# 06derived - → 1-1) and diﬀerentiable function. 2a. Pr [...

This preview shows pages 1–2. Sign up to view the full content.

EECS 501 DERIVED DISTRIBUTIONS Fall 2001 Given: pdf f x ( X ) and function y = g ( x ). Goal: Compute pdf f y ( Y ). pmfs: p y ( Y ) = Pr [ y = Y ] = Pr [ g ( x ) = Y ] = Pr [ x g - 1 ( Y )] = g - 1 ( Y ) p x ( X ). Scale: y = ax f y ( Y ) = 1 | a | f x ( Y a ) so integrates to one. Compare to δ ( X ). Shift: y = x - b f y ( Y ) = f x ( Y + b ) just shift pdf. I. Method of events: Straightforward; g ( · ) need not be diﬀerentiable. 1. F y ( Y ) = Pr [ y Y ] = Pr [ g ( x ) Y ] = Pr [ x g - 1 ( { y : y Y } )]. 2. f y ( Y ) = d dY F y ( Y ) = d dY R X g - 1 ( { y : y Y } ) f x ( X ) dX . EX1: f x ( X ) = 1 2 , 0 < X < 2; 0 otherwise. y = g ( x ) = 1 /x . Compute f y ( Y ). 1. F y ( Y ) = Pr [ y Y ] = Pr [ 1 x Y ] = Pr [ x 1 Y ]. X < 2 Y > 1 2 . 2. F y ( Y ) = 1 2 (2 - 1 Y ) if Y > 1 2 0 if Y < 1 2 f y ( Y ) = 1 / (2 Y 2 ) if Y > 1 2 0 if Y < 1 2 . 3. Check: F y ( Y ) is continuous at Y = 1 2 ; F y ( -∞ ) = 0; F y ( ) = 1. EX2: Arbitrary f x ( X ). y = | x | . Compute f y ( Y ) in terms of f x ( X ). 1. F y ( Y ) = Pr [ y Y ] = Pr [ | x | ≤ Y ] = Pr [ - Y x Y ] = R Y - Y f x ( X ) dX . 2. f y ( Y ) = d dY R Y - Y f x ( X ) dX = f x ( Y ) + f x ( - Y ) ,Y 0; 0 if Y < 0. II. Jacobian method: Requires g ( · ) to be diﬀerentiable, but easier. 1. Suppose g ( · ) is any nondecreasing (

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: → 1-1) and diﬀerentiable function. 2a. Pr [ a < x < b ] = Pr [ g ( a ) < y < g ( b )] = R g ( b ) g ( a ) f y ( Y ) dY . 2b. Pr [ a < x < b ] = R b a f x ( X ) dX = R g ( b ) g ( a ) f x ( X = g-1 ( Y )) | dx/dy | dY . 2c. These are equal if f y ( Y ) = f x ( X = g-1 ( Y )) | dg-1 ( Y ) /dY | . EX1: y = 1 /x → X = g-1 ( Y ) = 1 /Y is decreasing and 1-1 for X,Y > 0. f y ( Y ) = | d (1 /Y ) dY | ‰ 1 2 if Y > 1 2 otherwise = ‰ 1 / (2 Y 2 ) if Y > 1 2 otherwise . EX2: Can’t use Jacobian since y = | x | not diﬀerentiable at x = 0....
View Full Document

## This note was uploaded on 07/22/2011 for the course EECS 370 taught by Professor Lehman during the Spring '10 term at University of Florida.

### Page1 / 2

06derived - → 1-1) and diﬀerentiable function. 2a. Pr [...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online