Chapter 3: Special Probability Distributions

I. Discrete Probability Distributions

3.1 Bernoulli & Binomial Distributions
3.2. Geometric Probability Distribution
3.3. Hyper-Geometric Distribution
3.4. The Poisson Distribution
II. Continuous Probability Distributions
3.5. Uniform Density
3.6. The Normal Distribution
III. Normal Approximation
3.7. The Normal Approximation to the Binomial Distribution
3.1. Bernoulli and Binomial Distribution
3.1.1. Bernoulli Distribution

• Bernoulli is a binomial distribution with a single trial

➢ Its probability mass function: 𝑓 𝑥 = 𝑝 𝑥 (1 − 𝑝)1−𝑥 , x = 0, 1
3.1.2. Binomial Distribution

• A Binomial Experiment is a probability experiment that satisfies

the following conditions.

1. n, the number of trails is finite

2. Each trail results in one of two possible outcomes: success
(S) or failure (F).
3. The probability of a success P (S) is the same for each trial.
4. Trials are independent
Notation for Binomial Experiments

Symbol Description
n The number of times a trial is repeated.

p = P ( S) The probability of success in a single trial.

q = P ( F) The probability of failure in a single trial. [q = 1 – p]

x The random variable represents a count of the number

of successes in n trials: x = 0, 1, 2, 3, … , n.
Binomial Probability Formula
In a binomial experiment, the probability of exactly x successes in n trials is

P (x ) = nC x p xq n − x = n! p xq n − x .
(n − x )! x !

Example 1: Studies show color blindness affect about 8% of men. A random

sample of 10 men is taken.
a) Does this question fulfill the conditions of a binomial distribution?
b) What is the probability that all men are color blind?
c) What is the probability that no men are color blind?
d) What is the probability that at least 3 mean are color blind?
Binomial Distribution: Mean, Variance and Standard Deviation
Population Parameters of a Binomial Distribution
Mean: μ = np
σ 2 = npq
Variance:
Standard deviation: σ = npq
Example 1:
One out of 5 students at Premium College skip breakfast in the morning. Find the mean, variance
and standard deviation, if 10 students are randomly selected.

n = 10 μ = np σ 2 = npq σ = npq
p = 1 = 0.2 = 10(0.2) = (10)(0.2)(0.8) = 1.6
5
q = 0.8 =2 = 1.6  1.3
3.2. Geometric Probability Distribution

❑ Experimenting until success is obtained!

❑ A geometric distribution is a discrete probability distribution of a
random variable x that satisfies the following conditions.
❑ Characteristics:
1) Binary (success or failure)
2) Independent trails
3) Number of trails until the first success
4) Success is the same for each trail (i.e., probability is the same for
each trial)

The probability that the first success will occur on trial x is

P (x) = pqx – 1, where q = 1 – p.
…geometric probability … (Cont’d)

❑ Here, instead of the number of successes that occur in n trials, the

geometric random variable X is the number of the trial on which the first
success occurs.
❑ Thus, the experiment consists of a series of trials that is concluded when
the first success is observed.
❑ Consequently, the experiment could end with the first trial if a success is
observed or it could go on indefinitely.
Example: Geometric Distribution

Shoa Supermarket puts a winning game piece on every fifth package of

French fries. Find the probability that you will win a prize,
a.) with your third purchase of French fries,
b.) with your third or fourth purchase of French fries.

p = 0.20 q = 0.80
a.) x = 3 b.) x = 3, 4
P (3) = (0.2)(0.8)3 – 1 P (3 or 4) = P (3) + P (4)
= (0.2)(0.8)2  0.128 + 0.102
= (0.2)(0.64)  0.230
= 0.128
Mean and Variance of Geometric Distribution

❑ Mean = E(X) = 1/p

❑ Variance (X) = q/p2
Example: Refer to the previous example and find the mean and
variance of the geometric distribution.
• Mean = 1/p = 1/0.2 = 5
• Variance = q/p2 = 0.8/(0.22) = 20
3.3. Hyper-Geometric Probability Distribution
❑ Suppose a set of N objects contains k objects that are classified as
successes and N-k objects that are classified as failures, then with a
sample size of n randomly selected objects, without replacement
❑ Probability mass function is:
where, N = population size
K = # of success states in the population
n = # of draws (i.e., quantity drawn in each trial)
k = # of observed successes

