STAT 21613 Probability Distributions and Applications II

Chapter 1
Two Dimensional Random Variables

Let’s review what you have learnt in the first year.

1.0 Preliminaries:
Definition1: Probability Space
In probability theory, a probability space or a probability triple (Ω, 𝐹, p) is a mathematical construct
that models a real-world process (or “experiment”) consisting of states that occur randomly.
 A sample space, Ω (or S), which is the set of all possible outcomes of an experiment.
 A set of events F, where each event is a set containing zero or more outcomes.
 The assignment of probabilities to the events; that is, a function p from events to
probabilities.

Example: Consider a tossing a fair coin

Probability:

Random Variable:
Definition: A random variable, denoted by 𝑋 or 𝑋(∙) is a function with a sample space Ω as the
domain and the set of real numbers ℜ as the co-domain. The function 𝑋(∙) must be such that the set
𝐴𝑟 , defined by 𝐴𝑟 = {𝜔: 𝑋(𝜔) ≤ 𝑟}, belongs to the event space for-every real number r.

1
STAT 21613 Probability Distributions and Applications II
Example: Consider the experiment of tossing a single coin. Ω = {head, tail}, and 𝑋(𝜔) = 1 if 𝜔 =
head, and : 𝑋(𝜔) = 0 if 𝜔 = tail. Show that 𝑋(𝜔) satisfies the definition of random variable.
Discrete Random Variables
If the space of random variable X is countable, then X is called a discrete random variable.
 Every random variable characterized through its probability density function.

Ex. Discuss a few examples of discrete rvs and possible probability distributions.

Continuous Random Variables

The random variable X is defined as continuous random variable of the exists a non-negative
function defined on ℝ, having the property that and 𝐵 ⊆ ℝ

𝑃(𝑋 ∈ 𝐵) = ∫ 𝑓(𝑥)𝑑𝑥
𝑩
The function 𝑓(𝑥) is called the probability density function of the random variable X.

For you: Discuss a few examples continuous rvs and possible probability distributions.

Welcome to the new course!!!!

Section 1: Introduction to Two-dimensional Random Variables

In the study of many random experiments, there could be more than one random variable of interest.
 An educator may study the joint behaviour of grades and time devoted to study
 A physician may study the joint behaviour of blood pressure and weight
 An economist may study the joint behaviour of business volume and profit

For you: Think about some other scenarios which encounter bivariate/multivariate random variables

2
STAT 21613 Probability Distributions and Applications II
Definition 1
Let X and Y be two random variables defined on the same probability space (Ω, F, p). Then the
ordered pair (X, Y) is called a two-dimensional/bivariate random variable.
 Note: Two dimensional random variables are also called bivariate random variables as well.
 Depending on the random variable type, we get two dimensional discrete or continuous
random variables

Definition 2
A two-dimensional/Bivariate random variable (X, Y) is set to be a two-dimensional/Bivariate
discrete random variable if it can assume values only at a countable number of points (x, y) in two-
dimensional real space. We also say that the random variables X, Y are jointly discrete random
variables.

Example 1 Roll a pair of unbiased dice. Let X denotes the smaller and
Y denotes the larger outcome on the dice.
i. What is the Sample Space?
ii. What are the possible (X,Y) pair values
iii. Compute the joint probability for the event {𝑋 = 2, 𝑌 = 3}

Solution:
(i) Sample space,

(ii) Possible (X,Y) values:

(iii) There are two outcomes namely (2, 3) and (3, 2) in the sample S of 36 outcomes
which contribute to the joint event (X = 2, Y = 3).

3
STAT 21613 Probability Distributions and Applications II
Section 2: Joint Distributions of Discrete Variables
If X and Y are two discrete random variables, the probability distribution for their simultaneous
occurrence can be represented by a function with values f(x, y) for any pair of values (x, y)
within the range of the random variables X and Y . It is customary to refer to this function as the
joint probability distribution of X and Y .

Definition 3

Example 1 ctd: Joint discrete probability density function

Example 2: Two ballpoint pens are selected at random from a box that
contains 3 blue pens, 2 red pens, and 3 green pens.

