MHB Question about problem statement (marginal distribution)

  • Thread starter Thread starter kalish1
  • Start date Start date
  • Tags Tags
    Distribution
AI Thread Summary
The discussion centers on a practice final problem involving independent normal random variables X and Y, and the confusion arises from the relevance of a provided corollary for finding their marginal distributions. The problem statement suggests using the corollary to derive distributions for U and V, which are defined as U = X + Y and V = X + Y, leading to questions about the necessity of this approach. Participants clarify that the marginal distributions of X and Y are indeed just X and Y themselves due to their independence. There is also a suggestion to consider V as X - Y, which may indicate a misunderstanding of the problem setup. The overall consensus emphasizes the need to apply the corollary correctly to find the distributions of U and V.
kalish1
Messages
79
Reaction score
0
I am doing some problems from a practice final and would like to know if the following problem has mistakes in the way it is written. We are supposed to apply a corollary that doesn't seem to have any relevance in this context. It is throwing me off.

**Problem statement:** Suppose that $X$ ~ $N(\mu,\sigma^2)$ and $Y$ ~ $N(\mu,\sigma^2)$ and they are independent. Let $U=X+Y$ and $V=X+Y$. Use the following corollary to find the marginal distributions of $X$ and $Y$.

**Corollary:** Let $X_1, \ldots, X_n$ be mutually independent random variables with $X_i$ ~ $n(\mu_i, \sigma_i^2)$. Let $a_1, \ldots, a_n$ and $b_1, \ldots, b_n$ be fixed constants Then

$Z=\sum_{i=1}^n(a_iX_i + b_i)$ ~ $n(\sum_{i=1}^n(a_i\mu_i + b_i),\sum_{i=1}^na_i^2\sigma_i^2)$.

Also, aren't the marginal distributions of $X$ and $Y$ just $X$ and $Y$ themselves, because they are independent of each other??

Any help would be greatly appreciated. My final is tomorrow and I'm studying as hard as I can.
 
Physics news on Phys.org
I would guess that $$V= X - Y$$ and that you should find the find the marginal distributions of U and [FONT=MathJax_Math]V.

You should use the Corollary to find their distribution, then try and apply the marginal distribution stuff.

But I could be wrong, good luck!
 
Last edited:
Back
Top