NORMAL DISTRIBUTION:

The Normal distribution is an important distribution in statistics. Many

characteristics of manufactured products in industries and human characteristics
such as height, weight, IQ approximate a normal distribution. Therefore, the
Normal distribution is one of the examples of a continuous random variable.
For example; a person’s weight will not be exactly equal to the average weight of
all people say in Uganda. However, we would expect many people to be close to
the average and very few in the extremes.
If a random Variable 𝑋 follows a normal distribution then 𝑋~𝑁(𝜇, 𝛿 2 )
Where 𝜇 = 𝑀𝑒𝑎𝑛 and 𝛿 2 = 𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒.
The curve below is called a Normal curve.

The Normal distribution has the following properties:

(i) It is symmetrical about the mean 𝜇.
(ii) It is asymptotic about the 𝑥 − 𝑎𝑥𝑖𝑠.
(iii) The Mean, Mode and Median Coincide at the maximum value of the
function.
(iv) The area under the curve equals to unity.
(v) The area under the normal curves is used to find probabilities.

1
 STANDARDISATION:
To calculate probabilities of a given 𝑥 −value from a normal distribution with
mean 𝜇 and standard deviation 𝛿.
𝑥−𝜇
This is done by using the formula 𝑍 = .
𝛿

𝑍 is called the standardized score and the process of obtaining it is called

Standardisation.
We can read the probability of any given value of 𝑍 from Cumulative normal
distribution tables.
Example 1:
𝐼𝑓 𝑋 ~ 𝑁(4, 9), 𝑓𝑖𝑛𝑑 𝑃(𝑋 < 12).
SOLUTION:
𝑥−𝜇 12−4
From 𝑍 = , we get 𝑍 = = 2.667
𝛿 3

𝑃(𝑋 < 12) = 𝑃(𝑍 < 2.667)

0 2.667 𝑍

𝑃(𝑍 < 2.667) = 0.5 + 𝑃(0 < 𝑍 < 2.667)

𝑃(𝑍 < 2.667) = 0.5 + 0.4961
𝑃(𝑍 < 2.667) = 𝟎. 𝟗𝟗𝟔𝟏

2
Example 2:
𝑋 is a normally distributed variable with mean 𝜇 = 30 and standard deviation
𝜎 = 4. Find:
(i) 𝑃(𝑥 < 40)
(ii) 𝑃(𝑥 > 21)
(iii) 𝑃(30 < 𝑥 < 35)

SOLUTION:
𝑥−𝜇 40−30
(i) From 𝑍 = , we get 𝑍 = = 2.5
𝛿 4

𝑃(𝑋 < 40) = 𝑃(𝑍 < 2.5)

0 2.5 𝑍

𝑃(𝑍 < 2.5) = 0.5 + 𝑃(0 < 𝑍 < 2.5)

𝑃(𝑍 < 2.5) = 0.5 + 0.4938
𝑃(𝑍 < 2.5) = 𝟎. 𝟗𝟗𝟑𝟖

3
 𝑥−𝜇 21−30
(ii) From 𝑍 = , we get 𝑍 = = −2.25
𝛿 4

𝑃(𝑋 > 21) = 𝑃(𝑍 > −2.25)

−2.25 0 𝑍

𝑃(𝑍 > −2.25) = 0.5 + 𝑃(0 < 𝑍 < 2.25) By symmetry

𝑃(𝑍 > −2.25) = 0.5 + 0.4878
𝑃(𝑍 > −2.25) = 𝟎. 𝟗𝟖𝟕𝟖
𝑥−𝜇 30−30
(iii)𝑃(30 < 𝑥 < 35) =? From 𝑍 = , we get 𝑍1 = =0
𝛿 4
35−30
And 𝑍2 = = 1.25
4

0 1.25 𝑍

𝑃(30 < 𝑥 < 35) = 𝑃(0 < 𝑍 < 1.25)

𝑃(0 < 𝑍 < 1.25) = 𝟎. 𝟑𝟗𝟒𝟒

4
Example 3:
The time taken to assemble a car in a certain plant is a random variable
having a normal distribution of mean 20 hours and a standard deviation of
2 hours. What is the probability that a car can be assembled at this plant in
a period of time:
(i) Less than 19.5 hours?
(ii) Between 20 hours and 22 hours?
SOLUTION:
Let 𝑋 be the time taken to assemble a car in a certain plant.
(i) 𝜇 = 20 and 𝛿 = 2
𝑥−𝜇 19.5−20
From 𝑍 = , we get 𝑍 = = −0.25
𝛿 2

