Normal distribution

and
Standard normal
distribution
Maizam Alias
MBE1223 Statistics in Education
UTHM Business Centre, Bangi
1 -2 October 2010
Understanding of the normal distribution is
important because…
 many psychological and educational variables are
distributed approximately normally. Eg. measures of
reading ability, introversion, job satisfaction, and
memory
 it is easy for mathematical statisticians to work
with. This means that many kinds of statistical tests
can be derived for normal distributions.
 it is easy to convert back and forth from raw
scores to percentiles if the mean and standard
deviation of a normal distribution are known
 Learning outcomes
 Upon completion of this course you should be able to
 Explain the relationship between continuous variables,

frequency distribution, histogram and normal distribution

curves (conceptual knowledge/narrative knowledge)
 Explain the relationship between area under a probability

curve and probability for a continuous probability

distribution. (narrative knowledge)
 Explain how measures of central tendency and dispersion

influence the graph of the probability distribution.

(narrative knowledge)
 Describe major differences and similarities between a

normal distribution and the standard normal distribution.

(narrative knowledge)
 Learning outcomes: continued
 Compute probabilities using a normal probability
distribution. (procedural knowledge)
 Determine probabilities or z-scores associated with
the standard normal distribution given one of those
measures.  Be able to perform similar calculations for
problems involving a non-standard normal
distribution. (procedural knowledge)
 Compute P(a < X < b), P(X > a), and P(X < b) for a
normally distributed variable X manually and using
Excel (procedural knowledge)
What is a normal
distribution?
 Normal distribution is a common data
distribution shape

THE
NORMAL
LAW OF ERROR
STANDS OUT IN THE
EXPERIENCE OF MANKIND
AS ONE OF THE BROADEST
GENERALIZATIONS OF NATURAL
PHILOSOPHY  IT SERVES AS THE
GUIDING INSTRUMENT IN RESEARCH
IN THE PHYSICAL AND SOCIAL SCIENCES AND
IN MEDICINE, AGRICULTURE, AND ENGINEERING 
IT IS AN INDISPENSABLE TOOL FOR THE ANALYSIS AND THE
INTERPRETATION OF THE BASIC DATA OBTAINED BY OBSERVATION AND EXPERIMENT
 William Youden
 A normal distribution is…
•a family of distributions that
have the same general shape
that is sometimes described as
bell-shaped distributions
(symmetrical), i.e,. its mean
= mode = median.
•its size and shape is entirely
determined by two
parameters: the mean,  and
standard deviation, .



 Characteristics of a normal
distribution
 Proportions under the distribution has fixed
values
 About 68.3% of observations from a normal
distribution lie within - and +
 About 95.4% of observations from a normal
distribution lie within -2 and +2
 About 99.7% of observations from a normal
distribution lie within -3 and +3
 What is the use of the normal
distribution?
 To determine the proportion and
percentages of occurrences with respect to a
variable of interest.
 Demonstration 1
 The mean and standard deviation of the height of
male students in KKTM is 165 cm and 10 cm
respectively. What proportion of male students are
between 165 cm and 175cm?
 Demonstration 1 continues
 Solution steps:
 (i) Calculate the number of standard deviations.
 175-165 = 10, i.e. equals to 1 standard deviation above
the mean.
 Draw the distribution and shade the area required.

 Determine the proportion based on the properties of

the normal distributions.
 The curve is symmetrical, so the proportion of students
between 165 - 175 = 0.683/2 = 34.15%.
 Practice 1
 For the same distribution,
 (i) what proportion of students are less than
155 cm tall? (Draw the relevant diagrams
and calculate)
 (ii) What proportion of students is between
135 and 155 cm tall?
 Follow this strategy: Do it individually do
with a friend  discuss with class
 Practice 2
 For the same distribution,
 (i) what proportion of students are greater than
167 cm tall?
 Having difficulty getting the proportion?
Use the standard normal
distribution.
What is a standard normal
distribution?
 Standard normal distribution

 Has a mean of zero

 Has a standard deviation equals to 1.
 Is sometimes called the z-distribution.
 Has an area under its curve equals to 1
Standard normal distribution continues
 Any normal distribution can be transformed
to standard normal distribution (z-
distribution) by the formula:
x
Z

•where X is a score from the original normal distribution,
•µ is the mean of the original normal distribution,
 is the standard deviation of original normal distribution.
Standard normal distribution continues

 A z-score always reflects the number of

standard deviations above or below the mean a
particular distribution of which the score is a
part.
 Demonstration 2
 For instance if a person scores 65 on a test with a
distribution mean of 50 and a standard deviation of
10
 The x-score of 65 would become a z-score of 1.5
using the formula:
 x 65  50
Z Z  1.5
 10

 A z- score of 1.5 means, the original score (65) was

1.5 standard deviations above the mean.
 Mean 50, std dev = 10

0.045
0.04
0.035
0.03
0.025
0.02
0.015
0.01
0.005
0
10 20 30 40 50 60 70 80 90

92.51%

-6 -4 -2 0 1.5 2 4 6
 Demonstration 3
 If a test is normally distributed with a mean of 60 and
a standard deviation of 10, what proportion of the
scores is above 85?
 Solution steps:
 Calculate the number of standard deviations above or
below the mean for 85 by changing the raw score of
85 into a z-score.
 Draw the distribution and shade the area required.
 Determine the proportion based on the properties of
the normal distributions using a table.
Demonstration 3 continues