X is the number of blue pens selected

Y is the number of red pens selected,

4
STAT 21613 Probability Distributions and Applications II
The possible pairs of values (x, y) are (0, 0), (0, 1), (1, 0), (1, 1), (0, 2), and (2, 0)

Compute f(0,1)

f(0, 1), represents the probability that a red and a green pens are selected. The total number of equally likely
ways of selecting any 2 pens from the 8 is 28. The number of ways of selecting 1 red from 2 red pens and 1
green from 3 green pens = 6

Example 3
A group of 9 executives of a certain firm include 4 who are married,3 who never married, and 2 who
are divorced. Three of the executives are to be selected for promotion. Let X denote the number pf
married executives and Y the number of never married executives among the 3 selected for
promotions. Assuming that the three are randomly selected from the nine available, what is the joint
probability density function of the random variable X and Y?
Answer:
9
The number of ways we can chose 3 out of 9 is ( ) which is 84. Thus
3
0
𝑓(0,0) = 𝑃(𝑋 = 0, 𝑌 = 0) = =0
84
4 3 2
( )( )( ) 4
𝑓(1,0) = 𝑃(𝑋 = 1, 𝑌 = 0) = 1 0 2 =
84 84
4 3 2
( ) ( ) ( ) 12
𝑓(2,0) = 𝑃(𝑋 = 2, 𝑌 = 0) = 2 0 1 =
84 84
4 3 2
( )( )( ) 4
𝑓(3,0) = 𝑃(𝑋 = 3, 𝑌 = 0) = 4 0 0 =
84 84
By continuing same procedure, you can calculate the all probabilities of the possible outcomes.

5
STAT 21613 Probability Distributions and Applications II
 Probabilities for all outcomes:

Marginal Discrete Density

Given the joint probability distribution f(x, y) of the discrete random variables X and Y , the
probability distribution g(x) of X alone is obtained by summing f(x, y) over the values of Y .
Similarly, the probability distribution h(y) of Y alone is obtained by summing f(x, y) over the
values of X.

Definition 4

Example: Find the marginal distribution of X and Y for the following joint discrete distribution.

6
STAT 21613 Probability Distributions and Applications II

P(X = 0) = ∑ 𝑓(0, 𝑦) =

Example 4: If the Joint probability density function of the discrete random variable X and Y is given
by

then what are marginal of X and Y?

Answer: The marginal of X can be obtained by summing the joint probability density function
𝑓(𝑥, 𝑦) for all y values in the range space 𝑆𝑌 of the random variable Y. That is
𝑓𝑋 (𝑥) = ∑ 𝑓(𝑥. 𝑦)
𝑦∈𝑆𝑌
6

= ∑ 𝑓(𝑥, 𝑦)
𝑦=1

= 𝑓(𝑥. 𝑥) + ∑ 𝑓(𝑥. 𝑦) + ∑ 𝑓(𝑥. 𝑦)

𝑦>𝑥 𝑦<𝑥
1 2
= + (6 − 𝑥) +0
36 36
1
= (13 − 2𝑥), 𝑥 = 1,2, … ,6
36

Similar, one can obtain the marginal probability density of Y by summing over for all x values.
Hence.
𝑓2 (𝑦) = ∑ 𝑓(𝑥. 𝑦)
𝑥∈𝑅𝑋

7
STAT 21613 Probability Distributions and Applications II
6

= ∑ 𝑓(𝑥, 𝑦)
𝑥=1
= 𝑓(𝑦. 𝑦) + ∑ 𝑓(𝑥. 𝑦) + ∑ 𝑓(𝑥. 𝑦)
𝑥<𝑦 𝑥>𝑦
1 2
= + (𝑦 − 1) + 0
36 36
1
= (2𝑦 − 1), 𝑦 = 1,2, … ,6
36

Example 5: Let X and Y be discrete random variables with joint probability density function.
1
𝑓(𝑥, 𝑦) = {21 (𝑥 + 𝑦) 𝑖𝑓 𝑥 = 1,2; 𝑦 = 1,2,3
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒
What are the marginal density functions of X and Y?

Answer:
The marginal of X is given by
3
1
𝑓1 (𝑥) = ∑ (𝑥 + 𝑦)
21
𝑦=1
1 1
= 3𝑥 + [1 + 2 + 3]
21 21
𝑥+2
= , 𝑥 = 1,2.
7
Similarly, the marginal of Y is given by
2
1
𝑓2 (𝑦) = ∑ (𝑥 + 𝑦)
21
𝑥=1
2𝑦 3
= +
21 21
3+2𝑦
= , 𝑦 = 1,2,3
21

Example 6: For what values of the constant k the function given by

𝑘𝑥𝑦 𝑖𝑓 𝑥 = 1,2,3; 𝑦 = 1,2,3
𝑓(𝑥, 𝑦) = {
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒
is a joint probability density function of some random variables of X and Y?

