Chapter Three

Special Probability Distributions and Densities

3.1 special probability distributions for discrete variables:

a. Bernoulli Distribution:

Consider a random variable experiment that can give rise to just two possible mutually exclusive
and collectively exhaustive outcomes, which for convenience labelled “success” and “failure”.
Let P denotes the probability of success, so that the probability is (1-P). Now, define the random
variable X so that X takes the value 1 if the outcome of the experiment is success and 0
otherwise. The probability function of this random variable is then

P ( 0 )= (1−P )∧P ( 1 )=P

This distribution is known as Bernoulli distribution.

μ=E ( x ) =∑ xP ( x )=0 × ( 1−P )+1 × P=P

x

σ 2=E [ ( X−μ )2 ]=∑ ( X −μ )2 P ( x )=( 0−P )2 P ( 0 )+ ( 1−P )2 P ( 1 )=P 2 ( 1−P )+ (1−P )2 P=p ( 1−p ) [ p+1−p ] = p(1− p)

Example: For a Bernoulli random variable with probability of success P=0.5, compute the mean
and variance. μ=P=0.5 σ 2=P ( 1−P )=0.5 × 0.5=0.25

b. Binomial distribution: suppose that a random experiment can result in two possible mutually
exclusive & collectively exhaustive outcomes, “success” and “failure” and that P is the
probability of success in a single trail. If n independent trials are carried out, the distribution of
the number of resulting successes, x, is called the binomial distribution. Its probability
distribution function for the binomial random variable X=x is P(X successes in n independent
trails¿

n! X
P(x )= P ¿
( n−x ) ! x !

Mean and variance of binomial probability distributions: let X be number the of in n independent
trails, each with probability of success P. Then X follows binomial distribution with mean

μ=E ( x ) =nP
2 2
σ =E[ ( X −μ ) ]=nP (1−P)

Example: for a binomial probability function with P=0.7 and n=18, find the probability that the
number of success is equal to 12, and the probability that the number of successes is less than 6.

1
 P ( X=12 ) , n=18 , x=12 , P=0.7
18 12 6
P ( X=12 )=C12 (0.7) (0.3) =0.1873 ¿ binomial probability distributiontable

c. Hyper geometric distribution:

The binomial distribution is used in situations where there is sampling with replacement. But in
case if there is sampling without replacement the hyper geometric distribution is used. Suppose
that a random sample of n objects is chosen from a group of N objects, S of which are successes.
The distribution of the number of successes, x, in the sample is called the hyper geometric
distribution. Its probability function is
S N −S
C x C n−x
P ( x )= N
Cn

Example: Compute the probability of 8 successes in a random sample of size n=15 obtained from
a population size N= 400 that contains 200 successes.
200 200
C8 C7
P ( x=8 ) = 400
=0.199
C 15

d. The Poisson probability distribution:

Assumptions: assume that an interval is divided into a very large number of sub-intervals so that
the probability of the occurrence of an event in any sub-interval is very small.

1. The probability of the occurrence of an event is constant for all sub intervals.
2. There can be no more than one occurrence in each interval
3. Occurrences are independent, i.e; the occurrences in non overlapping intervals are
independent of one another.

If this is the case, a random variable X is said to follow the Poisson probability distribution, if it
has the probability function
−λ x
e λ
P ( x )= for x=0.1 .2 , …
x!

P(x) is the probability of x successes in a given time or space given λ , which represents the
expected number of successes per time or space unit.

μ=E ( X )=λ=σ =E [ ( X −μ ) ]
2 2

Example: the number of accidents in a production facility has a Poisson distribution with a mean
of 2.6 per month.

2
 a. For a given month what is the probability that there will be fewer than two accidents?
−2.6 0 −2.6 1
e 2.6 e 2.6
p ( x< 2 )= p ( 0 ) + p ( 1 )= + =0.0743+ 0.1931=0.2674
0! 1!
b. For a given month what is the probability there will be more than three accidents
−2.6 0 −2.6 1 −2.6 2 −2.6 3
e 2.6 e 2.6 e 2.6 e 2.6
P ( X >3 )=1−[ P ( 0 ) + P ( 1 ) + P (3 ) ] =1−{ + + =1−(0.0743+ 0.1931+0.25
0! 1! 2! 3!
¿ 1−0.7350=0.2650

3.2 Special probability distribution (densities) for continuous random variables:

A. Normal Distribution: the probability density function for a normally distributed random
variable x is
2
−(x− μ)
1 2

f ( x )= e 2σ
for−∝< x< ∝
√2 π σ 2
P(x)

Probability density function for normal distribution

0 μ x

Properties of normal distribution:

Suppose that the random variable x follows a normal distribution with parameter μ∧σ 2. Then the
following properties hold.

1. The mean of the random variable is μ , E ( X )=μ

2. The variance of the random variable is σ 2
3. The shape of the probability density function is a symmetric bell shaped curve centered
on the mean μ as shown above.
4. If the mean and variance is known, normal distribution can be defined as,
X N ( μ , σ2)
2
μ , σ has different effects on probability density functions of normal distribution., the first
provides measure of central location while the later measures dispersion from the mean.