Mean = 0, std dev =1

0.45

0.4

0.35
0.3

0.25
0.2
0.15

0.1
0.05
0
-4 -3 -2 -1 1E-15 1 2 3 4
0
Demonstration 3 continues
 Standard normal distribution is
applicable to all normal distribution
problems because the value of its
mean and standard deviation is
“standard”
 Do exercise
 Standard Normal Distribution
 Can also be used to convert scores from
percentile and to percentile rank if the
distribution is normal
 Relationship between normal distribution
and percentiles
 One important use of the standard normal
distribution is for converting between scores
from a normal distribution and percentile
ranks.

 Z-scorepercentile rank
 Percentile rankz-score
Demonstration 4: A student gets a z-
score of 1.5
 What does it mean?
 It means he is above X% of his class-mates
 How do you get X?
 Draw the normal distribution for the class
 Sketch the relevant area
 Look up the z-distribution table.
 92.51%

93.32%

-6 -4 -2 0 Z=1.5 2 4 6
 Demonstration 5: If a test is normally
distributed with a mean of 50 and a standard
deviation of 10, what is the percentile rank for
Ali who got 77 in the test? (x-score 
percentile)
 Solution Input X-score
 Convert x-score to z-score
 Refer to z-table Convert x to
z-score
 Report observation in percentage
Look up z-
table
 Relationship between cumulative
probability and normal distribution
Mean 50, std dev = 10

0.045 1.1
0.04 1
0.9
0.035

Cumulative Probability
0.8
0.03 0.7
0.025 0.6
0.02 0.5
0.015 0.4
0.3
0.01
0.2
0.005 0.1
0 0
10 20 30 40 50 60 70 80 90
 The standard normal
distribution is also known as

The normal probability

distribution
 Normal probability
 Area between two scores under the standard
normal distribution curve is the probability of
getting a random data value between the two
scores.
 E.g probability of getting a student with above
85 marks if we randomly select a student from
a class test scores that is normally distributed,
with a mean of 60 and a standard deviation of
10?
 The probability of getting a student with above
85 marks is the area under the curve that is
above 85.
 To get the probability,
 Draw the distribution
 Shade the area that you want
 Change 85 to z score
 Read the probability from the z table.
 Example 3 continues

Mean = 0, std dev =1

0.45

0.4

0.35
0.3

0.25
0.2
0.15

0.1
0.05
0
-4 -3 -2 -1 1E-15 1 2 3 4
0
 Probability area is the area above z=2.5
 P(z<2.5) is 0.9936
 P(z>2.5)= 1- 0.9936
 Do exercise 3
 Example problem
 The life of a drawing pen used by KKTM
students is normally distributed. Suppose
92.51% of the items have lifetimes exceeding
2,160 hours and 3.92% have lifetimes
exceeding 17,040 hours. Find the mean and
the standard deviation of item life
expectancy.  
 Draw a diagram of the normal
distribution with mean µ and
standard deviation σ, and
marked 17,040 hours on the
axis.
 Since the probability of an
item having a lifetime
exceeding 17,040 hours is
3.92% or 0.0392, the
probability that an item has a
lifetime between µ and 17,040
hours is 0.5 -0.0392 = 0.4608.
 If you then convert
this to the standard
normal distribution
using the conversion
z = (x - µ)/ σ and
you get
 Z = (17,040 –µ)/ σ
 From the normal table, the probability that a standard normal
random variable is between 0 and 1.76 is 0.4608.
 Thus  (17,040 - µ)/σ = 1.76
 This gives you an equation relating µ and σ.
 Now go through the same procedure using the fact that the
probability of an item having a lifetime exceeding 2,160 hours
is 92.51% to find a second equation relating µ and σ .
 You can then solve these equations to find µ and σ.
 Be careful about signs when you find this second equation.
The shaded portion of the diagram will be to the left of the
origin so the z-value will be negative.
Questions & Answers
 Areas is 1-std.dev above the mean

0.045
0.04
0.035
0.03
0.025
0.02 68.3/2
0.015
0.01
0.005
0
125 135 145 155 165 175 185 195 205
Same standard deviation different
mean
Same mean different standard
deviation
Areas within 1-std dev away from
mean
Areas between 1-std.dev away fro mean

0.045
0.04
0.035
0.03
0.025
0.02
68.3%
0.015
0.01
0.005
0
125 135 145 155 165 175 185 195 205
Areas within 2-std dev away from
mean
Area between 2- std dev. away from the mean

0.045
0.04
0.035
0.03
0.025
0.02 95.4%
0.015
0.01
0.005
0
125 135 145 155 165 175 185 195 205
Areas withing 3-std dev away from
mean

Areas between 3-std.dev away fro mean

0.045
0.04
0.035
0.03
0.025
0.02 99.7%
0.015
0.01
0.005
0
125 135 145 155 165 175 185 195 205
Areas under Normal distribution