Probability Distribution

DR. K.M. EARFAN ALI

PROFESSOR
DEPARTMENT OF STATISTICS
 Probability Distribution
A probability distribution shows the possible
outcomes of an experiment and the probability of
each of these outcomes.
Or
A listing of all the outcomes of an experiment and the
probability associated with each outcome.
 Example
To begin our study of probability distribution, let’s go
back to the idea of a fair coin, suppose we toss a fair
coin twice the possible outcomes are:
 Types of probability distribution
Probability Distribution

Discrete probability distribution Continuous probability distribution

Bernoulli distribution Uniform distribution

Binomial distribution Exponential distribution

Poisson distribution Normal distribution

Geometric distribution Gamma distribution

Negative binomial distribution

Lognormal distribution

Cauchy distribution
 Discrete probability distribution
A discrete probability can take on only a limited
number of values which can be listed.

Example

The probability that you were born in a given month

is also discrete because there are 12 possible values.
 Continuous probability distribution
In a continuous probability distribution the variable
under consideration is allowed to take on any within
a given range. So we can not list all the possible
values.

Example

Suppose we were examining the level of effluent in

a variety of streams and we measured the level of
effluent by parts of effluent per million parts of
water.
We would expect quite a continuous range of
parts per million (ppm), all the way from very low
levels is clear mountains streams of extremely
high levels in polluted streams. We would call the
distribution of this variable (ppm) a continuous
distribution.
 Bernoulli distribution
Bernoulli trial
A random experiment whose outcomes have
been classified into two categories namely
“success” and “failure” represented by letters 𝑆
and 𝐹 respectively is called a Bernoulli trail.
Bernoulli distribution
A discrete random variable 𝑋 is said to have a
Bernoulli distribution if its probability function is
given by
 𝑝𝑞1−𝑥 ; 𝑓𝑜𝑟 𝑥 = 0,1
𝑓 𝑥, 𝑝 = ቊ
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
where 𝑝 is the parameter of the distribution
satisfying 0 ≤ 𝑝 ≤ 1 and 𝑝 + 𝑞 = 1.
Example
A coin is tossed in which the outcome “head” is a
success and the probability of head is 𝑝. Then 𝑞 =
1 − 𝑝 is the probability of failure or tail. If the
number of heads or success is a random variable
𝑋, the can take values 0 or 1 according to the
outcome is tail (failure) or head (success).
Then the probability function of 𝑋 is

𝑝𝑞1−𝑥 ; 𝑓𝑜𝑟 𝑥 = 0,1

𝑓 𝑥, 𝑝 = ቊ
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
 Binomial distribution
Definitions: A discrete random variable 𝑋 is said to have a
binomial distribution if its probability function is given by
𝑛 𝑥 𝑛−𝑥
𝑝 𝑞
𝑓 𝑥; 𝑛, 𝑝 = ൝ 𝑥 ; 𝑋~𝐵 𝑛𝑝, 𝑛𝑝𝑞 ,
0
for 𝑥 = 0,1,2, … , 𝑛
where, the two parameters 𝑛 and 𝑝 satisfy 0 ≤ 𝑝 ≤ 1
𝑛 = independent trials and positive integers
𝑥 = number of success and a discrete random variable
which can assume values 0,1,2, .., 𝑛.
𝑝 = probability of success and
𝑞 = probability of failure; so, that 𝑝 + 𝑞 = 1.
 Conditions of Binomial Distributions
1. There are is a fixed number of trails
2. The trails are independent.
3. There are only two outcomes for each trail such as
success and failure.
4. The probability of success remains constant from
trail to trail.
5. The number of success, 𝑥(𝑥 = 0,1,2, … , 𝑛) in 𝑛
trails is a discrete random variable.
 Prosperities of Binomial Distribution
1. It is a discrete probability distribution with
parameters 𝑛 and 𝑝.
2. Its mean is 𝑛𝑝 and variance is 𝑛𝑝𝑞; mean is
greater than the variance.
3. It is a skew distribution except for 𝑝 = 𝑞 = 1/2
4. Binomial Distribution tends to Poisson
distribution if the number of trials, 𝑛 is very large
(𝑛 → ∞) and the probability of success, 𝑝 is very
small (𝑝 → 0).
5. Binomial distribution approaches to normal
distribution if the number of independent trial, 𝑛
is very large (𝑛 → ∞) and neither 𝑝 nor 𝑞 is very
small.
𝑞−𝑝 𝑞−𝑝
6. Co-efficient of skewness is, 𝑆𝑘 = = and
𝑛𝑝𝑞 𝜎

