Are Functions of Independent Random Variables Always Independent?

  • Thread starter Thread starter kingwinner
  • Start date Start date
  • Tags Tags
    Statistics
Click For Summary
SUMMARY

The discussion centers on the independence of functions derived from independent random variables, specifically examining the random variables X ~ N(5, 25) and Y ~ N(2, 16). The user seeks to find a function F of both X and Y that follows an F-distribution with parameters (1, 2). The key equation referenced is (X/n)/(Y/m) ~ F(n, m), which establishes the relationship between chi-square distributions and the F-distribution. The user questions whether the derived functions, specifically F = [(X-5)/5]^2 / {([(X-5)/5]^2 + [(Y-2)/4]^2)/2}, maintain independence, highlighting the need for proof of independence in this context.

PREREQUISITES
  • Understanding of normal distributions, specifically N(5, 25) and N(2, 16).
  • Familiarity with the properties of independent random variables.
  • Knowledge of chi-square distributions and their relationship to the F-distribution.
  • Basic statistical concepts of functions of random variables.
NEXT STEPS
  • Study the properties of functions of independent random variables in depth.
  • Learn about the derivation and application of the F-distribution in statistical analysis.
  • Explore proofs of independence for functions of random variables.
  • Investigate the implications of transformations on the independence of random variables.
USEFUL FOR

Statisticians, data analysts, and students studying probability theory who are interested in the behavior of functions derived from independent random variables and their distributions.

kingwinner
Messages
1,266
Reaction score
0

Homework Statement


Suppose the random variable X has a N(5,25) dsitribution and Y has a N(2,16) distribution and that X and Y are independent. Find a random variable F that is a function of both X and Y such that F has a F-distribution with parameters (1,2), i.e. F(1,2).


Homework Equations


Definition: If X~chi square(n), Y~chi square(m), and X and Y are independent, then (X/n)/(Y/m)~F(n,m)


The Attempt at a Solution


Does F=[(X-5)/5]^2 / {([(X-5)/5]^2 + [(Y-2)/4]^2])/2} work?
The only trouble I am seeing is that (X-5)/5]^2 and [(X-5)/5]^2 + (Y-2)/4]^2] might not be independent. So are they independent? If so, how can I prove it? If not, what else can I do?


Any stat guy here?
I appreciate for any help!
 
Physics news on Phys.org
In other words, we know that if X and Y are independent, then g(X) and h(Y) are independent, but are a function of X (f1(X)) and a function of X and Y (f2(X,Y)always independent?
 

Similar threads

  • · Replies 4 ·
Replies
4
Views
1K
Replies
8
Views
2K
Replies
2
Views
2K
Replies
2
Views
1K
Replies
6
Views
1K
Replies
2
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 8 ·
Replies
8
Views
2K
Replies
1
Views
2K
  • · Replies 6 ·
Replies
6
Views
2K