Probability distribution function

Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Continuous Random Variables

Dr. Mohamed Kobeissi

January 21, 2021

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Probability distribution function

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

A continuous random variable is a variable whose values are

within an interval (a, b), with a, b ∈ R ∪ {∞}

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

The probability distribution function (pdf), or density, f (x) of

a continuous random variable X satisfy the following
properties:
a) f (x) ≥ 0 for all x in (a, b)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

The probability distribution function (pdf), or density, f (x) of

a continuous random variable X satisfy the following
properties:
a) f (x) ≥ 0 for all x in (a, b)
Z
b) f (x) dx = 1
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

The probability distribution function (pdf), or density, f (x) of

a continuous random variable X satisfy the following
properties:
a) f (x) ≥ 0 for all x in (a, b)
Z
b) f (x) dx = 1
R R
c) P(X ∈ A) = A f (x) dx , for every interval A ∈ R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

The cumulative distribution function (cdf) of a random

variable X is defined by:
Z x
FX (x) = P(X ≤ x) = f (t)dt
−∞

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

The cumulative distribution function (cdf) of a random

variable X is defined by:
Z x
FX (x) = P(X ≤ x) = f (t)dt
−∞

The pdf and the cdf of a random variable of X are related by

the formula:
f (x) = FX0 (x)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2

- P(X < 1/2) =

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2
Z 1/2
- P(X < 1/2) = 2xdx = 1/4
0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2
Z 1/2
- P(X < 1/2) = 2xdx = 1/4
0
Z x
- F (x) = P(X ≤ x) = f (t) dt =
−∞

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2
Z 1/2
- P(X < 1/2) = 2xdx = 1/4
0 
Z x  0 x <0
- F (x) = P(X ≤ x) = f (t) dt =
−∞ 

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2
Z 1/2
- P(X < 1/2) = 2xdx = 1/4
0 
Z x  0 x <0
- F (x) = P(X ≤ x) = f (t) dt = x2 0 < x < 1
−∞ 

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Definition
Mathematical expectation
Probability Density
Usual Continuous Random Variables
Cumulative distribution function
Transformation of Random Variables

Example

Let X be a random variable whose density is

f (x) = cx , 0 < x < 1
Z 1
c
- f is a pdf, hence cxdx = = 1 ⇒ c = 2
0 2
Z 1/2
- P(X < 1/2) = 2xdx = 1/4
0 
Z x  0 x <0
- F (x) = P(X ≤ x) = f (t) dt = x2 0 < x < 1
−∞ 
1 x >1

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Mathematical expectation

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

The mean (expected value, average) of a continuous random

variable X , denoted E (X ) (or µ), is defined by:
Z
E (X ) = xf (x) dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

In the previous example,

Z 1
E (X ) = 2x 2 dx
0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

In the previous example,

Z 1  1
2
E (X ) = 2x dx = x 3
2
0 3 0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

In the previous example,

Z 1  1
2
E (X ) = 2x dx = x 3
2
= 2/3
0 3 0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

The expectation of g (X ), where g is ”any” function, is

defined by: Z
E (g (X )) = g (x)f (x) dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Linearity of E (X )

If X is a continuous random variable, with pdf f (x), then

E (aX + b) = aE (X ) + b , a, b ∈ R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Linearity of E (X )

If X is a continuous random variable, with pdf f (x), then

E (aX + b) = aE (X ) + b , a, b ∈ R

proof:
E (aX + b) =

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Linearity of E (X )

If X is a continuous random variable, with pdf f (x), then

E (aX + b) = aE (X ) + b , a, b ∈ R

proof: Z
E (aX + b) = (ax + b)f (x)dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Linearity of E (X )

If X is a continuous random variable, with pdf f (x), then

E (aX + b) = aE (X ) + b , a, b ∈ R

proof: Z Z Z
E (aX + b) = (ax + b)f (x)dx = a xf (x)dx + b f (x)dx
R R R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Linearity of E (X )

If X is a continuous random variable, with pdf f (x), then

E (aX + b) = aE (X ) + b , a, b ∈ R

proof: Z Z Z
E (aX + b) = (ax + b)f (x)dx = a xf (x)dx + b f (x)dx
R R R

= aE (X ) + b

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Defining Formula

The variance of X , denoted Var (X ) (or σ 2 ) is defined by

h i
2
Var (X ) = E (X − E (X ))

