Questions about Linear Combinations of Random Variables

Join the discussion
Ask a follow-up here, or get your own question answered by working scientists, mathematicians and engineers — people, not an autocomplete.
Real named experts · corrections over time · the nuance an AI answer skips
4 replies · 3K views
ken15ken15
Messages
4
Reaction score
0

Homework Statement


RQwRhjc.jpg

Homework Equations


Y=1/2*(X1-X3)^2+1/14*(X2+2X4-3X5)^2

The Attempt at a Solution


For (a) part, I have only learned to find the moment-generating function of Y, but not finding the p.d.f.
Moreover, the examples I have seen only involves random variables Xi to the power 1, but not to higher power.

For (b) part, the difficulty for me is just similar to part (a).
 
Last edited:
Physics news on Phys.org
Hint: [tex](Z_1^2 + ... +Z_n^2) +(Z_1^2 + ... +Z_m^2) = (Z_1^2 + ... +Z_n^2 +...+ Z_m^2)[/tex]
 
dirk_mec1 said:
Hint: [tex](Z_1^2 + ... +Z_n^2) +(Z_1^2 + ... +Z_m^2) = (Z_1^2 + ... +Z_n^2 +...+ Z_m^2)[/tex]

sorry but...what property is it? I haven't learned this before...
 
ken15ken15 said:

Homework Statement


RQwRhjc.jpg



Homework Equations


Y=1/2*(X1-X3)^2+1/14*(X2+2X4-3X5)^2


The Attempt at a Solution


For (a) part, I have only learned to find the moment-generating function of Y, but not finding the p.d.f.
Moreover, the examples I have seen only involves random variables Xi to the power 1, but not to higher power.

For (b) part, the difficulty for me is just similar to part (a).

##Z_1 = X_1 - X_3## has an ##N(0,a)## distribution, ##Z_2 = X_2+2X_4-3X_5## is ##N(0,b)##, and ##Z_1, Z_2## are independent. So ##Y## involves a weighted sum of squares of independent, mean-0 random variables.
 
Ray Vickson said:
##Z_1 = X_1 - X_3## has an ##N(0,a)## distribution, ##Z_2 = X_2+2X_4-3X_5## is ##N(0,b)##, and ##Z_1, Z_2## are independent. So ##Y## involves a weighted sum of squares of independent, mean-0 random variables.

So do you mean given the random variables are independent, the sum or difference of them will also have the same distribution of them? Also, how can a duel with the square of the random variables? Do I need to consider it with transformation of variables?