NORMAL DISTRIBUTION

Prepared by Mohammad Nazmul Hoq

Normal Distribution
The normal distribution was discovered by De Moiver as the limiting case of Binomial
distribution in 1733.
If n becomes large i.e. n → ∞ and p & q are fairly near equality i.e. p≅q then the limited
form of binomial distribution is called normal distribution. The probability distribution of
a random variable X is said to have a normal distribution with parameter μ and σ² if the
density function is given by

y = ƒ(x) = ’ –∝ ≤ x ≤∝

Where, y = the computed height of an ordinate at a distance of X from the mean.

σ = Standard deviation of the given normal distribution.

π = the constant = 3.1416
e = the constant = 2.71828
μ = Mean of the random variable X

Normal curve
If we draw the graph of normal distribution, the curve so obtained will be known as
normal curve and is given below

The graph of y = f (x) is a ‘bell shaped curve’. The top of the bell is directly above the
mean μ. For large values of σ, the curve tends to flatten out and for small values of σ, it
has a sharp peak.

Standardized normal variable:

 A random variable with any mean and standard deviation can be transfer to a
standardized normal variable by subtracting the mean dividing by the standard deviation.
For a normal distribution with a mean μ and standard deviation σ the standardized
variable z is obtain as
z=

A value z represents the distance expressed as a multiple of standard deviation that the
value X lies away from the mean. The standardized variable z is called a standard normal
variate which has mean zero and standard deviation 1. In symbols if X→N( μ, σ ) then
z→ N(0,1)

The probability density function of the standard normal variate z is given by

y=f (z) = , –∝ ≤ z ≤∝

Properties of normal distribution:

The following are the important properties of the normal curve and the normal
distribution:

a) Normal distribution is a continuous distribution.

b) It has two parameters.
c) The probability density function of normal distribution is,

y = ƒ(x) = ’ –∝ ≤ x ≤∝

d) The normal curve is symmetrical. (i.e. skewness is 0)

e) The height of the normal curve is at the maximum at the mean. Thus for a
normal distribution mean, median and mode are all equal.
f) The curve approaches nearer and nearer to the base but it never touches it.
g) Mean deviation about mean is ⅘ σ.
h) All odd moments of the normal distribution are zero. i.e. μ₊₁ = 0.
i) β=3 implies the normal curve is neither leptokurtic nor platykurtic.
j) Mean ± σ, mean ± 2σ and mean ± 3σ covers 68.27%, 95.45%, and 99.73% area
respectively.
k) Mean , median and mode of normal distribution are equal.

Importance of Normal Distribution in Statistics:

Normal distribution plays a very important role in statistics because of the following
reasons:
 i) The normal distribution has the remarkable property stated in the so-called
central limit theorem.
ii) As n becomes large, the normal distribution serves as a good approximation
for many discrete distributions.
iii) The proofs of all tests of significance in sampling are based upon the
fundamental assumption that the population from which the samples have
been drawn is normal.
iv) Normal distribution finds large application in statistical quality control theory.
v) Most of the distribution occurring in practices e.g. Binomial, Poisson; Hyper-
geometric distribution etc. can be approximated by the normal distribution
under certain assumptions.
vi) Many of the sampling distribution e.g. students t, F and chi-square tends to
normality for large samples.

Applications of the Normal Distribution

The normal distribution is mostly used for the purposes
1. To approximate or ‘fit’ a distribution of measurement under certain conditions.
2. To approximate the binomial distribution and other discrete or continuous probability
distribution under suitable conditions.
3. To approximate the distributions of means and certain other statistic calculated from
samples, especially large samples.

** When binomial distribution approaches to normal distribution?

Normal distribution is obtained from binomial distribution under the following

conditions:

1) The probability of success p or the probability of failure q is not so small.

2) n, the number of trials is very large i.e. n tends to infinity.

Note: When the number of trials is greater than 20,000, the Binomial Calculator uses a
normal distribution to estimate the cumulative binomial probability. In most cases, this
yields very good results - often accurate to the third decimal place.

** When Poisson distribution approaches to normal distribution?

If the mean , ƛ, of Poisson distribution tends to infinity , then Poisson distribution tends
into normal distribution.

** Why is the normal distribution useful?

• Many things actually are normally distributed, or very close to it. For example, height
and intelligence are approximately normally distributed; measurement errors also often
have a normal distribution
• The normal distribution is easy to work with mathematically. In many practical cases,
the methods developed using normal theory work quite well even when the distribution is
not normal.
• There is a very strong connection between the size of a sample N and the extent to
which a sampling distribution approaches the normal form. Many sampling distributions
based on large N can be approximated by the normal distribution even though the
population distribution itself is definitely not normal.

** When we use standard normal distribution?

There exists a normal distribution with a mean of 0 and a standard deviation of 1. It is
called the standard normal distribution.
It is often used to:
 Compare two or more distributions of data.
 Estimate or to compute probabilities of events involving normal distributions .

** How can we transform normal probability distribution in to standard normal

distribution?
For continuous distributions the probability that the variable will fall between two values
is the area under the curve between those values. In our case one of the values will
always be the mean of the probability distribution. To determine a probability we will
start with a z Score which is calculated as z = (X - Mean)/Standard Deviation. With the
use of a z Score we will be able to transform any normal probability distribution into a
"Standard Normal Distribution".