1−6𝑝𝑞 1−6𝑝𝑞
7. Excess of kurtosis is 𝛾 = 𝛽2 − 3 = =
𝑛𝑝𝑞 𝜎2
 Properties of Binomial Distribution
Mean(𝜇):
We know 𝜇 = 𝜇1′ = 𝐸 𝑥
𝑛

= ෍ 𝑥𝑝 𝑥 (𝑜𝑛 𝑠𝑖𝑚𝑝𝑙𝑖𝑐𝑎𝑡𝑖𝑜𝑛)
𝑥=0

∴ 𝜇 = 𝑛𝑝
Variance (𝜎 2 ) = 𝐸 𝑥 2 = 𝐸 𝑥 𝑥 − 1 + 𝑥
= 𝐸 𝑥 𝑥 − 1 + 𝐸 𝑥 … … … (𝑖)
′2
Now, 𝜇2 = 𝜇2′ − 𝜇1
= 𝑛 𝑛 − 1 𝑝2 + 𝑛𝑝 − (𝑛𝑝)2
= 𝑛𝑝𝑞
∴ 𝜇2 = 𝑛𝑝𝑞
Variance (𝜎 2 ) = 𝜇2 = 𝑛𝑝𝑞
𝜎
𝐶𝑉 = × 100
𝜇
𝑛𝑝𝑞
= × 100
𝑛𝑝

𝑞
= 100
𝑛𝑝

Show that mean is always greater than variance

Theorem: Mean of the binomial distribution is greater
than the variance

Proof: We know the mean of binomial distribution is

𝑛𝑝 and variance is 𝑛𝑝𝑞.

Here, variance = 𝑛𝑝𝑞

= 𝑛𝑝(1 − 𝑝), since 𝑝 + 𝑞 = 1

implies that 𝑞 = 1 − 𝑝
= 𝑛𝑝 − 𝑛𝑝2
= 𝑚𝑒𝑎𝑛 − 𝑛𝑝2
Implies that, 𝑚𝑒𝑎𝑛 = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 + 𝑛𝑝2
= 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 + 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒 𝑞𝑢𝑎𝑛𝑡𝑖𝑡𝑦
Therefore, 𝑚𝑒𝑎𝑛 > 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒.
Third Moment (𝜇3 ):

′3
𝜇3 = 𝜇3′ − 3𝜇2′ 𝜇1′ + 2𝜇1

Now, 𝜇3′ = 𝐸 𝑥 𝑥 − 1 + 2𝑥 𝑥 + 1 𝑥 + 2 + 𝑥
= 𝐸 𝑥 𝑥 − 1 + 2𝐸 𝑥 𝑥 + 1 𝑥 + 2 + 𝐸 𝑥 … (𝑖𝑖)

Now simplification on the equation (ii) we get

𝜇3 = 𝑛𝑝𝑞(𝑞 − 𝑝)
Fourth Moment (𝜇4 ):
4
′ ′2
𝜇3 = 𝜇4′ − 4𝜇3′ 𝜇1′ + 6𝜇2 𝜇1 − 3𝜇1′

Now, 𝜇4′ = 𝐸 𝑥 𝑥 − 1 + 2𝑥 𝑥 + 1 𝑥 + 2 + 3𝑥 𝑥+1 𝑥+2 𝑥+3 +𝑥

= 𝐸 𝑥 𝑥 − 1 + 2𝐸 𝑥 𝑥 + 1 𝑥 + 2
+ 3𝐸 𝑥 𝑥 + 1 𝑥 + 2 (𝑥 + 3) + 𝐸 𝑥 … (𝑖𝑖𝑖)

Now simplification on the equation (ii) we get

= 3𝑛2 𝑝2 𝑞 2 + 𝑛𝑝𝑞(1 − 6𝑝𝑞)