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Defining Formula

The variance of X , denoted Var (X ) (or σ 2 ) is defined by

h i
2
Var (X ) = E (X − E (X ))

For a continuous random variable X with pdf f (x):

Z
Var (X ) = (x − E (X ))f (x)dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Computing Formula

The variance of a random variable X can be computed by the

formula:
Var (X ) = E (X 2 ) − [E (X )]2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Computing Formula

The variance of a random variable X can be computed by the

formula:
Var (X ) = E (X 2 ) − [E (X )]2
proof:

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Properties of the Variance

If X is a continuous random variable, and a, b are real

numbers, then:
a) Var (X ) ≥ 0; moreover Var (X ) = 0 iff X = E (X )
b) Var (aX + b) = a2 Var (X )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Standard deviation

The standard deviation of a continuous random variable X ,

denoted σ, is the square root of the variance of X , i.e
p
σ(X ) = Var (X )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Standard deviation

The standard deviation of a continuous random variable X ,

denoted σ, is the square root of the variance of X , i.e
p
σ(X ) = Var (X )

It is simple to check that

σ(aX + b) = |a|σ(X )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Example 1, continue

For a random variable X with density

f (x) = 2x , 0 < x < 1

Calculate E (3X − 1), E (X 2 ), Var (X ), and Var (2X + 6)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1
2
E (X ) = 2x 3 dx
0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2
0 0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2 = 1/2
0 0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2 = 1/2
0 0

hence Var (X ) = E (X 2 ) − (E (X ))2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2 = 1/2
0 0

1 4 1
hence Var (X ) = E (X 2 ) − (E (X ))2 = 2
− 9
= 18

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2 = 1/2
0 0

1 4 1
hence Var (X ) = E (X 2 ) − (E (X ))2 = 2
− 9
= 18

therefore Var (2X + 6) = 4Var (X )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

E (3X − 1) = 3E (X ) − 1 = 3 ∗ 23 − 1 = 1
Z 1 h i1
2 3 4
E (X ) = 2x dx = x /2 = 1/2
0 0

1 4 1
hence Var (X ) = E (X 2 ) − (E (X ))2 = 2
− 9
= 18

therefore Var (2X + 6) = 4Var (X ) = 4/18 = 2/9

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Moments

The moments of order n of a random variable X are defined

by E (X n ):

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Moments

The moments of order n of a random variable X are defined

by E (X n ): Z
n
E (X ) = x n f (x) dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Moments

The moments of order n of a random variable X are defined

by E (X n ): Z
n
E (X ) = x n f (x) dx
R

E (X ) is the moment of order 1 of X

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Moment Generating Function

The moment generating function (mgf) of a random variable

X , denoted GX , is defined by:

GX (s) = E (e sX )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mean of a random variable
Mathematical expectation
Mean of a function of random variable
Usual Continuous Random Variables
Variance
Transformation of Random Variables

Moment Generating Function

The moment generating function (mgf) of a random variable

X , denoted GX , is defined by:
Z
sX
GX (s) = E (e ) = e sx f (x) dx
R

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Usual Continuous Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

The uniform distribution

A random variable X whose density is:

1
f (x) = , a<x <b
b−a
is called uniform distribution over the interval (a, b), denoted
U(a, b)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z x
F (x) = f (t) dt
−∞

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
x
Z 

F (x) = f (t) dt =
−∞ 



Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1 x−a
F (x) = f (t) dt = a b−a
dt = b−a
a<x <b
−∞ 



Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1 x−a
F (x) = f (t) dt = a b−a
dt = b−a
a<x <b
−∞ 
 1 x >b


Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1 x−a
F (x) = f (t) dt = a b−a
dt = b−a
a<x <b
−∞ 
 1 x >b

