This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: MA2216/ST2131 Probability Notes 8 Multidimensional Changes of Variables and Bivariate Normal Distribution § 1. Changes of Variables Let X 1 and X 2 be jointly distributed random variables with joint prob ability density function f X 1 ,X 2 . It is sometimes necessary to obtain the joint distribution of the random variables Y 1 and Y 2 , which arise as func tions of X 1 and X 2 . Specifically, suppose that Y 1 = g 1 ( X 1 ,X 2 ) and Y 2 = g 2 ( X 1 ,X 2 ) . For example, X 1 and X 2 are independent exponentially distributed ran dom variables, and we are interested to know the joint probability density function of Y 1 = X 1 + X 2 , and Y 2 = X 1 X 1 + X 2 . In this case, g 1 ( x 1 ,x 2 ) = x 1 + x 2 and g 2 ( x 1 ,x 2 ) = x 1 / ( x 1 + x 2 ) . (The details can be found in item 4 below.) Note. The above is a typical example of changeofvariables for a bi variate case. In item 6, we will also touch upon briefly the formula for change of variables for multivariate cases. 1 1. Assumptions: (i) Let X 1 and X 2 be jointly continuous random variables with known joint p.d.f. f X 1 ,X 2 ( x 1 ,x 2 ). (ii) Let Y 1 and Y 2 be given functions of X 1 and X 2 in the form: Y 1 = g 1 ( X 1 ,X 2 ) and Y 2 = g 2 ( X 1 ,X 2 ) . We can uniquely solve for x 1 and x 2 in terms of y 1 and y 2 with solutions given by, say, x 1 = h 1 ( y 1 ,y 2 ) and x 2 = h 2 ( y 1 ,y 2 ) . In other words, the inverse transformation exists. (iii) The functions g 1 and g 2 have continuous partial derivatives at all points ( x 1 ,x 2 ) and are such that the following 2 × 2 determinant J ( x 1 ,x 2 ) = fl fl fl fl fl fl fl ∂g 1 ∂x 1 ∂g 1 ∂x 2 ∂g 2 ∂x 1 ∂g 2 ∂x 2 fl fl fl fl fl fl fl = ∂g 1 ∂x 1 ∂g 2 ∂x 2 ∂g 1 ∂x 2 ∂g 2 ∂x 1 6 = 0 (1 . 1) at all points ( x 1 ,x 2 ). (Note that J ( x 1 ,x 2 ) is called the Jacobian .) Question: We would like to find the joint p.d.f. of Y 1 and Y 2 in terms of the joint p.d.f. f X 1 ,X 2 together with the transformations g 1 and g 2 . Conclusion: Under the above conditions, it can be shown that the random variables Y 1 and Y 2 are jointly continuous with joint p.d.f. given by f Y 1 ,Y 2 ( y 1 ,y 2 ) = 1  J ( x 1 ,x 2 )  f X 1 ,X 2 ( x 1 ,x 2 ) (1 . 2) where x 1 = h 1 ( y 1 ,y 2 ) and x 2 = h 2 ( y 1 ,y 2 ). 2 2. Example. Let X 1 and X 2 be jointly continuous random variables. Find the joint p.d.f. of Y 1 = X 1 + X 2 and Y 2 = X 1 X 2 . Sol. Generally speaking, one should first specify the transformation, which is in this example given below: y 1 = g 1 ( x 1 ,x 2 ) = x 1 + x 2 , y 2 = g 2 ( x 1 ,x 2 ) = x 1 x 2 . Second , determine the inverse transformation, which is expressible as follows: x 1 = h 1 ( y 1 ,y 2 ) = y 1 + y 2 2 , x 2 = h 2 ( y 1 ,y 2 ) = y 1 y 2 2 ....
View
Full
Document
This note was uploaded on 03/19/2012 for the course SCIENCE ST2131 taught by Professor Forgot during the Fall '08 term at National University of Singapore.
 Fall '08
 Forgot

Click to edit the document details