𝜇4 = 3𝑛2 𝑝2 𝑞 2 + 𝑛𝑝𝑞(1 − 6𝑝𝑞)
 𝜇32 (𝑞−𝑝)2
Hence, 𝛽1 = =
𝜇23 𝑛𝑝𝑞
And
𝜇4 1 − 6𝑝𝑞
𝛽2 = 2 =
𝜇2 𝑛𝑝𝑞
Recurrence Relation;

𝑛−𝑥 𝑝
𝑃 𝑥+1 = . 𝑥 , =0,1,2,…,n. This relation is
𝑥+1 𝑞

helpful for calculating probabilities for different

values of binomial variate.
 Example:
The mean and variance of a binomial distribution are
4 and 4/3 respectively. Find the probability of getting
at least 1 success.

Solutions:

𝑛 and 𝑝 are the two parameters of binomial

distribution.

Given that mean 𝑛𝑝 = 4 and

variance, 𝑛𝑝𝑞 = 4/3

 𝑛𝑝𝑞 4Τ 1
3
Therefore, = =
𝑛𝑝 4 3
1
Implies that, 𝑞 =
3
1 2
Therefore, 𝑝 = 1 − 𝑞 = 1 − =
3 3
2
𝑝= , again 𝑛𝑝 = 4
3
2
𝑛 = 4, implies that, 𝑛 = 6
3
Therefore the probability density function of the
distribution is given by
 6 𝑥 𝑛−𝑥
𝑃 𝑥 = 𝑝 𝑞
𝑥
6
= (2/3)𝑥 (1/3)6−𝑥 , 𝑥 = 0,1,2, … , 6
𝑥
Therefore, 𝑃 𝑥 ≥ 1 = 1 − 𝑃 𝑥 = 0
6
=1− (2/3)0 (1/3)6−0
0
6
1
=1−
3
= 1 − 0.00137
= 0.99863
 Example
On any given day that you go fishing, you have a
0.70 probability of catching a fish. Suppose you
go fishing 6 days in a Lake.
a) What is the probability that you will catch a
fish on exactly four of the 6 days?
b) What is the probability that you will catch a
fish at least four of the 6 days?
c) What is the probability that you will catch a
fish more than four of the 6 days?
 Solution
Here the number of days for fishing is 6.
Let x the number of catching fish (0, 1, 2, ....., 6).
The probability of success is 0.70.
Using the formula for binomial distribution, we
have
6 𝑥 𝑛−𝑥
𝑃 𝑋=𝑥 = 𝑝 𝑞
𝑥
6
= (0.7)𝑥 (0.3)6−𝑥 , 𝑥 = 0,1,2, … , 6
𝑥
a) We wish to find p(4), the probability of
catching exactly four fish.
6
𝑃 𝑋=4 = (0.7)4 (0.3)6−4 = 0.324
4
There is a 32% chance that you will catch 4 fish
in 6 days period.
b) We are to compute probability of 𝑃 𝑋 ≥ 4 .
We have, 𝑃 𝑋 ≥ 4 = 𝑃 4 + 𝑃 5 + 𝑃(6)
= 0.324 + 0.303 + 0.118
= 0.745
There is about a 74% chance that you will catch
4 or more fish in 6 days period.
𝑐) We are to compute probability of 𝑃 𝑋 ≤ 4 .
We have,
𝑃 𝑋 ≤ 4 = 𝑃 0 + 𝑃 1 + 𝑃 2 + 𝑃(3)
=1− 𝑃 4 +𝑃 5 +𝑃 6
= 1 −0.745=0.255
There is a 25% chance that you will catch 4 or
fewer fish in 6 days period.
 Assignment
1. Example
In a community, the probability that a newly born
child will be boy 2/5. Among the 4 newly born
children in that community, what is the probability
that
a) All the four boys
b) No boys
c) Exactly one boy.
2. Example
A fair coin is tossed 5 times. Find the probability of

a) exactly two heads

b) no head

3. Example

Determine the binomial distribution for which mean is 4

and variance is 3.
Home works
Book By D. Lind Page 195, Exercises: 9, 10, 11, 12, 13,
14, 15, 17, 18. (Use for ).
4. Example
We can consider the probability of passing a multiple
choice exam paper comprising 20 questions each
with 5 answers by random guessing.
The Bernoulli trial is a guess at the question, for
which the probability of a pass is 0.2 (one fifth). It is
important to distinguish between the fact there
happen to be five answers but only two outcomes
(you pick the right answer or you do not). If there
were five possible outcomes, then this would not be
a Bernoulli trial.
 Poisson distribution:
Introduction
 Poisson distribution was developed by France
mathematician and physicist Simeon Denis Poisson
(1781-1840), who published it in 1837.
 Definitions:
A discrete random variable x is said to have a Poisson
distribution if its probability function is given by