Example 1: Two normal distributions with different mean

3
 f(x)

5 6 x

Example 2: two normal distributions with different variance

f(x)

Variance=1

Variance =0

μ x

Cumulative distribution functions of the normal distribution:

Suppose that x is a normal random variable with mean μ and varianceσ 2, that is x N ( μ , σ 2 ), then
the cumulative distribution function is

F ( xo )=P ( X ≤ xo )

This is the area under the normal probability density function to the left of X0. The total area
under the curve is
∝
F ( ∝ )=∫ f (x )dx
−∝

f(x) F(xo)

xo 0 x

Range probabilities for normal random variables:

Let x be a normal random variable with cumulative distribution function F(x), and let a and b be
two possible values of x, with a<b. Then

4
 b
p ( a< x <b )=∫ f (x)dx=F ( b )−F (a)
a

f(x)

a b x

B. Standard Normal Distributions:

Let Z be a random variable with mean zero and variance one i.e, Z~N(0,1), we say that Z
follows standard normal distribution. Given a normally distributed random variable
X N ( μ , σ 2 ), it is transformed to Z by

X−μ
Z=
σ

The cumulative distribution function of z is

F ( z )=P ( Z ≤ z )

F (−z )=1−P ( Z ≤ z )

if a <b , P ( a< x <b )=P ( a−μ

σ
<z<
σ )
b−μ

¿F ( b−μ
σ )−F (
a−μ
σ
)

Example 1: let the random variable x follows a normal distribution with μ=50∧σ 2=64.

a. Find the probability that x is greater than 60

(
P ( x> 60 )=P Z > )60−50
8

¿ P ( Z > )=1−P ( Z < )

5 5
4 4
¿ 1−0.8944=0.1056
b. Find the probability that x is greater than 35 and less than 62
P¿

¿ F ( 1.5 )−( 1−F (1.875 ) )

5
 ¿ 0.9332− (1−0.9693 ) =0.9028

c. Find the probability that x is less than 55

(
P ( X <55 ) =P Z<
55−50
8 ) =P ( Z< 0.625 )

F ( 0.63 )−F ( 0.62 )

¿ F ( 0.62 ) +
2
0.7357−0.7324
¿ 0.7324 +
2
¿ 0.73405
d. The probability is 0.2 that X is greater than what number?
Let the number be a.
P ( x> a )=0.2

⟹ P Z> ( a−50
8 )
=0.2=1−P Z< ( a−50
8 )
⇒P Z<( a−50
8 )
=0.8

a−50
⇒ =1.0186
8
⇒ a=58.15 ≈ 58
e. The probability is 0.05 that x is in the symmetric interval about the mean between which
numbers? Let the numbers be a & b, then
P ( a< x <b=0.05 )

⇒P ( a−50
8
<z<
b−50
8 )=0.05

⇒F( )−F (
8 )
b−50 a−50
=0.05
8

But ( )=(−(
8 )
a−50 b−50
)
8

⇒F(
b−50
8 )−F −(
( 8 ))=0.05
b−50

⇒2 F (
8 )
b−50
−1=0.05

⇒F(
8 )
b−50
=0.525

b−50
⇒ =0.06275
8
⇒ b=50.502
but
a−50
8
=−
b−50
8 ( )
=−0.06275

6
 ⇒ a=49.498

Example 2: Let a continuous random variable “x” be the amount of money spent on clothing in a
year by a university student. It is known that X N (380 , 2500).

a) What is the probability that they will spend less than 400 birr?
b) What is the probability that they will spend more than 360 birr?
c) What is the probability that they will spend more than 300 birr but less than 400birr?
d) Above how much birr they should spent so that the probability to be 0.10?
e) Find a symmetric range of clothing expenditure from the mean that include 80% of all the
students.

Solution:

(
a. p ( x< 400 ) =p z <
400−380
50 )
¿ p ( z< 0.4 ) =F ( 0.4 )
¿ 0.6554

(
b. p ( x> 360 )= p z >
360−380
50 )
¿ p ( z>−0.4 )=p ( z <0.4 )=F ( 0.4 )
¿ 0.6554

c. p ( 300< x <400 )= p (
300−380
50
<z<
400−380
50 )
=p (−1.6< z <0.4 )

¿ p ( z< 0.4 ) −p ( z ←1.6 ) =F ( 0.4 )−F (−1.6 )=F ( 0.4 )− [ 1−F ( 1.6 ) ]
¿ F ( 0.4 ) + F ( 1.6 )−1=0.6554 +0.9452−1
¿ 0.6006
d. p ( x> b )=0.10

(
¿ p z>
b−380
50 )
=0.10

¿ 1− p z<( )
b−380
50
=0.10

→ p (z<
50 )
b−380
=0.90

b−380
→ =1.2815
50
→ b=444 birr
e. p ( x 0< x < x 1 )=0.80
¿ p ( 380−a< x <380+a )=0.80 ; where x 0=380−a and x 1=380+ a

¿p ( ( 380−a50)−380 )< z < p( ( 380+a50)−380 )=0.80

7
 (( ) ( ))
¿p
−a
50
<z<
a
50
=0.80

¿F ( ) ( ) ( ) ( ( ))
a
50
−F
−a
50
=F
a
50
− 1−F
a
50
=0.80

¿2 F ( 50a )−1=0.80
¿ F ( )=0.90
a
50
a
→ =1.28
50
→ a=64
∴ x 0=380−64=316 , and x 1=380+64=444