Z b
x
E (X ) = dx
a b−a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1 x−a
F (x) = f (t) dt = a b−a
dt = b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2

x
E (X ) = dx =
a b−a 2(b − a) a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x
E (X ) = dx = =
a b−a 2(b − a) a 2(b − a)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x a+b
E (X ) = dx = = =
a b−a 2(b − a) a 2(b − a) 2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x a+b
E (X ) = dx = = =
a b−a 2(b − a) a 2(b − a) 2

b
x2
Z
2
E (X ) = dx
a b−a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x a+b
E (X ) = dx = = =
a b−a 2(b − a) a 2(b − a) 2

b b
x2 x3
Z 
2
E (X ) = dx =
a b−a 3(b − a) a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x a+b
E (X ) = dx = = =
a b−a 2(b − a) a 2(b − a) 2

b b
x2 x3 b 3 − a3
Z 
2
E (X ) = dx = =
a b−a 3(b − a) a 3(b − a)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables


 0 x <a
Z x 
 Rx 1
F (x) = f (t) dt = a b−a
dt = x−a
b−a
a<x <b
−∞ 
 1 x >b

Z b b
x2 b 2 − a2

x a+b
E (X ) = dx = = =
a b−a 2(b − a) a 2(b − a) 2

b b
x2 x3 b 3 − a3
Z 
2
E (X ) = dx = =
a b−a 3(b − a) a 3(b − a)
b 2 + ab + b 2
=
3

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Var (X ) = E (X 2 ) − (E (X ))2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

b 2 + ab + b 2 (b + a)2
Var (X ) = E (X 2 ) − (E (X ))2 = −
3 4

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

b 2 + ab + b 2 (b + a)2
Var (X ) = E (X 2 ) − (E (X ))2 = −
3 4
2
(b − a)
=
12

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

b 2 + ab + b 2 (b + a)2
Var (X ) = E (X 2 ) − (E (X ))2 = −
3 4
2
(b − a)
=
12

b
xn
Z
n
E (X ) = dx
a b−a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

b 2 + ab + b 2 (b + a)2
Var (X ) = E (X 2 ) − (E (X ))2 = −
3 4
2
(b − a)
=
12

b b
xn x n+1
Z 
n
E (X ) = dx =
a b−a n + 1(b − a) a

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

b 2 + ab + b 2 (b + a)2
Var (X ) = E (X 2 ) − (E (X ))2 = −
3 4
2
(b − a)
=
12

b b
xn x n+1 b n+1 − an+1
Z 
n
E (X ) = dx = =
a b−a n + 1(b − a) a (n + 1)(b − a)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

15 trains arrive at a train station between 10 and 11 am. Find

the expected number of trains that arrive between 10:15 and
10:25 am

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

The exponential distribution

A variable Y whose pdf (density) is:

1 −y /θ
f (y ) = e , 0<y <∞
θ
is called exponential distribution with parameter θ > 0,
denoted E(θ)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y 
0 y ≤0
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y 
0 y ≤0
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞ 1 − e −y /θ y ≥0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y 
0 y ≤0
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞ 1 − e −y /θ y ≥0

Z ∞
1 −y /θ
E (Y ) = ye dy
0 θ

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y 
0 y ≤0
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞ 1 − e −y /θ y ≥0

Z ∞
1 −y /θ ∞
dy = −y e −y /θ − θ e −y /θ 0

E (Y ) = ye
0 θ

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z y 
0 y ≤0
F (y ) = P(Y ≤ y ) = f (t) dt =
−∞ 1 − e −y /θ y ≥0

Z ∞
1 −y /θ ∞
dy = −y e −y /θ − θ e −y /θ 0 = θ

E (Y ) = ye
0 θ

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z ∞
2 1 2 −y /θ
E (Y ) = y e dy
0 θ

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z ∞
2 1 2 −y /θ
E (Y ) = y e dy =
 2 −y /θ 0 θ −y /θ ∞
−y e − 2θy e − 2θ2 e −y /θ 0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z ∞
2 1 2 −y /θ
E (Y ) = y e dy =
 2 −y /θ 0 θ −y /θ ∞
−y e − 2θy e − 2θ2 e −y /θ 0 = 2θ2 ;

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Z ∞
2 1 2 −y /θ
E (Y ) = y e dy =
 2 −y /θ 0 θ −y /θ ∞
−y e − 2θy e − 2θ2 e −y /θ 0 = 2θ2 ;
hence Var (Y ) = θ2

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

The lifetime X (in hours) of type A electrical bulb is an

exponential random variable with pdf
1 −x/800
f (x) = e , 0<x <∞
800

a) Find the probability that a type A bulb lasts for at least

950 h
b) Find the expected lifetime of type A bulbs

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

The Gamma function

Z ∞
For α > 0, define Γ(α) = x α−1 e −x dx
0
a) Use integration by part to express Γ(α) in terms of
Γ(α − 1)
b) Show that Γ(α) = (α − 1)!