𝑒 −𝜆 𝜆𝑥
𝑓 𝑥; 𝜆 = ቐ 𝑥! ; 𝑋~𝑃 𝜆 , for 𝑥 = 0,1,2, … , 𝑛
0
where,
𝑒 = 2.71828 and only one parameter 𝜆.
𝑛 = independent trials and positive integers
𝑥 = a discrete random variable which can assume
values 0,1,2, … … … . , ∞.
 Some examples of Poisson Distributions
1. Number of road accidents in a city in some of unit
time

2. Number of printing mistakes in each page of a

book

3. Number of unfilled grains per panicle.

4. Number of defective screws per box of 100 screws

5. Number of bacterial colonies in a given cultures

per unit area of microscope slab.
6. Number of suicides reported in a particular city in
a fixed time.

7. Number of dead by heart attack in fixed time.

8. Number of deaths of cattle’s in a certain area by a

certain disease.
Poisson distribution is a limiting case of the binomial
distribution under the following conditions;
1. The probability of success or failure in binomial
trails is very small 𝑖. 𝑒., 𝑝 → 0 𝑜𝑟 𝑞 → 0
2. The number of independent trails is very large.
i.e., 𝑛 → ∞
3. n𝑝 = 𝜆 (say) is a finite constant.
 Prosperities of Poisson distribution
1. Poisson distributions is a discrete probability
distribution
2. Poisson distribution has only one parameter 𝜆.
3. Its mean and variance is equal.
𝑖. 𝑒. , 𝑚𝑒𝑎𝑛 = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝜆.
4. It is a skewed measures of skewness,
1 1
𝛾1 = 𝛽1 = and 𝛽2 =
𝜆 𝜆

5. Since, 𝛽2 > 3; the distribution is leptokurtic.

6. Poisson distribution is a limiting case from
binomial distribution when the number of
independent trails n is very large (𝑛 → ∞) but
probability of success is very small.
 Properties of Poisson distribution
1. The Poisson distribution is a discrete distribution
with a parameter 𝜆

2. Total probability of the distribution will be unity

i.e. σ∞
𝑥=0 𝑃 𝑥 = 1

3. The mean and variance of Poisson distribution is

equal to 𝜆; 𝑖. 𝑒. , 𝜇 = 𝜎 2 = 𝜆
1 1
4. 1 = and 2 = 3 +
𝜆 𝜆

5. As 𝜆 → ∞, 𝛽1 → 0 and 𝛽2 → 3
 Properties of Poisson distribution
Mean(𝜇):
We know 𝜇 = 𝜇1′ = 𝐸 𝑥
𝑛

= ෍ 𝑥𝑝 𝑥
𝑥=0

𝑛
𝑒 −𝜆 𝜆𝑥
= ෍𝑥 (𝑜𝑛 𝑠𝑖𝑚𝑝𝑙𝑖𝑓𝑖𝑐𝑎𝑡𝑖𝑜𝑛)
𝑥!
𝑥=0

= 𝜆𝑒 −𝜆 𝑒 𝜆 = 𝜆
∴𝜇=𝜆
Variance (𝜎 2 ) = 𝜇2

𝜇2′ = 𝐸 𝑥 2 = 𝐸 𝑥 𝑥 − 1 + 𝑥
= 𝐸 𝑥 𝑥 − 1 + 𝐸 𝑥 … … … (𝑖)

′2
Now, 𝜇2 = 𝜇2′ − 𝜇1

= 𝜆2 + 𝜆 − 𝜆2 (𝑜𝑛 𝑠𝑖𝑚𝑝𝑙𝑖𝑓𝑖𝑐𝑎𝑡𝑖𝑜𝑛)
Variance (𝜎 2 ) = 𝜇2 = 𝜆
Third Moment (𝜇3 ):

