Transformations and joint pdf's

Click For Summary
SUMMARY

The discussion focuses on deriving the joint probability density function (pdf) of transformed random variables Y1 and Y2, defined as Y1 = X1X2 and Y2 = X1/X2, from the joint pdf fX1X2(x1,x2) of the original random variables X1 and X2. The transformation technique involves using the Jacobian determinant to generalize the single-variable case to multiple variables. The key equation utilized is fy(y) = f(g-1(y1,y2)) * |Jacobian[g-1(y1,y2)]|, where g represents the transformation function.

PREREQUISITES
  • Understanding of joint probability density functions (pdfs)
  • Familiarity with transformations of random variables
  • Knowledge of Jacobian determinants in multivariable calculus
  • Experience with calculus concepts related to variable substitution
NEXT STEPS
  • Study the derivation of joint pdfs using the Jacobian method
  • Learn about transformations of random variables in probability theory
  • Explore examples of multivariable transformations in statistical contexts
  • Review calculus techniques for changing variables in integrals
USEFUL FOR

Students and professionals in statistics, probability theory, and applied mathematics, particularly those working with random variable transformations and joint distributions.

6.28318531
Messages
51
Reaction score
0

Homework Statement



Let X1 and X2 be random variables having a joint pdf, fX1X2(x1,x2). Suppose that Y1=X1X2, and Y2=X1X2 Use the transformation result to derive an expression for the joint pdf of Y1 and Y2
in terms of that for X1 and X2

Homework Equations



The single random variable case

fy(y)=f[g-1(y)] |dg-1(y)/dy|
where g is our transformation


The Attempt at a Solution


So many subscripts,

Anyway I know the single variable case, so how do I generalise this to multiple random variables? Do much the same thing? Let g(Y1,Y2)= (X1 X2,X1/X2) , then what take ∇ .g-1? I'm not really sure how you generalise the derivative part,

Thanks,
 
Physics news on Phys.org
Think back to calculus when you changed variables from x and y to u=u(x,y) and v=v(x,y) in 2-dimensional integrals. You're doing the same thing here. You need to use the Jacobian.
 
I think I see what you mean
so fy(y)= f( g-1(y1,y2)) . Jacobian[ g-1(y1,y2)]
 

Similar threads

  • · Replies 9 ·
Replies
9
Views
5K
  • · Replies 26 ·
Replies
26
Views
3K
  • · Replies 8 ·
Replies
8
Views
2K
  • · Replies 16 ·
Replies
16
Views
2K
  • · Replies 5 ·
Replies
5
Views
3K
Replies
3
Views
2K
  • · Replies 8 ·
Replies
8
Views
4K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 11 ·
Replies
11
Views
2K