Normal Distribution

Fiona Brocklehurst
Portsmouth Business School
University of Portsmouth

1
Learning Outcomes
1. Identify the use of continuous probability distributions
using the example of the Normal distribution

2. Introduce the concept of a Normal distribution and a

Standard Normal Distribution

3. Understand the use of Standard Normal Distribution

Tables

2
Specific Distributions
 Binomial – discrete
 Poisson – discrete
 Geometric - discrete

 Normal - continuous

3
Continuous probability distribution
- example of the Normal Distribution -

4
Normal Distribution A large number of
practical situations give
data values clustered
around the mean
(symmetrically) - e.g.
height, weights, journey
times, IQs, etc.

x
Random Variable ( e.g. Height) - along x axis
…. is an example of a continuous distribution
- the Random Variable takes continuous values
5
Normal Distribution
The probability that x lies in an interval, e.g. 190-191, is the shaded area

190 cm 191cm x
Random Variable ( e.g. Height) - along x axis
…. is an example of a continuous distribution
- the Random Variable takes continuous values 6
Normal Distribution
The probability that x lies in the interval ( x1, x2 ) is the shaded area

x1 x2 x
Random Variable – e.g. Height along x axis

7
 ‘negative infinity’
Normal Distribution
The probability that x lies in the interval (, x1 )
is the shaded area

x1 x
Random Variable – e.g. Height along x axis

8
Normal Distribution ‘positive infinity’

The probability that x lies in the interval ( x1 , )

is the shaded area

x1 x
Random Variable – e.g. Height along x axis

9
Normal distribution
vs
Standard Normal distribution

10
Normal Distribution
If X is a Random Variable (e.g. height)
which is normally distributed
We write X ~ N ( , 2 )

where

Expected Value = 
and
Variance =  2

11
Standard Normal Distribution
If  = 0 and  = 1
2

Then we write Z ~ N(0,1)

Referred to as Standard Normal

12
Normal Distribution
Normal Distribution

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal - N(0,1)

13
Normal Distribution
Normal Distribution

Mean = 0

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal - N(0,1)

14
Normal Distribution
Normal Distribution

Variance = 1

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal - N(0,1)

15
Identifying probabilities
– using standard normal tables

16
Normal Distribution
Normal Distribution

Probability that z > 1

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal - N(0,1)

17
P(Z > 1) = 0.1587
18
Normal Distribution
Normal Distribution

Probability that z
lies in interval (-1,1)

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal - N(0,1)

19
P(Z > 1) = 0.1587
20
Due to symmetry: P(Z > 1) = P (Z < -1) = 0.1587
P(Z > -1) = 1 – P (Z < - 1) = 0.8413 21
Standard Normal Distribution
Normal Distribution

Probability that z
lies in interval (-1,1)

0.6826

-4 -3 -2 -1 0 1 2 3 4
Z

P(Z > -1) - P(Z > 1) = 0.8413 – 0.1587 = 0.6826

22
Normal Distribution
Normal Distribution

Probability that z
lies in interval (-1.96,1.96)

-1.96 +1.96

-4 -3 -2 -1 0 1 2 3 4
Z

Standard Normal – N(0,1)

23
P(X > 1.96) = 0.0250
24
 P(Z < - 1.96) = P( Z > 1.96) = 0.0250
P(Z > -1.96) = 1 – P(Z < -1.96) = 0.975 25
Normal Distribution
Normal Distribution

Probability that z
lies in interval (-1.96,1.96)

0.95
-1.96 +1.96

-4 -3 -2 -1 0 1 2 3 4
Z

P(Z > 1.96) = 0.0250 P(Z > - 1.96) = 0.9750

P(-1.96 < Z < - 1.96) = P(Z > -1.96) – P(Z > 1.96) = 0.9750-0.0250 = 0.95 26
Standard Normal Distribution
If  = 0 and  = 1
2

Then we write Z ~ N(0,1)

Referred to as Standard Normal

27
Standardising Normal Distribution
-If X is distributed Normally then

1. we subtract the mean value (µ) from X

2. and divide by the standard deviation (σ) of X

-the result, notated usually by Z, is still distributed

Normally but now with mean = 0 and variance = 1

– i.e. the result Z ~ N(0,1)

28
Normal Distribution
If X is N (  ,  2
) and if Z  (X  ) /

then Z is N(0,1)

i.e. the Standard Normal

29
How to use it?
 College examination scores are distributed with mean
500 and standard deviation 100. Find probability that
student scores are over 650.

X ~ N(500, (100)2)
650  500
P( X  650)  P( Z  )
100
 P(Z  1.5 )

 0.0668
30
Example 1:
A company that is considering the launch of a new
product estimates tat the possible demand for the
product, in its first year, will be approximately normally
distributed with a mean of 2000 units and a standard
deviation of 500 units. What is the probability that the
first year demand will be
(a) Over 2500 units?
(b) Less than 1600 units?

31
Answer (a) :
X ~ (2000, (500)2)

P(X > 2500) = ?

2500  2000
Standardise: Z = 1
500

P(X > 2500) = P(Z > 1) = 0.1587 => 15.87%

32
Answer (b) :
X ~ (2000, (500)2)

P(X < 1600) = ?

1600  2000
Z=  0.8
500

P(X < 1600) = P(Z < -0.8) = P(Z > 0.8) = 0.2119

33
Example 2:
On average, last year a local leisure centre had 230
customers per day, standard deviation of 27, and the
distribution of customers was found to be normal.
Determine the probability that on any one day the centre
has:
(a) More than 210 customers?
(b) Between 225 and 250 customers?

34
Answer (a) :
X ~ (230, (27)2)

P(X > 210) = ?

210  230
Z=  0.74
27

P(X > 210) = P(Z > -0.74)

= 1 – P(Z < -0.74)
= 1 – P(Z > 0.74) = 1 – 0.2296 = 0.7704
35
Answer (b):
 X ~ N(230, (27)2)

P ( 225 < X < 250) = P ( X > 225) - P( X > 250)

= P (Z > (225 – 230)/27) – P(Z > (250 – 230)/27)

=P(Z > -0.19) – P(Z > 0.74) = 1 – P(Z > 0.19) – P(Z > 0.74)

=1 - 0.4247 – 0.2296 = 0.3457

36