We have, 𝜇3′ = 𝜆3 + 3𝜆2 + 𝜆 (on simplification)

′3
Therefore, 𝜇3 = 𝜇3′ − 3𝜇2′ 𝜇1′ + 2𝜇1

= 𝜆3 +3𝜆2 + 𝜆 − 3 𝜆2 + 𝜆 𝜆 + 2𝜆3
after simplification, we get
∴ 𝜇3 = 𝜆
Fourth Moment (𝜇4 ):

We have, 𝜇4′ = 𝜆4 + 6𝜆3 + 7𝜆2 + 𝜆 (on

simplification)
4
′ ′ ′ ′2
Thefore, 𝜇4 = 𝜇4′ − 4𝜇3 𝜇1 + 6𝜇2 𝜇1 − 3𝜇1′

= 3𝜆2 + 𝜆

on simplification, we get
∴ 𝜇4 = 3𝜆2 + 𝜆
 𝜇32 1
Hence, 𝛽1 = =
𝜇23 𝜆
And
𝜇4 1
𝛽2 = 2 = 3 +
𝜇2 𝜆
Recurrence Relation;

𝜆
𝑃 𝑥+1 = . 𝑃 𝑥 , X=0,1,2,…,∞.
𝑥+1

This relation is helpful for calculating probabilities

for different values of Poisson variate.
 Example
Pyramid Lake is located in Nevada on the Paiute
Indian Reservation. The Paiute Nation uses highly
trained fish biologists to study and maintain this
famous fishery. In one of their publications, Creel
Chronicle, it was reported that the November
catch for boat fishermen was 0.667 fish per hour.
Suppose you decide to fish Pyramid Lake for 7
hours during the month of November.
a) Find the probability distribution function for
the number of fish you catch in a period of 7
hours.
b) What is probability that in 7 hours you will
catch 3 fish?
c) What is the probability that you will get 4 or
more fish in the 7-hour period?
 Solution
a) For fish of all sizes, the mean success rate per
hour is 0.667. We are given a value of = 0.667
for 1 hour
Since we want to study a 7-hour interval, we
adjust so that it represents the average number
of fish expected in a 7-hour period.
0.667 𝑓𝑖𝑠ℎ 7 4.669
𝜆= × =
1 ℎ𝑜𝑢𝑟 7 7 ℎ𝑜𝑢𝑟𝑠
Then the Poisson distribution function is
4.669𝑋 𝑒 −4.669
𝑃(𝑋) = .
𝑋!
b) We have,
4.669𝑋 𝑒 −4.669
𝑃(𝑋) =
𝑋!

4.6693 𝑒 −4.669
𝑃 3 = = 0.1591 or about 16%
3!

There is about a 16% chance that you will catch

exactly 3 fish in a 7-hour period.
c) The sample space of all x values is x = 0, 1, 2, 3,
4, … and so on. The probability of the entire
sample space is 1, and these events are mutually
exclusive. Therefore,
1 = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + …
So, 𝑃(𝑥 4) = 𝑃(4) + 𝑃(5) + 𝑃(6) + …
= 1 – 𝑃(0) – 𝑃(1) – 𝑃(2)𝑃(3)
= 1 – 0.0094 – 0.0438 – 0.1023 – 0.1591
= 0.6854
There is about a 69% chance that you will catch 4
or more fish in a 7-hour period.
 Assignment
1. Example:
A producer of seeds knows that 5% of his seeds
are defective. If he sells seeds in boxes of 200
find the probability that a) no defective seeds will
be found in a box, b) at most 3 defective seeds
will be found in a box.
2. Example
Suppose that the number of emergency patients
in a given day at a certain hospital is a Poisson
variable with parameter . What is the
probability that in a given day there will be
1. 15 emergency patients.
2. At least 3 emergency patients.
3. More than 20 but less than 25 patients.
3. Example
If the probability that a car accident happens is
a very busy road in on hour is 0.001. If 2000
cars passed in one hour by the road, what is
the probability that
a) exactly 3
b) more than 2 car accidents happened on
that hour of the road.
4. Example

