Scribd
Upload
8 views14 pages

05.02.the Continuous Case

The document discusses the joint probability density function (p.d.f.) of two continuous random variables, detailing the conditions that must be satisfied for a function to qualify as a joint p.d.f. It includes examples of calculating probabilities and marginal p.d.f.s, as well as concepts of independence and conditional p.d.f.s. Additionally, it provides methods for calculating expected values and practical examples related to joint p.d.f.s.

Uploaded by

batoulkhodor012
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views14 pages

05.02.the Continuous Case

The document discusses the joint probability density function (p.d.f.) of two continuous random variables, detailing the conditions that must be satisfied for a function to qualify as a joint p.d.f. It includes examples of calculating probabilities and marginal p.d.f.s, as well as concepts of independence and conditional p.d.f.s. Additionally, it provides methods for calculating expected values and practical examples related to joint p.d.f.s.

Uploaded by

batoulkhodor012
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 14

Pre-foundation Statistics

Abbas Alhakim

Joint Distribution if Two Random Variables


Part 2:
The continuous case
Continuous Case: Joint p.d.f.

A function of two random variables 𝑓(𝑥, 𝑦) is said to be the joint probability density
function of two random variables X and Y if and only if:
1) 𝑓 𝑥, 𝑦 ≥ 0 for all points (𝑥, 𝑦) in the plane
∞ ∞
2) ‫׬‬−∞ ‫׬‬−∞ 𝑓 𝑥, 𝑦 𝑑𝑥𝑑𝑦 = 1

3) P 𝑋, 𝑌 ∈ 𝐴 = ‫𝑥 𝑓 𝐴׭‬, 𝑦 𝑑𝑥𝑑𝑦 for any subdomain 𝐴 in the plane

3
Continuous Case: Joint p.d.f.

A function of two random variables 𝑓(𝑥, 𝑦) is said to be the joint probability density function of two random
variables X and Y if and only if:
1) 𝑓 𝑥, 𝑦 ≥ 0 for all points (𝑥, 𝑦) in the plane
∞ ∞
2) ‫׬‬−∞ ‫׬‬−∞ 𝑓 𝑥, 𝑦 𝑑𝑥𝑑𝑦 = 1

3) P 𝑋, 𝑌 ∈ 𝐴 = ‫𝑥 𝑓 𝐴׭‬, 𝑦 𝑑𝑥𝑑𝑦 for any subdomain 𝐴 in the plane

Observations:
1) To check that 𝑓(𝑥, 𝑦) is a joint p.d.f., only properties (1) and (2) need to be verified.
2) The third property relates 𝑓 to 𝑋 and 𝑌 in particular.
3) In two dimensions, typical shapes for A are rectangles, disks, triangles. But can be of any shape.
4) To calculate probability of an event, that is described in words, it must first be transformed into a
subdomain

4
Example

Let 𝑋 and 𝑌 have the joint pdf


𝑘𝑥𝑦; 𝑤ℎ𝑒𝑛 0 < 𝑥 < 1 𝑎𝑛𝑑 0 < 𝑦 < 1
𝑓 𝑥, 𝑦 = ቊ
0; 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
(a) Find 𝑘
(b) Find 𝑃[𝑋 < 𝑌]
ANSWERS:
1 1
(a) We need ‫׬‬0 ‫׬‬0 𝑓 𝑥, 𝑦 𝑑𝑥𝑑𝑦 = 1,
1 1 1 𝑥2 1
k ‫׬‬0 ‫׬‬0 𝑥𝑦𝑑𝑥𝑑𝑦 = k ‫׬‬0 𝑦 ቚ 𝑑𝑦 =𝑘 = 1. Thus k = 4
2 4

5
Example

Let X and Y have the joint pdf


4𝑥𝑦; 𝑤ℎ𝑒𝑛 0 < 𝑥 < 1 𝑎𝑛𝑑 0 < 𝑦 < 1
𝑓 𝑥, 𝑦 = ቊ
0; 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
ANSWERS:
1 𝑦
(b) 𝑃 𝑋 < 𝑌 = ‫׬‬0 ‫׬‬0 4𝑥𝑦𝑑𝑥𝑑𝑦
This integral evaluates to ½

Another argument: symmetry

6
Marginal pdf

We can recover the individual, univariate pdf of 𝑋 and 𝑌 from the joint pdf 𝑓(𝑥, 𝑦)
∞
Marginal pdf of 𝑋: 𝑓𝑋 𝑥 = ‫׬‬−∞ 𝑓 𝑥, 𝑦 𝑑𝑦
∞
Marginal pdf of 𝑌: 𝑓𝑌 𝑦 = ‫׬‬−∞ 𝑓 𝑥, 𝑦 𝑑𝑥