𝑃(𝑋 < 19.5) = 𝑃(𝑍 < −0.25)

−0.25 0 𝑍

𝑃(𝑍 < −0.25) = 0.5 − 𝑃(0 < 𝑍 < 0.25) By symmetry

𝑃(𝑍 < −0.25) = 0.5 − 0.0987
𝑃(𝑍 < −0.25) = 𝟎. 𝟒𝟎𝟏𝟑
20−20 20−20
(ii)𝑃(20 < 𝑥 < 22) =? From 𝑍 = , we get 𝑍1 = =0
2 2
22−20
And 𝑍2 = = 1.0
2

5
 0 1 𝑍

𝑃(20 < 𝑥 < 22) = 𝑃(0 < 𝑍 < 1)

𝑃(0 < 𝑍 < 1) = 𝟎. 𝟑𝟒𝟏𝟑
Example 4:
The weights of gravel may be modelled by a Normal distribution with
Mean 25.8kg and standard deviation 0.5kg.
(a) Determine the probability that a randomly selected bag will weigh
(i) Less than 25kg
(ii) Between 25.5kg and 26.5 kg
(b) Determine the weight exceeded by 75% of the bags.
SOLUTION:
Let 𝑋 be the Weight of gravel.
(i) 𝜇 = 25.8 and 𝛿 = 0.5
𝑥−𝜇 25−25.8
From 𝑍 = , we get 𝑍 = = −1.6
𝛿 0.5

𝑃(𝑋 < 25) = 𝑃(𝑍 < −1.6)

−1.6 0 𝑍

𝑃(𝑍 < −1.6) = 0.5 − 𝑃(0 < 𝑍 < 1.6) By symmetry

6
 𝑃(𝑍 < −1.6) = 0.5 − 0.4452
𝑃(𝑍 < −1.6) = 𝟎. 𝟎𝟓𝟒𝟖
(iii) 𝑃(25.5 < 𝑥 < 26.5) =?
𝑥−𝜇 25.5−25.8
From 𝑍 = , we get 𝑍1 = = −0.6
𝛿 0.5
26.5−25.8
And 𝑍2 = = 1.4
0.5

−0.6 0 1.4 𝑍

𝑃(25.5 < 𝑥 < 26.5) = 𝑃(−0.6 < 𝑍 < 1.4)

𝑃(−0.6 < 𝑍 < 1.4) = 𝑃(0 < 𝑍 < 0.6) + 𝑃(0 < 𝑍 < 1.4)
𝑃(−0.6 < 𝑍 < 1.4) = 0.2257 + 0.4192
𝑃(−0.6 < 𝑍 < 1.4) = 𝟎. 𝟔𝟒𝟒𝟗
(b)𝑃(𝑥 > 𝑥1 ) = 0.7

0.25 0.50

−𝑍1 0 𝑍

7
 This gives 𝑍1 = −0.674
𝑥−𝜇
From 𝑍 = , we get 𝑥 = 𝑍𝛿 + 𝜇
𝛿

This gives 𝑥1 = (−0.674 × 0.5) + 25.8 and yields 𝑥1 = 25.463

The weight exceeded by 75% of the bags is 𝟐𝟓. 𝟒𝟔𝟑 𝒌𝒈.
Example 5:
The length of similar components produced by a company are
approximated by a normal distribution model with a mean of 5 cm and a
standard deviation of 0.02 cm. If a component is chosen at random, what is
the probability that the length:
(i) Of this component is between 4.98 and 5.02 cm? [𝟎. 𝟔𝟖𝟐𝟔]
(ii) Of this component is between 4.96 and 5.04 cm? [𝟎. 𝟗𝟓𝟒𝟒]
Example 5.1:
A random variable X has a normal distribution such that 𝑃(𝑋 > 9) =
0.9192 and 𝑃(𝑋 < 11) = 0.7580. Find:
(i) Values of the Mean and Standard deviation.
(ii) 𝑃(𝑋 > 10)
SOLUTION:
(i) 𝑃(𝑥 > 9) = 0.9192

0.4192 0.50

−𝑍1 0 𝑍
This gives 𝑍1 = −1.40
For 𝑃(𝑋 < 11) = 0.7580 we get 𝑍2 = 0.70

8
 0.7580

𝑍2

𝑥−𝜇
From 𝑍 = , we get 𝑥 = 𝑍𝛿 + 𝜇
𝛿

We shall have 9 = −1.40𝛿 + 𝜇 …..(i) and 11 = 0.70𝛿 + 𝜇……...(ii).

