How Do You Prove Independence of Z-Squared in Sample Distributions?

[fighthard88]

Homework Statement

[PLAIN]http://img40.imageshack.us/img40/1503/question1l.jpg

Homework Equations

[URL]http://onlinecourses.science.psu.edu/stat414/sites/onlinecourses.science.psu.edu.stat414/files/lesson26/Variance10.gif[/URL]

[URL]http://onlinecourses.science.psu.edu/stat414/sites/onlinecourses.science.psu.edu.stat414/files/lesson26/Variance11.gif[/URL]

[URL]http://onlinecourses.science.psu.edu/stat414/sites/onlinecourses.science.psu.edu.stat414/files/lesson26/Variance13.gif[/URL]

The Attempt at a Solution

I need help with this question. I know that to get this distribution, I need to sum the Z^2's of both respective samples. However, in order to do so wouldn't I need to prove that Z^2's are independent? I'm assuming I'll need to utilize the moment generating function. However, I'm not sure how to go about this. Any help would be much appreciated!

 

[lanedance]

so if you're happy up to the point where Z^2 is equivalent to chi square distribution with 1 DoF, then the sum of two chi square distribution with DoF k1 & k2 is another chi square distribution with DoF = k1 + k2.

the question says the 2 samples are independent. As it is not stated otherwise I would assume the individual samples are independent, though state it as a n assumption