2012, 11:24 PMchiroRe: conditional normal distribution
Hey simon999.

Did you ask this question on physics forums? If so I gave an answer there. - October 19th 2012, 11:45 PMsimon999Re: conditional normal distribution
Hi yes I did, not sure I understood your replies though sorry,

so is your answer that P(X|Y) does also has to be normal or not necessarily? - October 19th 2012, 11:55 PMchiroRe: conditional normal distribution
No it has to be if P(Y|X) is proportional to P(X|Y)*P(Y) and if P(X|Y) and P(Y) are both Normal then P(X|Y) also has to be normal.

For a more indepth explanation look up Bayesian statistics with Normal Likelihood and a Normal conjugate prior to see the details. - October 20th 2012, 01:16 AMsimon999Re: conditional normal distribution
Are you sure that by having both marginals normal already cover your condition of P(Y|X) is proportional to P(X|Y)*P(Y)

- October 20th 2012, 01:24 AMchiroRe: conditional normal distribution
If you want to prove it, take two PDFs that are Normally distributed f(X) and g(X) and then show that f(X)*g(X) also has a normal distribution. This is a very simple exercise and would do you well to understand what is going on.

- October 20th 2012, 01:32 AMsimon999Re: conditional normal distribution
Thanks,

Someone else tells me

Look at the 2-d density function for dependent normal variables. You will see that, except for singular cases, that the form of the integrand is symmetric in x and y (except for constants). Therefore if one of the conditional distributions is normal, the other must be.

Singular case - correlation = 1.

Is he wrong then? - October 20th 2012, 01:50 AMchiroRe: conditional normal distribution
You can have a variable covariance matrix in the general situation (can you can include this in your PDF's for X and Y if you want).

- October 20th 2012, 02:10 AMsimon999Re: conditional normal distribution
Sorry so what is the right answer?

if P(X), P(Y) and P(Y|X) are all normal, then does P(X|Y) also can only be normal or not necessarily?

You are saying no but the other person is saying yes