Solving (i) and (ii) gives 𝛿 = 0.952 and 𝜇 = 10.333
(ii) 𝑃(𝑋 > 10)
𝑥−𝜇 10−10.333
From 𝑍 = , we get 𝑍 = = −0.350
𝛿 0.952

𝑃(𝑋 > 10) = 𝑃(𝑍 > −0.350)

−0.35 0 𝑍

𝑃(𝑍 > −0.35) = 0.5 + 𝑃(0 < 𝑍 < 0.35) By symmetry

𝑃(𝑍 > −0.35) = 0.5 + 0.1368
𝑃(𝑍 > −0.35) = 0.6368
Example 6:
The number of cows owned by residents in a village is assumed to be
normally distributed. 15 % of the residents have less than 60cows while
5% of the residents have over 90 cows.

9
 (i) Determine the values of the Mean and Standard deviation of the
cows.
(ii) If there are 200 residents, find how many have over 80 cows.
SOLUTION:
(i) For 𝑃(𝑋 < 60) = 0.15 , we get 𝑍1 = −1.036
0.35

0.15

−𝑍1 0 𝑍
For 𝑃(𝑋 > 90) = 0.05 , we get 𝑍2 = 1.64
0.45

0.05

0 𝑍2

𝑥−𝜇
From 𝑍 = , we get 𝑥 = 𝑍𝛿 + 𝜇
𝛿

We shall have 60 = −1.036𝛿 + 𝜇 …..(i) and 90 = 1.64𝛿 + 𝜇……...(ii).

Solving (i) and (ii) gives 𝛿 = 11.21 and 𝜇 = 71.61
(ii) 𝑃(𝑋 > 80)
𝑥−𝜇 80−71.61
From 𝑍 = , we get 𝑍 = = 0.748
𝛿 11.21

𝑃(𝑋 > 80) = 𝑃(𝑍 > 0.748)

10
 0 0.748 𝑍

𝑃(𝑍 > 0.748) = 0.5 − 𝑃(0 < 𝑍 < 0.748)

𝑃(𝑍 > 0.748) = 0.5 − 0.2728
𝑃(𝑍 > 0.748) = 0.2272
And now 0.2272 × 200 = 45
Therefore 𝟒𝟓 residents have over 80 cows.
Example 7:
The marks in an examination were normally distributed with mean 𝜇 and
Standard deviation 𝛿. 20% of the candidates scored less than 40 marks
while 10% scored more than 75 marks. Find the:
(i) Values of 𝜇 and 𝛿.
(ii) Percentage of candidates who scored more than 50 marks.
SOLUTION:
(i) Let 𝑋 be the marks in an examination.
For 𝑃(𝑋 < 40) = 0.20 , we get 𝑍1 = −0.842
0.30

0.20

−𝑍1 0

11
 For 𝑃(𝑋 > 75) = 0.10, we get 𝑍2 = 1.282
0.40

0.10

0 𝑍2

𝑥−𝜇
From 𝑍 = , we get 𝑥 = 𝑍𝛿 + 𝜇
𝛿

We shall have 40 = −0.842𝛿 + 𝜇 …..(i) and 75 = 1.282𝛿 + 𝜇……...(ii).

Solving (i) and (ii) gives 𝛿 = 16.48 and 𝜇 = 53.84
(ii) 𝑃(𝑋 > 50)
𝑥−𝜇 50−53.84
From 𝑍 = , we get 𝑍 = = −0.233
𝛿 16.48

𝑃(𝑋 > 80) = 𝑃(𝑍 > −0.233)

−0.233 0 𝑍

𝑃(𝑍 > −0.233) = 0.5 + 𝑃(0 < 𝑍 < 0.233) By symmetry

𝑃(𝑍 > −0.233) = 0.5 + 0.0922
𝑃(𝑍 > −0.233) = 0.5922
0.5922 × 100 = 59.22
The Percentage of candidates who scored more than 50 marks is
𝟓𝟗. 𝟐𝟐%
12
TRIAL QUESTIONS:
1. A random Variable 𝑋 is normally distributed with mean 79 and Variance
144.
Find: (a) 𝑃(𝑥 < 70) (b) 𝑃(64 < 𝑥 < 96)
[𝟎. 𝟕𝟕𝟑𝟒, 𝟎. 𝟖𝟏𝟔𝟏]
2. The length of similar components produced by a company is approximated by a
normal distribution model with a mean of 5 cm and a standard deviation
of 0.02 cm. If a component is chosen at random .what is the probability that the
length of this component is between 4.98 and 5.02 cm? [𝟎. 𝟔𝟖𝟐𝟔]

13