When Normal distribution tends to standard normal distribution

We know probability density function of normal distribution is

y = ƒ(x) = ’ –∝ ≤ x ≤∝

and the probability distribution function of standard normal distribution is

y=f (z) = , –∝ ≤ z ≤∝

if the mean of normal variate is zero i.e. µ=0 and standard deviation is one i.e. =1
then normal distribution becomes standard normal distribution.

** What are the properties for which we can called density function of normal
distribution as a probability density function?
Since normal distribution satisfies all the properties of probability density function for
that we called density function of normal distribution as a probability density function.
The properties are
1) f(x)≥0

2)
3) The probability is P(E) is given by
 P(E)=

is well defined for any event E.

Problem 1:
On a final examination in mathematics, the mean was 70 and standard deviation was
10. Determine the standard scores (i.e. grades in standard deviation units) of students
receiving the grades a) 72, b) 83 and c) 74.

Solution:
a) We have, z =
b) Try
c) Try

Problem 2:
Referring to previous problem, find the grades corresponding to the standard scores a)
-2 and b) 1.4.

Solution:

a)
We have, z=

Or, X-µ = σ z
Or, X= µ + σ z
Or, X = 70+10×-2
= 70-20
= 50
Problem 3:
Two students were informed that they received standard scores of 0.9 and -0.5
respectively, on a multiple choice examination in English. If their grades were 80 and 65
respectively, find the mean and standard deviation of the examination grades.

Solution:
Using the equation, X = µ + Zσ
We have, 80 = µ + 0.9σ…….. (1) for the first student
And 65 = µ - 0.5σ………. (2) for the second student.

Solving equation (1) and (2), we have, 15 = 1.4σ or, σ = = 10.71 and
µ = 80-0.9 × 10.71 = 80-9.639 = 70.631
Problem 4:
The average daily sale of 500 branch offices was Tk. 150 thousand and the standard deviation
Tk. 15 thousand. Assuming the distribution to be normal indicate how many branches have sales
i) between Tk. 120 thousand and Tk. 145 thousand;
ii) less than Tk. 140 thousand;
iii) over Tk. 155 thousand.

Solution:
Let X denote amount of sales and X follows normal distribution.
Given, µ + 150 and σ = 15, N = 500
i) The probability that a branch have sales between Tk. 120 thousand Tk. 145 thousand
is given by
P(120≤X≤145)
We have, standard normal variate, Z = .

Now standard normal variate corresponding to 120 is Z = = -2 and corresponding to

145 is, Z= = -0.33

Now, P(120≤X≤145) = P( 2≤ Z ≤ 0.33) = P(Z ≤ 0.33)-P(Z ≤ 2)

= 0.3707-0.0228 = 0.3479

Thus, the expected no. branches having sales between Tk. 120 thousand and Tk. 145 thousand is
given by
N P(120≤X≤145) = 500 × 0.3479 = 173.95 = 174 (app.)

(ii) The probability that a branch have sales less than Tk. 140 thousand is given by
P(X≤140)
When X = 140, then Z = = 0.67
Now,
P(X≤140) = P(Z≤ 0.67) = 0.2514

Thus, the expected no. branches having sales less than Tk. 140 thousand is given by

N P(X≤140) = 500×0.2514 = 12507 = 126(app.)

ii) The probability that a branch have sales over Tk. 155 thousand is given by

P(155≤X)
When X = 155, then Z = = 0.33
Now,
P(155≤X) = P(0.33≤Z)
= 1 – P(Z≤0.33) = 1-0.6293 = 0.3707
Thus, the expected no. branches having sales over Tk. 155 thousand is given by
 N P(155≤X) = 500 × 0.3707 = 185.35 = 185(app.)

Problem 5:
A workshop produces 2000 units per day. The average weight of units is 130 kg.
With a standard deviation of 10 kg. Assuming normal distribution, how many units are
expected to weight
i) less than 142 kg.;
ii) more than 135 kg.;
iii) between 120 kg. to 145 kg..

Problem 6:
The mean and standard deviation of wages of 1000 labors are Tk. 50 and Tk. 10.
The wages of workers are normally distributed. Find the no. of workers of which wages
are (i) from Tk. 45 to Tk. 75; (ii) less than Tk. 80.

Problem 7:
The time required by bank cashier be dealt with a customer has been observed to be
normally distributed with mean 25 seconds and a standard deviation 10 seconds. Find the
probability that a customer arriving at random will have to wait (i) between 20 and 28
seconds; (ii) less than 23 seconds.

Problem 8:
How many workers have a salary (i) above Tk. 675; (ii) between Tk. 490 and Tk.
550; (iii) at most Tk. 560 in the distribution whose mean is Tk. 500 and standard
deviation is Tk. 100 and the number of workers in that factory is 1500, if the salary of
workers follows normal law?

Problem 9:
The mean and standard deviation for the life times of a population of light tubes are
1200 hours and 150 hours respectively. Assuming these life times are normally
distributed, what is the probability that a light bulb will last

i) over 1100 hrs.;

ii) between 1000 hrs. and 1300 hrs.

Problem 10:
In an intelligence test conducted on 1000 students, the average score was 75 and
standard deviation 10. Find the no. of students getting i) more than 80 marks; ii) less than
74 marks.