Example:
1) A deck of cards contains 20 cards: 6 red cards and 14 black cards. 5 cards are drawn
randomly without replacement. What is the probability that exactly 4 red cards are
drawn?(Answer= 0.0135)
2) A candy dish contains 100 jellybeans and 80 gumdrops. Fifty candies are picked at
random. What is the probability that 35 of the 50 are gumdrops? The two groups are
jellybeans and gumdrops.
3.4. Poisson Probability Distribution

The Poisson distribution is a discrete probability distribution of a random variable x

that satisfies the following conditions.
Example: Poisson Distribution
The mean number of power outages in Addis Ababa is 4 per month.
Find the probability that in a given month,
a.) there are exactly 3 outages,
b.) there are more than 3 outages.

b.) P (more than 3)

= 1 − P (x  3)
43(2.71828)-4
P (3) = = 1 − [P (3) + P (2) + P (1) + P (0)]
3!

 0.195 = 1 − (0.195 + 0.147 + 0.073 + 0.018)

 0.567
Mean & Variance of Poisson Distribution

Summary:
Distribution E(x) Var(X)

Binomial

Geometric

Poisson
B) Continuous Probability Distributions
❑ Uniform Probability Distribution
❑ Normal Probability Distribution

Uniform Normal
f (x) f (x)

x x
Continuous Probability Distributions

A continuous random variable can assume any value in

an interval on the real line or in a collection of intervals.

It is not possible to talk about the probability of the

random variable assuming a particular value.

Instead, we talk about the probability of the random

variable assuming a value within a given interval.
 …Continuous Probability… (Cont’d)
The probability of the random variable assuming a value within
some given interval from x1 to x2 is defined to be the area under the
graph of the probability density function between x1 and x2.

Uniform Normal
f (x) f (x)

x x
x1 x2 x1 x2
3.5. Uniform Probability Distribution
A random variable is uniformly distributed
whenever the probability is proportional to the
interval’s length.
The uniform probability density function is:

f (x) = 1/(b – a) for a < x < b

=0 elsewhere
where: a = smallest value the variable can assume
b = largest value the variable can assume
Uniform Probability Distribution
Expected Value of x

E(x) = (a + b)/2

Variance of x

Var(x) = (b - a)2/12
Area as a Measure of Probability
The area under the graph of f(x) and probability are
identical.

This is valid for all continuous random variables.

The probability that x takes on a value between some

lower value x1 and some higher value x2 can be found
by computing the area under the graph of f(x) over the
interval from x1 to x2.
Example: Uniform Probability Distribution
3.6. Normal Probability Distribution
❑ The normal probability distribution is the most important
distribution for describing a continuous random variable.

❑ It is widely used in statistical inference.

❑ Abraham de Moivre, a French mathematician,

published The Doctrine of Chances in 1733.

❑ He derived the normal distribution.

Normal Probability Distribution
Normal Probability Density Function

1 − ( x −  )2 /2  2
f (x) = e
 2
where:
 = mean
 = standard deviation
 = 3.14159
e = 2.71828
 …Normal …(Cont’d)
Characteristics

The distribution is symmetric; its skewness

measure is zero.

x
 …Normal …(Cont’d)
Characteristics
The entire family of normal probability
distributions is defined by its mean  and its
standard deviation  .
Standard Deviation 

x
Mean 
 …Normal …(Cont’d)
Characteristics
The highest point on the normal curve is at the
mean, which is also the median and mode.

x
 …Normal …(Cont’d)
Characteristics
The mean can be any numerical value: negative,
zero, or positive.

x
-10 0 25
 …Normal …(Cont’d)
Characteristics
The standard deviation determines the width of the
curve: larger values result in wider, flatter curves.
 = 15

 = 25

x
 …Normal …(Cont’d)
Characteristics
Probabilities for the normal random variable are given by areas under
the curve. The total area under the curve is 1
(.5 to the left of the mean and .5 to the right).