7
Independence of Two Continuous RV’s

Two continuous random variables 𝑋 and 𝑌 with joint pdf 𝑓 𝑥, 𝑦 are said to be
independent if

𝑓 𝑥, 𝑦 = 𝑓𝑋 𝑥 × 𝑓𝑌 𝑦

This needs to be true for all pairs (𝑥, 𝑦)


Interpretation: If 𝑋 and 𝑌 are continuous, then any knowledge of the value of one
of them does not alter or change our assessment of how the other is distributed

8
Conditional pdf of X given Y

If we learn that 𝑌 takes a specific value 𝑦, we can alter the entire distribution of 𝑋.
We get the conditional pdf of 𝑋|𝑌 = 𝑦
𝑓(𝑥, 𝑦)
𝑓𝑋|𝑌 𝑥|𝑦 =
𝑓𝑌 𝑦

𝑓(𝑥,𝑦)
Similarly, 𝑓𝑌|𝑋 𝑦|𝑥 =
𝑓𝑋 𝑥

9
Expected Values from Joint pdfs

Unconditional Expectations:
∞ ∞
𝐸 𝑋 = න න 𝑥𝑓 𝑥, 𝑦 𝑑𝑥𝑑𝑦
−∞ −∞
∞ ∞
𝐸 𝑌 =න න 𝑦𝑓 𝑥, 𝑦 𝑑𝑥𝑑𝑦
−∞ −∞

Conditional Expectations:
∞

𝐸 𝑋|𝑌 = 𝑦 = න 𝑥𝑓𝑋|𝑌 𝑥|𝑦 𝑑𝑥


−∞
∞

𝐸 𝑌|𝑋 = 𝑥 = න 𝑦𝑓𝑌|𝑋 𝑦|𝑥 𝑑𝑦


−∞

10
Joint pdf Example

The useful lifetimes, years, `of two components of a system have the following
𝑥𝑒 −𝑥 1+𝑦 ; 𝑥 ≥ 0 𝑎𝑛𝑑 𝑦 ≥ 0
joint pdf: 𝑓 𝑥, 𝑦 = ቊ
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒

a) Find 𝑃(𝑋 > 3)


b) Are 𝑋 and 𝑌 independent?
c) Find the probability that at least one lifetime exceeds 3 years

11
Joint pdf Example

To answer (a), we set it up as a two-fold integral:


∞ ∞ ∞ ∞
𝑃 𝑋 > 3 = න න 𝑥𝑒 −𝑥 1+𝑦
𝑑𝑦𝑑𝑥= න 𝑒 −𝑥 න 𝑥𝑒 −𝑥𝑦 𝑑𝑦𝑑𝑥
3 0 3 0
∞
= න 𝑒 −𝑥 𝑑𝑥
3
Which is 𝑒 −3 = 0.050

12
Joint pdf Example

To answer (b), we need to calculate the marginal densities of X and Y:


∞
𝑓𝑋 𝑥 = ‫׬‬0 𝑥𝑒 −𝑥 1+𝑦 𝑑𝑦 = 𝑒 −𝑥 for 𝑥 ≥ 0
∞ 1
𝑓𝑌 𝑦 = ‫׬‬0 𝑥𝑒 −𝑥 1+𝑦 𝑑𝑥 =
1+𝑦 2
for 𝑦 ≥ 0

13
Joint pdf Example

To answer (c), we will go to the complement:


𝑃 𝑋 > 3 𝑜𝑟 𝑌 > 3 = 1 − 𝑃(𝑋 ≤ 3 𝑎𝑛𝑑 𝑌 ≤ 3)
∞ ∞ 3 3
This is 1 − ‫׬‬3 ‫׬‬3 𝑥𝑒 −𝑥 1+𝑦 𝑑𝑦𝑑𝑥 = 1 − ‫׬‬0 ‫׬‬0 𝑥𝑒 −𝑥 𝑒 −𝑥𝑦 𝑑𝑦𝑑𝑥
3 −𝑥
=1− ‫׬‬0 𝑒 1 − 𝑒 −3𝑥 𝑑𝑦𝑑𝑥 = 𝑒 −3 + 0.25 − 0.25𝑒 −12 = 0.300

14

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy