THE NORMAL PROBABILITY

DISTRIBUTION

ENS185 2nd Semester

 2

When computing probabilities for discrete

random variables, we usually substitute the
value of the random variable into a formula.
However, this is not the same for continuous
variables since they can take up infinite
values within an interval.
 PROPERTIES OF THE
NORMAL PROBABILITY
DISTRIBUTION
Probability 4

PROBABILITY DENSITY FUNCTION

A probability density function (pdf) is an equation
used to compute probabilities of
continuous random variables. It must satisfy the
following two rules:

1. The total area under the graph of the equation

over all possible values of the
random variable must equal 1.
∞
2. The height of the graph of the equation must be 𝑃 = න 𝑓(𝑥) 𝑑𝑥 = 1
greater than or equal to 0 for all −∞
possible values of the random variable.
Probability 5

PROBABILITY DENSITY FUNCTION

Unlike the case of discrete random variables, for a continuous random variable any
single outcome has probability zero of occurring. (ex. P(x=1)=0)

The probability that a random variable X takes a value in the interval [a,b] is
given by the function f(x)
𝑏
𝑃 𝑎 ≤ 𝑋 ≤ 𝑏 = න 𝑓(𝑥) 𝑑𝑥
𝑎

The area under the graph of a density

function over an interval represents the
probability of observing a value of the
random variable in that interval.
Probability 6

UNIFORM PROBABILITY DISTRIBUTION

This is a type of continuous probability
distributions is equally likely. In a given
interval, all values of the random variable X
has the same chance of occurring.

The probability density function of a uniform distribution is a constant.

1
𝑓 𝑥 =
𝑏−𝑎

Where b=upper limit, a=lower limit.

𝑎+𝑏 𝑏−𝑎 2
𝜇= 𝜎=
2 12
Presentation title 7

• 𝑎=5
• b= 10
• 𝑃(𝑥 ≥ 6)
Probability 8

NORMAL PROBABILITY DISTRIBUTION

A continuous random variable is normally distributed, or has a normal
probability distribution, if its relative frequency histogram has the shape of a
normal curve.
Probability 9

PROPERTIES OF THE NORMAL CURVE

1. The normal curve is symmetric about the mean.
2. Because median=mean=mode, the normal curve has
a single peak and the highest point occurs at 𝑥 = 𝜇
3. The normal curve has inflection points at 𝜇 − 𝜎 and
𝜇+𝜎
4. The area under the normal curve is 1.
5. Area below or above the mean is 0.5.
6. As x increases without bound (gets larger and larger),
the graph approaches but never reaches, the
horizontal axis. As x decreases without bound (gets
more and more negative), the graph approaches, but
never reaches, the horizontal axis.
7. It follows the Empirical rule: 68-95-99.7
Probability 10

STANDARDIZING THE NORMAL CUVE

Recall, the z-score allows us to transform a random variable X with mean µ and
standard deviation σ into a random variable Z with mean 0 and standard
deviation 1.

The random variable Z is said to have a standard normal distribution:

𝑥−𝜇
𝑧=
𝜎

The Z-score can then be used to find the area under the curve (this is equal to
the probability).
Presentation title 11

EXAMPLE
A pediatrician obtains the heights of her three-
year-old female patients. The heights are
approximately normally distributed, with mean
38.72 inches and standard deviation 3.17 inches.
Use the normal model to determine the
proportion of the three-year-old females that
have a height less than 35 inches.

𝐹𝑖𝑛𝑑 𝑃(𝑥 < 35)

Presentation title 12

SOLUTION
Find the corresponding Z-score
35 − 38.72
𝑧= = −1.17
3.17
Since we are interested with P(x<35), we want
the area to the left of the z-score.
Presentation title 13

SOLUTION
Presentation title 14

EXAMPLE
A pediatrician obtains the heights of her three-
year-old female patients. The heights are
approximately normally distributed, with mean
38.72 inches and standard deviation 3.17 inches.
Use the normal model to determine the
proportion of the three-year-old females that
have a height greater than 39 inches.

𝐹𝑖𝑛𝑑 𝑃(𝑥 > 39)

Presentation title 15

SOLUTION
Find the corresponding Z-score
39 − 38.72
𝑧= = 0.09
3.17
Since we are interested with P(x>39), we want
the area to the right of the z-score.
P 𝑧 > 0.09 = 1 − 0.53586 = 0.46414
Presentation title 16

SOLUTION
Presentation title 17

EXAMPLE
A pediatrician obtains the heights of her three-
year-old female patients. The heights are
approximately normally distributed, with mean
38.72 inches and standard deviation 3.17 inches.
Use the normal model to determine the
proportion of the three-year-old females that
have a height between 35 and 39 inches.

𝐹𝑖𝑛𝑑 𝑃(35 < 𝑥 < 39)

Presentation title 18

EXAMPLE
The heights of a pediatrician’s three-year-old
females are approximately normally distributed,
with mean 38.72 inches and standard deviation
3.17 inches. Find the height of a three-year-old
female at the 25th percentile.

𝐹𝑖𝑛𝑑 𝑃 𝑥 <? = 0.25

Presentation title 19

EXAMPLE
Z-score Pz
-0.67 0.25143
? 0.25
-0.68 0.24825

Interpolate
−0.67 − 𝑧 0.25143 − 0.25
=
−0.67 − (−0.68) 0.25143 − 0.24825
𝑧=
Using z, solve for x.
𝑥 − 38.72
𝑧=
3.17
ASSESSING NORMALITY
 21

A random variable X is normally distributed

or approximately normal given that the
histogram is symmetric and bell-shaped. This
works well for large data sets, but this is not
always the case for smaller samples.
Probability 22

USING NORMAL PROBABILITY PLOTS

A normal probability plot is a graph that plots observed data versus normal
scores. A normal score is the expected z-score of the data value, assuming that
the distribution of the random variable is normal.

If sample data are taken from a population that is normally distributed, a normal
probability plot of the observed values versus the expected z-scores will be
approximately linear.
Probability 23

CONSTRUCTING A NORMAL PROBABILITY PLOT

The data in Table 4 represent the finishing time (in seconds) for six randomly
selected races of a greyhound named Barbies Bomber in the 3-mile race at
Greyhound Park in Dubuque, Iowa. Is there evidence to support the belief that
the variable “finishing time” is normally distributed?
Probability 24

CONSTRUCTING A NORMAL PROBABILITY PLOT

Step 1: Arrange the data in ascending order

Index Observed Value 𝑓𝑖 Expected z-score

1 31.26
2 31.35
3 31.91
4 32.06
5 32.37
6 32.52
Probability 25

CONSTRUCTING A NORMAL PROBABILITY PLOT

𝑖−0.375
Step 2: Compute 𝑓𝑖 = where i is the index (the position of the data value in the
𝑛+0.25
ordered list) and n is the number of observations.)

Index Observed Value 𝑓𝑖 Expected z-score

1 31.26 1 − 0.375
𝑓𝑖 = = 0.10
6 + 0.25
2 31.35
3 31.91
4 32.06
5 32.37
6 32.52
Probability 26

CONSTRUCTING A NORMAL PROBABILITY PLOT

Step 3: Find the z-score corresponding to 𝑓𝑖 from Table V.

Index Observed Value 𝑓𝑖 Expected z-score

1 31.26 1 − 0.375
𝑓𝑖 = = 0.10
6 + 0.25 -1.28
2 31.35
3 31.91
4 32.06
5 32.37
6 32.52
Probability 27

CONSTRUCTING A NORMAL PROBABILITY PLOT

Step 4: Plot the observed values on the horizontal axis and the corresponding
expected z-scores on the vertical axis.

Index Observed Value 𝑓𝑖 Expected z-score

1 31.26 1 − 0.375
𝑓𝑖 = = 0.10
6 + 0.25 -1.28
2 31.35 0.26 -0.64
3 31.91 0.42 -0.20
4 32.06 0.58 0.20
5 32.37 0.74 0.64
6 32.52 0.90 1.28
 28

𝑟 = 0.970
Since the correlation coefficient
(0.970>0.888) is greater than the
critical value for n=6, it is reasonable
to conclude that the data is
approximately normally distributed.
 THE NORMAL
APPROXIMATION TO THE
BINOMIAL DISTRIBUTION
Probability 30

BINOMIAL PROBABILITY DISTRIBUTION

An experiment is said to be a binomial experiment if
1. The experiment is performed a fixed number of times (n trials).
Each experiment is called a trial.
2. The trials are independent.
3. For each trial, there are two mutually exclusive outcomes:
success (p) and failure (q=1-p).
4. The probability of success is the same for each trial.
Let X be the number of success in n trials.
 31

For a fixed p, as the number of trials n in a

binomial experiment increases, the
probability distribution of the random
variable X becomes more nearly symmetric
and bell shaped.

As a rule of thumb, if 𝑛𝑝 1 − 𝑝 ≥ 10, the

probability distribution will be
approximately symmetric and bell-shaped.
Probability 32

NORMAL APPROXIMATION
If 𝑛𝑝 1 − 𝑝 ≥ 10, the binomial random variable X is approximately normally
distributed with
𝜇𝑥 = 𝑛𝑝
𝜎𝑥 = 𝑛𝑝(1 − 𝑝)
Normal Probability 33

Exact Approximate Probability Using Keywords

Probability Normal
using Binomial
P(a) 𝑃(𝑎 − 0.5 ≤ 𝑋 ≤ 𝑎 + 0.5) Equal to
P(X≤a) 𝑃(𝑋 ≤ 𝑎 + 0.5) At most, less than or equal to
P(X≥a) 𝑃(𝑎 − 0.5 ≤ 𝑋) At least, greater than or equal
to
P(a≤X≤b) 𝑃(𝑎 − 0.5 ≤ 𝑋 ≤ 𝑏 + 0.5)
P(a<X) 𝑃(𝑎 + 0.5 < 𝑋) Greater than
P(X<a) 𝑃(𝑋 < 𝑎 − 0.5) Less than
Probability 34

EXAMPLE
According to the American Red Cross, 7% of
people in the United States have blood type O-
negative. What is the probability that, in a
simple random sample of 500 people in the
United States, fewer than 30 have blood type
O-negative?
Probability 35

SOLUTION
Approach:
1. This is a binomial experiment with n=500
2. The probability of success is p=0.07
Probability 36

SOLUTION
Verify if 𝒏𝒑 𝟏 − 𝒑 ≥ 𝟏𝟎

(500)(0.07) 1 − 0.07 ≥ 10
32.55 ≥ 10
Probability 37

SOLUTION
Compute for the mean and standard
deviation
𝜇𝑥 = 𝑛𝑝
𝜇𝑥 = 500 0.07 = 35

𝜎𝑥 = 𝑛𝑝(1 − 𝑝)
𝜎𝑥 = 500 0.07 1 − 0.07 = 32.55
Probability 38

SOLUTION
Find P(x<30)
𝑃 𝑥 < 30 = 𝑃(𝑥 ≤ 29)

Normal approximation
𝑃 𝑥 < 29.5

Solve for the z-score

29.5 − 35
𝑧= = −0.96
32.55
Probability 39

SOLUTION
Probability 40

EXAMPLE
What is the probability that, in a simple random
sample of 500 people in the United States, 20
have blood type O-negative?
REFERENCE
Statistics: Informed Decisions
using Data with Integrated
Review by Michael Sullivan III

Chapter 5