.5 .5

x
Standard Normal Probability Distribution

Characteristics

A random variable having a normal distribution

with a mean of 0 and a standard deviation of 1 is
said to have a standard normal probability
distribution.
 Standard Normal Probability Distribution

Characteristics
The letter z is used to designate the standard
normal random variable.

=1

z
0
Standard Normal Probability Distribution

Converting to the Standard Normal Distribution

x−
z=


We can think of z as a measure of the

number of standard deviations x is from .
 Example: Normal Probability (finding probabilities)

A survey indicates that people use their cellular phones an average of

1.5 years before buying a new one. The standard deviation is 0.25
year. A cellular phone user is selected at random.
Find the probability that the user will use their current phone for less
than 1 year before buying a new one. Assume that the variable x is
normally distributed and from normal table P(Z < -2) = 0.4772).
(Adapted from Fonebak)
Interpretation: So, 2.28% of cellular phone users will use their
cellular phone for less than 1 year before buying a new one.
Because 2.28% is less than 5%, this is an unusual event.
3.7. Normal Approximation to Binomial Distribution
❑ Binomial probabilities - If the following conditions are met,
binomial probabilities can be approximated using a normal
distribution.
Let 𝑿 be a binomial random variable with 𝒏 trials and success
probability 𝒑 . If 𝒏𝒑 ≥ 𝟏𝟎 and 𝒏(𝟏 − 𝒑) ≥ 𝟏𝟎 , then 𝑿 is
approximately normal with mean 𝝁𝒙 = 𝒏𝒑 and standard deviation
𝝈𝒙 = 𝒏𝒑(𝟏 − 𝒑).
❑ The binomial distribution is discrete, whereas the normal
distribution is continuous.
❑ The continuity correction is an adjustment to be made when
approximating a discrete distribution with a continuous one,
which can improve the accuracy of the approximation.
Continuity Correction
❑ Suppose a fair coin is tossed 100 times, let 𝑿 represent the number of heads that
result. Then 𝑋 has a binomial distribution with 𝒏 = 100 trials and success probability
𝒑 = 0.5. If we wanted to compute the probability 𝑋 is between 45 and 55 [ i.e. 𝑷(45 <
𝑿 < 55) ], the probability will differ depending on whether the endpoints 45 and 55
are included.
❑ To compute 𝑷(45 < 𝑿 < 55), the areas of the rectangles
corresponding to 45 and to 55 should be excluded. To
approximate undethis probability with the normal curve,
compute the area r the curve between 45.5 and 54.5.
❑ To compute 𝑷(45 ≤ 𝑿 ≤ 55), the areas of the rectangles
corresponding to 45 and to 55 should be included. To
approximate this probability with the normal curve,
compute the area under the curve between 44.5 and
55.5.
Continuity Correction Procedures
1. When using the normal distribution as an approximation to the binomial
distribution, always use the continuity correction.

2. In using the continuity correction, first identify the discrete whole number
x that is relevant to the binomial probability problem.
3. Draw a normal distribution centered about µ, then draw a vertical strip
area centered over x . Mark the left side of the strip with the number X−
0.5, and mark the right side with x + 0.5. For x = 64, draw a strip from
63.5 to 64.5. Consider the area of the strip to represent the
probability of discrete number x.
 …continuity …(Cont’d)
4. Now determine whether the value of x itself should be included in the
probability you want. Next, determine whether you want the
probability of at least x, at most x, more than x, fewer than x, or
exactly x. Shade the area to the right or left of the strip, as
appropriate; also shade the interior of the strip itself if and only if x
itself is to be included, the total shaded region corresponds to
probability being sought.
Example 1: Normal Approximation
Let 𝑋 be the number of heads that appear when a fair coin is tossed 100 times. Use the
normal curve to find 𝑃(45 ≤ 𝑋 ≤ 55).