Answer: Since
3 3

1 = ∑ ∑ 𝑓(𝑥, 𝑦)
𝑥=1 𝑦=1

8
STAT 21613 Probability Distributions and Applications II
3 3

= ∑ ∑ 𝑘𝑥𝑦
𝑥=1 𝑦=1
= 𝑘[1 + 2 + 3 + 2 + 4 + 6 + 3 + 6 + 9]
= 36𝑘
Hence, 𝑘 = 1/36

Compute the marginal density distributions.

Section 3: Cumulative distribution function of two random variables

Definition 5
Let X and Y be two random variables defined on the same probability space ( Ω, 𝐹 , P [.]).

Then the joint cumulative probability distribution of X and Y, denoted by 𝐹𝑋,𝑌 (𝑥, 𝑦), is defined as
𝐹𝑋,𝑌 (𝑥, 𝑦) = P(𝑋 ≤ 𝑥, 𝑌 ≤ 𝑦), 𝑓𝑜𝑟 𝑎𝑛𝑦 (𝑥, 𝑦) ∈ ℝ2

Example 7: Consider the following joint probability distribution. Compute ) 𝐹𝑋,𝑌 (1,1) and F(2,1)

𝐹𝑋,𝑌 (1,1) = 𝑓(0,0) + 𝑓(0,1) + 𝑓(1,0) + 𝑓(1,1) = 17/18

9
STAT 21613 Probability Distributions and Applications II

Lets
Recall
CDF for
the
Univariate
case

Properties of Bivariate Cumulative Distribution Function.

Let 𝐹𝑋,𝑌 (𝑥, 𝑦) be the bivariate cumulative distribution function of the two variables X and Y.

𝑙𝑖𝑚
(i) (a) 𝐹𝑋,𝑌 (−∞, 𝑦) = 𝑥→−∞ 𝐹𝑋,𝑌 (𝑥, 𝑦) = 0 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑦 ∈ ℜ
𝑙𝑖𝑚
(b) 𝐹𝑋,𝑌 (𝑥, −∞) = 𝑦→−∞𝐹𝑋,𝑌 (𝑥, 𝑦) = 0 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑥 ∈ ℜ
𝑙𝑖𝑚
(c) 𝐹𝑋,𝑌 (∞, ∞) = 𝑦→∞ 𝐹𝑋,𝑌 (𝑥, 𝑦) = 1
𝑥→∞

𝑙𝑖𝑚
(ii) (a) 𝐹𝑋,𝑌 (∞, 𝑦) = 𝑥→∞ 𝐹𝑋,𝑌 (𝑥, 𝑦) = 𝐹𝑌 (𝑦) 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑦 ∈ ℜ
𝐹𝑌 (𝑦) is known as the marginal cumulative probability distribution function of Y.

𝑙𝑖𝑚
(b) 𝐹𝑋,𝑌 (𝑥, ∞) = 𝑦→∞ 𝐹𝑋,𝑌 (𝑥, 𝑦) = 𝐹𝑋 (𝑥) 𝑓𝑜𝑟 𝑎𝑙𝑙 𝑥 ∈ ℜ
𝐹𝑋 (𝑥) is known as the marginal cumulative probability distribution function of X.

(iii) If 𝑥1 < 𝑥2 and 𝑦1 < 𝑦2 then

𝑃[𝑥1 < 𝑋 ≤ 𝑥2 , 𝑦1 < 𝑌 ≤ 𝑦2 ] = 𝐹𝑋,𝑌 (𝑥2 , 𝑦2 ) − 𝐹𝑋,𝑌 (𝑥2 , 𝑦1 )−𝐹𝑋,𝑌 (𝑥1 , 𝑦2 )+𝐹𝑋,𝑌 (𝑥1 , 𝑦1 ) ≥ 0

(iv) 𝐹𝑋,𝑌 (𝑥, 𝑦) is right continuous in each argument.