A factory produces blades in a packet of 10. The

probability of a blade to be defective is 0.2%.
Find the number of packets having two defective
blades in a consignment of 10,000 packets.
5. Example
What probability model is appropriate to describe a
situation where 100 misprints are distributed randomly
throughout the 100 pages of a book? For this model, what is
the probability that a page observed at random will contain
at least three misprints?
Home works
Book by D. Lind, page 203, Exercise: 31, 32, 33
Book by Paul Newbold page 160, Exercise: 5.40, 5.41.
Book by Paul Newbold page 158 & 159, Example: 5.13,
5.14.
 Normal Distribution
Introduction
Normal distribution is the most important continuous
probability distribution in the entire field of statistics. Its
graph, called the normal curve, is the bell-shaped curve
that describes the distribution of so many sets of data,
which in nature, industry, and research.
• The normal distribution was first discovered by the
English mathematician De Moivre (1667-1754), who in
1733 derived the distribution as the limiting form of the
binomial distribution.
• But the same formula was derived by Laplace and
Gauss (1777-1855) independently.
Definitions: A continuous random variable X is said to
have a normal distribution if its probability function is
given by
−(𝑥−𝜇)2
1
𝑓 𝑥; µ, 𝜎2 = 𝑒 2𝜎2 ; 𝑋~ 𝑁(µ, 𝜎2), for 𝑥 assumes
𝜎 2𝜋
−∞ < 𝑥 < ∞
where the two parameters µ 𝑎𝑛𝑑 𝜎2 satisfy
− ∞ < µ < ∞ 𝑎𝑛𝑑 𝜎2 > 0
µ = 𝑚𝑒𝑎𝑛 𝑜𝑓 𝑛𝑜𝑟𝑚𝑎𝑙 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛
𝜎2 = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 𝑜𝑓 𝑛𝑜𝑟𝑚𝑎𝑙 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛
𝜋 = 3.14157 𝑎𝑛𝑑 𝑒 = 2.71828
𝑇ℎ𝑒 𝑐𝑢𝑟𝑣𝑒 𝑜𝑓 𝑓(𝑥) 𝑖𝑠 𝑎 𝑏𝑒𝑙𝑙 𝑠ℎ𝑎𝑝𝑒𝑑 𝑐𝑢𝑟𝑣𝑒.
Definition: A continuous random variable Z is said to
have a normal standard normal variate if its
probability function is given by
1
1 − 𝑧2
𝑓 𝑧 = 𝑒 2 ; 𝑧~𝑁(0,1) for x assumes − ∞ <
2𝜋
𝑧 < ∞
where, 𝑋 is a normal variate with two parameters
µ 𝑎𝑛𝑑 𝜎2 satisfy − ∞ < 𝑧 < ∞ 𝑎𝑛𝑑 𝜎2 > 0
Mean of normal distribution µ = 0 and
Variance of normal distribution 𝜎2 = 1
𝜋 = 3.14157 𝑎𝑛𝑑 𝑒 = 2.71828
The curve of 𝑓(𝑥) is a bell shaped curve.
 Prosperities of Normal Distribution

1. It is a symmetrical distribution with two

parameters µ 𝑎𝑛𝑑 𝜎2.
2. It’s has maximum probability occurring at the
point 𝑥 = µ.
3. Mean, median and mode of the distribution are
equal
4. Skewness, 𝛽1 = 0 and kurtosis, 𝛽2 = 3
5. All odd moments of this distribution are zero.
6. It has two points of inflection at µ + 𝜎 𝑎𝑛𝑑 µ − 𝜎.

 P(µ - σ < x < µ + σ ) = 0.6826

 P(µ - 2σ < x < µ + 2σ ) = 0.9544

 P(µ - 3σ < x < µ + 3σ ) = 0.9973

 Confidence interval
 P(µ - 1.96σ < x < µ + 1.96σ ) = 0.95 = 95%
 P(µ - 2.58σ < x < µ + 2.58σ ) = 0.99 = 99%
Normal Distribution is the limiting form of binomial
distribution under the following conditions.
I. Number of trails is very large i.e. , 𝑛 → ∞
II. Neither the probability of success, 𝑝 𝑛𝑜𝑟 𝑞 is very
small 𝑖. 𝑒. , 𝑝 ≈ 𝑞.
 Importance of Normal distribution in
Statistics
Normal distribution plays a very important role in
Statistics because of the following reasons:

1. Most of the distributions occurring in practice e.g.

Binomial, Poisson; Hyper-geometric distribution
etc. can be approximated by the normal
distribution under some assumptions. Moreover,
many of the sampling distributions e.g. student 𝑡,
𝐹 and 𝜒 2 tends to normality for large samples.
2. The proofs of all the tests of significance in
sampling are based upon the fundamental
assumption that the population from which the
samples have been drawn is normal.