Solution:
First: The number of trials is 𝑛 = 100. Since the coin is fair, the success
probability is 𝑝 = 0.5. Therefore, 𝑛𝑝 = (100)(0.5) = 50 ≥ 10 and
𝑛(1 − 𝑝) = (100)(1 − 0.5) = 50 ≥ 10. We may use the normal
approximation.
Second: We compute the mean and standard deviation of 𝑋:
𝜇𝑥 = 𝑛𝑝 = 100 0.5 = 50
𝜎𝑥 = 𝑛𝑝(1 − 𝑝) = (100)(0.5)(1 − 0.5) = 5
Third: Because the probability is 𝑃(45 ≤ 𝑋 ≤ 55), we want to include both 45
and 55. Therefore, we set the left endpoint to 44.5 and the right
endpoint to 55.5.
From Normal Table [𝑃(−1.1 ≤ 𝑍 ≤ 0) = 0.3643]
Twice 𝑃(−1.1 ≤ 𝑍 ≤ 0) is 0.7287 or 72.87%
Example: Continuity Correction
A fair coin is tossed 100 times. Let 𝑋 be the number of heads that appear.

❑To approximate 𝑃(𝑋 ≤ 55), we would find

the area to the left of 55.5.

❑To approximate 𝑃(𝑋 ≥ 55), we would find

the area to the right of 54.5.

❑To approximate 𝑃(𝑋 = 55), we would find

the area between 54.5 and 55.5.
Approximating Binomial by Normal
Binomial Normal
When finding: Use:
𝑷(𝑿 = 𝒂) 𝑷(𝒂 − 𝟎. 𝟓 < 𝑿 < 𝒂 + 𝟎. 𝟓)
𝑷(𝑿 ≥ 𝒂) 𝑷(𝑿 ≥ 𝒂 − 𝟎. 𝟓)
𝑷(𝑿 > 𝒂) 𝑷(𝑿 > 𝒂 + 𝟎. 𝟓)
𝑷(𝑿 ≤ 𝒂) 𝑷(𝑿 < 𝒂 + 𝟎. 𝟓)
𝑷(𝑿 < 𝒂) 𝑷(𝑿 < 𝒂 − 𝟎. 𝟓)
For all cases, 𝝁 = 𝒏𝒑, 𝝈 = 𝒏𝒑𝒒, 𝒏𝒑 ≥ 10, 𝒏𝒒 ≥ 10
Areas to Use When the Continuity Correction is Applied
Suppose the mean 𝝁 = 𝟓𝟎

x = at least 64 .
= 64, 65, 66, . . .

50 64
63.5

x = more than 64
= 65, 66, 67, . . .

50 65
64.5

x = at most 64
= 0, 1, . . . 62, 63, 64
50 64
64.5

x = fewer than 64
= 0, 1, . . . 62, 63
50 63
63.5
x = exactly 64

50 64

50
63.5 64.5

Interval represents discrete number 64

Example 2: Normal Approximation
The FDRE Ministry of Education reported that 66% of students who
graduated from high school enrolled in college. One hundred high school
graduates are sampled. Let 𝑋 be the number students who enrolled in
college. Find 𝑃(𝑋 ≤ 75).
Solution:
The number of trials is 𝑛 = 100 and the success probability is 𝑝 = 0.66. Therefore,
𝑛𝑝 = (100)(0.66) = 66 ≥ 10 and 𝑛 1 − 𝑝 =
(100)(1 − 0.66) = 34 ≥ 10. We may use the normal approximation.
We compute the mean and standard deviation of 𝑋:
𝜇𝑥 = 𝑛𝑝 = 100 0.66 = 66
𝜎𝑥 = 𝑛𝑝(1 − 𝑝) = (100)(0.66)(1 − 0.66) = 4.73709
P (Z ≤ 2.00) = 0.9772
Because the probability is 𝑃(𝑋 ≤ 75), we compute the area
to the left of 75.5. Using tables, we find that the probability is 0.9772.
 Key takeaway message:

• Check if 𝑛𝑝 ≥ 10, 𝑛𝑞 ≥ 10
• Calculate mean (𝝁 = 𝒏𝒑) and standard deviation = 𝒏𝒑𝒒
• How to apply the continuity correction
• How to use the normal curve to approximate binomial
probabilities

END OF CHAPTER 3