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

The Gamma distribution

A variable X whose pdf (density) is:

1
f (x) = x α−1 e −x/θ , 0 < x < ∞
Γ(α)θα

is called gamme distribution with parameter α and θ, denoted

G (α, θ)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
The uniform distribution
Mathematical expectation
The exponential distribution
Usual Continuous Random Variables
The Gamma distribution
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Transformation of Random Variables

Let X be a random variable with pdf fX (x), and let Y = g (X )

be a function of X (Y is called transformation of X )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Transformation of Random Variables

Let X be a random variable with pdf fX (x), and let Y = g (X )

be a function of X (Y is called transformation of X )

question: what is the pdf of Y ?

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Proposition: If g is one-to-one, then the pdf of Y is given by:

fY (y ) = fX (g −1 (y )) × |(g −1 (y ))0 |

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y ) = P(g (X ) ≤ y )

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y ) = P(g (X ) ≤ y ) = P(X ≤ g −1 (y ))

(cause g is one-to-one)

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y ) = P(g (X ) ≤ y ) = P(X ≤ g −1 (y ))

(cause g is one-to-one)
hence FY (y ) = FX (g −1 (y ))

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y ) = P(g (X ) ≤ y ) = P(X ≤ g −1 (y ))

(cause g is one-to-one)
hence FY (y ) = FX (g −1 (y ))
therefore

fY (y ) = FY0 (y ) = FX0 (g −1 (y ))

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

proof: FY (y ) = P(Y ≤ y ) = P(g (X ) ≤ y ) = P(X ≤ g −1 (y ))

(cause g is one-to-one)
hence FY (y ) = FX (g −1 (y ))
therefore

fY (y ) = FY0 (y ) = FX0 (g −1 (y )) = fX (g −1 (y )) × (g −1 (y ))0

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one;

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[;

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[

g −1 (y ) = 1 − y 1/3 ,

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[
1
g −1 (y ) = 1 − y 1/3 , and (g −1 (y ))0 = − 2/3
3y

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[
1
g −1 (y ) = 1 − y 1/3 , and (g −1 (y ))0 = − 2/3
3y
therefore
1
h(y ) = 3[1 − (1 − y 1/3 )]2 × | 2/3 |
3y

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[
1
g −1 (y ) = 1 − y 1/3 , and (g −1 (y ))0 = − 2/3
3y
therefore
1
h(y ) = 3[1 − (1 − y 1/3 )]2 × | 2/3 | = 1 , 0 < y < 1
3y

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Example
Let X be a random variable with pdf
f (x) = 3(1 − x)2 , 0 < x < 1. Find the pdf of Y = (1 − X )3

solution: The function g (x) = (1 − x)3 is one-to-one; cause

g 0 (x) = −3(1 − x)2 < 0 is decreasing on ]0, 1[; the interval
]0, 1[ is mapped into ]0, 1[
1
g −1 (y ) = 1 − y 1/3 , and (g −1 (y ))0 = − 2/3
3y
therefore
1
h(y ) = 3[1 − (1 − y 1/3 )]2 × | 2/3 | = 1 , 0 < y < 1
3y
Y has an exponential distribution with mean 1
Dr. Mohamed Kobeissi Continuous Random Variables
 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Let X be a random variable with exponential distribution on,

i.e. the pdf of X is
1 −x/θ
f (x) = e 0<x <∞
θ
Find the pdf of Y = e X

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

what if g is not one-to-one ?

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

what if g is not one-to-one ?

Let X U(−1, 3), and let Y = X 2 . Find the pdf of Y

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables

 Probability distribution function
Mathematical expectation
Usual Continuous Random Variables
Transformation of Random Variables

Dr. Mohamed Kobeissi Continuous Random Variables