𝑙𝑖𝑚 𝑙𝑖𝑚
𝑖. 𝑒 0<ℎ→0 𝐹𝑋,𝑌 (𝑥 + ℎ, 𝑦) = 0<ℎ→0 𝐹𝑋,𝑌 (𝑥, 𝑦 + ℎ) = 𝐹𝑋,𝑌 (𝑥, 𝑦)

Lets
Recall
PDF for
the
Univariate
case

10
STAT 21613 Probability Distributions and Applications II

Section 4: Two-dimensional Continuous Random Variables

Definition 6
The two dimensional random variable (X,Y) is defined to be two dimensional continuous if there
exists a function f(.,.) such that
𝑥 𝑦
𝐹𝑋,𝑌 (𝑥, 𝑦) = ∫ ∫ 𝑓(𝑢, 𝑣)𝑑𝑢 𝑑𝑣
−∞ −∞

for all x,y.

The function 𝑓(𝑥, 𝑦) is defined to be the joint probability density function (joint pdf).
The joint probability density function (joint pdf) of two continuous-type random variables is an
integrable function f(x, y) with the following properties.

By fundamental theorem of calculus:

When 𝐹𝑋,𝑌 (𝑥, 𝑦) = P[X ≤ x, Y ≤ 𝑦] is given, 𝑓𝑋,𝑌 (𝑥, 𝑦) can be
obtained from
𝜕 2 𝐹𝑋,𝑌 (𝑥, 𝑦)
𝑓𝑋,𝑌 (𝑥, 𝑦) =
𝜕𝑦𝜕𝑥

11
STAT 21613 Probability Distributions and Applications II
Technical Version of the definition:
Definition 7: Let (X, Y) be a two-dimensional random variable. If there exists a function f(x,y) such
that

for any (𝑥, 𝑦) ∈ ℛ2 and 𝑓𝑋,𝑌 (𝑥, 𝑦) ≥ 0 for all (𝑥, 𝑦) ∈ ℛ2 then, 𝑓𝑋,𝑌 (𝑥, 𝑦) is said to be joint
probability density function of (X, Y).

 Let f X ,Y ( x, y) be joint probability function of (X, Y) and A be some region in 2 , then

P( X , Y )  A   f X ,Y ( x, y )dxdy
( x , y )A

i.e, the probability that (X, Y) lies in R is the volume under the surface is f X ,Y ( x, y) over the region
R.

Example: If the joint cumulative distribution function of X and Y is given by

3
1 2 2
𝐹(𝑥, 𝑦) = {5 (2𝑥 𝑦 + 3𝑥 𝑦 ) 𝑓𝑜𝑟 0 < 𝑥, 𝑦 < 1;
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒

Then what is the joint density of X and Y?

Answer:

1 𝜕 𝜕
𝑓(𝑥, 𝑦) = (2𝑥 3 𝑦 + 3𝑥 2 𝑦 2 )
5 𝜕𝑥 𝜕𝑦

1 𝜕
= (2𝑥 3 + 6𝑥 2 𝑦)
5 𝜕𝑥
1
= (6𝑥 2 + 12𝑥𝑦)
5

6 2
= (𝑥 + 2𝑥𝑦)
5

Hence, the joint density of X and Y is given by

12
STAT 21613 Probability Distributions and Applications II

6 2
(𝑥 + 2𝑥𝑦) 𝑓𝑜𝑟 0 < 𝑥, 𝑦 < 1
𝑓(𝑥, 𝑦) = {5
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒,

Example 8:

A privately owned business operates both a drive-in facility and a walk-in facility.
On a randomly selected day, let X and Y , respectively, be the proportions of the
time that the drive-in and the walk-in facilities are in use, and suppose that the
joint density function of these random variables is

Verify the first two conditions.

Solution: Page 97 Walepole book

X = the proportions of the time that the drive-in facilitiy is in use

Y = the proportions of the time that the walk-in facilitity is in use

13
STAT 21613 Probability Distributions and Applications II

Example 9: Let the joint density function of X and Y be given by

2
𝑓(𝑥, 𝑦) = {𝑘𝑥𝑦 𝑖𝑓 0 < 𝑥 < 𝑦 < 1
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒
What is the value of constant k?

14
STAT 21613 Probability Distributions and Applications II
Example 10: Let the joint density of the continuous random variables X and Y be
6 2
𝑓(𝑥, 𝑦) = {5 (𝑥 + 2𝑥𝑦) 𝑖𝑓 0 ≤ 𝑥 ≤ 1; 0 ≤ 𝑦 ≤ 1
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒
What is the probability of event (𝑋 ≤ 𝑌)?