3. Normal distribution finds large application in

statistical quality control theory.
 Example
The average size of the fish in a lake is 11.4
inches, with a standard deviation of 3.2 inches.
Find the probability of catching a fish longer
than 17 inches.
Solution:
𝐻𝑒𝑟𝑒, 𝜇 = 11.4 𝑖𝑛𝑐ℎ𝑒𝑠
𝜎 = 3.2 𝑖𝑛𝑐ℎ𝑒𝑠
𝑥 = 17 𝑖𝑛𝑐ℎ𝑒𝑠
We have
𝑧 = (𝑥 − 𝜇)/𝜎 = (17 − 11.4)/3.2 = 1.75
𝑃(𝑥 > 17 𝑖𝑛. ) = 𝑃(𝑧 > 1.75) = 𝑃(𝑧 > −1.75)
From 𝑍 − 𝑡𝑎𝑏𝑙𝑒𝑠,
𝑃 𝑧 < − 1.75 = 0.5 − 0.4599 = 0.0401
𝐻𝑒𝑛𝑐𝑒, 𝑃(𝑥 > 17 𝑖𝑛. ) = 0.0401 = 4%
There is a 4% chance of catching a fish longer than
17 inches.
 Example
A very large group of students obtains test scores that
are normally distributed with mean 60 and standard
deviation 15. What proportion of students obtained
scores

a) Less than 85.

b) More than 90.

c) Between 85 and 95.

 Solution
Let denote the test score. Then

𝑋 − 𝜇 85 − 𝜇
𝑎) 𝑝 𝑥 < 80 = 𝑝 <
𝜎 𝜎

85 − 60
=𝑝 𝑧<
15
= 𝑝 𝑧 < 1.67 = 𝑝 −∞ < 𝑧 < 1.67
= 0.9525 (By using Normal table).
That is 95.25% of the students obtained scores less than
80.
 𝑋−𝜇 90−𝜇 90−60
𝑏) 𝑝 𝑥 > 90 = 𝑝 < =𝑝 𝑧<
𝜎 𝜎 15

= 𝑝(𝑧 > 2) = 1 − 𝑝 𝑧 < 2

= 1 − 𝑝(−∞ < 𝑧 < 1.67

= 1 − 0.9772

= 0.0228 (𝐵𝑦 𝑢𝑠𝑖𝑛𝑔 𝑁𝑜𝑟𝑚𝑎𝑙 𝑡𝑎𝑏𝑙𝑒).

That is 2.28% of the students obtained scores more

than 90.
 85 − 𝜇 𝑋 − 𝜇 𝑋 − 𝜇
𝑐) 𝑝 85 < 𝑥 > 95 = 𝑝 < <
𝜎 𝜎 𝜎
85 − 60 95 − 60
=𝑝 <𝑧<
15 15
= 𝑝(1.67 < 𝑧 < 2.33)
= 𝑝 −∞ < 𝑧 < 2.33 − 𝑝(−∞ < 𝑧 < 1.67)

=0.9901-0.9525
= 0.03756 (𝐵𝑦 𝑢𝑠𝑖𝑛𝑔 𝑁𝑜𝑟𝑚𝑎𝑙 𝑡𝑎𝑏𝑙𝑒).

That is 3.76% of the students obtained scores in the

range 85 to 95.
 Assignment
1. Example

The average daily sales of 500 branch office were Tk.

150 thousands and the standard deviation Tk. 15
thousands. Assuming the distribution to be normal
indicate how many branches have sales between

a) Tk. 120 thousands and Tk. 145 thousands.

b) Tk. 140 thousands and Tk. 165 thousands.

2. Example

A company produces light bulbs whose life times

follows a normal distribution with mean 1200 hours
and standard deviation 250 hours. If a light bulb is
chosen randomly from the company’s output, what
is the probability that it’s life time will be between
900 and 1300 hours?