Re: Distribution functions

Quote:

Originally Posted by

**supermario88** Hi there,

I was wondering if someone could explain how to go about the following problem.

Let X and Y be independent random variables having distribution functions F_{x} and F_{Y} , respectively.

a) Define Z = max{X,Y} to be the larger of the two. Show that F_{Z}(z) = F_{X}(z)F_{Y}(z) for all z.

b) Define W = min{X,Y} to be the smaller of the two. Show that F_{W}(w) = 1 - [1-F_{X}(w)][1-F_{Y}(w)] for all w.

Thanks!

since they are independent,

$\displaystyle F_Z(z)=P[Z \leq z]=P[(X \leq z)\cap (Y \leq z)]= P(X \leq z) P(Y \leq z)=F_X(z)\cdot F_Y(z)$

and

$\displaystyle F_W(w)=P[W \leq w]=1-P[(X>w) \cap (Y>w)]=.......$

Re: Distribution functions

Hi harish21,

Thanks very much for the reply. So I can finish letter b thanks to your hint. Would you mind explaining the intuition of letter a? Specifically, could you talk about why

P[Z≤z] = P[(X≤z)∩(Y≤z)]

I just want to develop a better understanding of the problem. Thank you.

Re: Distribution functions

Z is the largest of X and Y

so IF Z is less than or equal to a, then both X and Y must be less than or equal to a.

For the minimum, use the complement twice

Re: Distribution functions

Re: Distribution functions

I work with order statistics all the time.

I can google my name and find some of my papers...

http://w3.math.sinica.edu.tw/bulleti...d322/32203.pdf

Re: Distribution functions

Understood. Thanks matheagle.