Answer: Let 𝐴 = (𝑋 ≤ 𝑌),we want to find;

𝑃(𝐴) = ∫ ∫ 𝑓(𝑥, 𝑦)𝑑𝑥𝑑𝑦

𝐴
1 𝑦
6 2
= ∫ [∫ (𝑥 + 2𝑥𝑦)𝑑𝑥 𝑑𝑦]
0 0 5
6 1 𝑥3 𝑥=𝑦
= ∫ [ + 𝑥 2] 𝑑𝑦
5 0 3 𝑥=0
6 14
= ∫ 𝑦 3 𝑑𝑦
5 0 3
2
= [𝑦 4 ]10
5
2
=
5

15
STAT 21613 Probability Distributions and Applications II
Marginal Probability Density Function (Continuous Case)
Definition 8:
Let f X ,Y ( x, y) be the joint probability function of (X,Y). Then,

 f X ( x)  f

X ,Y ( x, y )dy is called the marginal probability function of X and


 fY ( y )  f

X ,Y ( x, y )dx is called the marginal probability function of Y.

Example 11:

Find the marginal pdfs

Example 12: Find the Marginal PDFs of the joint PDF given in Example 9.
2
𝑓(𝑥, 𝑦) = {10𝑥𝑦 𝑖𝑓 0 < 𝑥 < 𝑦 < 1
0 𝑜𝑡ℎ𝑒𝑤𝑖𝑠𝑒

16
STAT 21613 Probability Distributions and Applications II
More Problems

Example 13: Let X and Y have the joint density function

2𝑥 𝑓𝑜𝑟 0 < 𝑥 < 1; 0 < 𝑦 < 1

𝑓(𝑥, 𝑦) = {
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒,
1
What is 𝑃 (𝑋 + 𝑌 ≤ 1 /𝑋 ≤ )?
2

Answer: (See the diagram below)

1
1 𝑃[(𝑋 + 𝑌 ≤ 1) ∩ (𝑋 ≤ )
𝑃 (𝑋 + 𝑌 ≤ 1 /𝑋 ≤ ) = 2
2 1
𝑃 (𝑋 ≤ )
2
1/2 1/2 1 1−𝑦
∫0 [∫0 2𝑥𝑑𝑥]𝑑𝑦 + ∫1/2[∫0 2𝑥𝑑𝑥]𝑑𝑦
= 1 1/2
∫0 [∫0 2𝑥𝑑𝑥] 𝑑𝑦

1
=6
1
4
2
=
3

Example 14: Let X and Y have the joint density function

17
STAT 21613 Probability Distributions and Applications II
𝑥+𝑦 𝑓𝑜𝑟 0 ≤ 𝑥 ≤ 1; 0 ≤ 𝑦 ≤ 1
𝑓(𝑥, 𝑦) = {
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒,

What is 𝑃(2𝑋 ≤ 1|𝑋 + 𝑌 ≤ 1 )?

Answer: We Know that

1
𝑃[(𝑋 ≤ ) ∩ (𝑋 + 𝑌 ≤ 1)]
𝑃(2𝑋 ≤ 1/ 𝑋 + 𝑌 ≤ 1) = 2
𝑃(𝑋 + 𝑌 ≤ 1)
1 1−𝑥
𝑃(𝑋 + 𝑌 ≤ 1) = ∫ [∫ (𝑥 + 𝑦)𝑑𝑦 ] 𝑑𝑥
0 0

1
𝑥 2 𝑥 3 (1 − 𝑥)3
= [ − − ]
2 3 6 0

2 1
= =
6 3

Similarly
1/2 1−𝑥
1
𝑃 [(𝑋 ≤ ) ∩ (𝑋 + 𝑌 ≤ 1)] = ∫ ∫ (𝑥 + 𝑦)𝑑𝑦𝑑𝑥
2 0 0

1/2
𝑥 2 𝑥 3 (1 − 𝑥)3
= [ − − ]
2 3 6 0

11
=
48

Thus
11 3 11
𝑃(2𝑋 ≤ 1/ 𝑋 + 𝑌 ≤ 1) = ( ) ( ) =
48 1 16

18
STAT 21613 Probability Distributions and Applications II
Example:

The joint cumulative distribution function for vector random variable 𝑋 = (𝑥, 𝑦) is given by
(1 − 𝑒 −𝛼𝑥 )(1 − 𝑒 −𝛽𝑦 ) 𝑓𝑜𝑟 𝑥 ≥ 0 ; 𝑦 ≥ 0
𝐹𝑋,𝑌 (𝑥, 𝑦) = {
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
Find the marginal cumulative distribution functions of 𝑋 and 𝑌.

19