Section 5.

2: Binomial Probability Distribution

Section 5.1 introduced the concept of a probability distribution. The focus of the section was on
discrete probability distributions (pdf). To find the pdf for a situation, you usually needed to
actually conduct the experiment and collect data. Then you can calculate the experimental
probabilities. Normally you cannot calculate the theoretical probabilities. However, there are
certain types of experiments that allow you to calculate the theoretical probability. One of those
types is called a Binomial Experiment.

Properties of a binomial experiment:

1) Fixed number of trials, n, which means that the experiment is repeated a specific number of
times.
2) The n trials are independent, which means that what happens on one trial does not influence
the outcomes of other trials.
3) There are only two outcomes possible for each trial of the experiment, which are called a
success and a failure.
4) The probability of a success doesn’t change from trial to trial, where p = probability of
success.

If you know you have a binomial experiment, then you can calculate binomial probabilities.
This is important because binomial probabilities come up often in real life. Examples of
binomial experiments are:
Toss a fair coin ten times, and find the probability of getting two heads.
Question twenty people in class, and look for the probability of more than half being
women.
Shoot five arrows at a target, and find the probability of hitting it five times.

To develop the process for calculating the probabilities in a binomial experiment, consider
example #5.2.1.

Example #5.2.1: Deriving the Binomial Probability Formula

Suppose you are given a 3-question multiple-choice test. Each question has 4 responses
and only one is correct. Suppose you want to find the probability that you can just guess
at the answers and get 2 questions right. (Teachers do this all the time when they make
up a multiple-choice test to see if students can still pass without studying. In most cases
the students can’t.) To help with the idea that you are going to guess, suppose the test is
in Martian.

a.) What is the random variable?

Solution:
rv X = number of correct answers out of 3
b.) Is this a binomial experiment?

Solution:
1.) There are 3 questions, and each question is a trial, so there are a fixed number of
trials. In this case, n = 3.
2.) Getting the first question right has no effect on getting the second or third
question right since you are guessing, thus the trials are independent.
3.) Either you get the question right or you get it wrong, so there are only two
outcomes. In this case, the success is getting the question right.
4.) The probability of getting a question right is one out of four since you are
guessing. This is the same for every trial since each question has 4 responses. In
1 1 3
this case, p  and q  1  
4 4 4

This is a binomial experiment, since all of the properties are met.

c.) What is the probability of getting 2 questions right?

Solution:
To answer this question, start with the sample space.
S = {RRR, RRW, RWR, WRR, WWR, WRW, RWW, WWW}, where RRW means
you get the first question right, the second question right, and the third question
wrong. The same is similar for the other outcomes.

Now the event space for getting 2 right is {RRW, RWR, WRR}. What you did in
chapter four was just to find three divided by eight. However, this would not be right
in this case. That is because the probability of getting a question right is different
from getting a question wrong. What else can you do?

Look at just P(RRW) for the moment. Again, that means

P(RRW) = P(R on 1st, R on 2nd, and W on 3rd)
Since the trials are independent, then
P(RRW) = P(R on 1st, R on 2nd, and W on 3rd)
= P(R on 1st) * P(R on 2nd) * P(W on 3rd)
So we multiply p * p * q
2 1
1 1 3 1 3
P  RRW   * *     
4 4 4 4 4

The same is true for P(RWR) and P(WRR). To find the probability of 2 correct
answers, we will add these three probabilities together. We get
P  2 correct answers   P  RRW   P  RWR   P  WRR 
2 1 2 1 2 1
1 3 1 3 1 3
            
4 4 4 4 4 4
2 1
1 3
 3   
4 4
 d.) What is the probability of getting zero right, one right, and all three right?

Solution:
You could go through the same argument that you did above and come up with the
following:

x right P(x right)

0 right 0
1 3
3

1*    
4 4
1 right 1
1 3
2

3*    
4 4
2 right 2
1 3
1

3*    
4 4
3 right 3
1 3
0

1*    
4 4

There is a pattern to these probabilities and the formula in the box below is the
mathematical formula to describe that pattern. Thankfully we have technology so we are
never going to have to use this formula.

First, the random variable in a binomial experiment is X = number of successes in n trials. Be

careful, a success is not always a good thing. Sometimes a success is something that is bad, like
finding a defect. A success just means you observed the outcome you are interested in counting.

Binomial Formula for the probability of x successes in n trials is

n!
P  X  x  p x 1  p   binompdf  n, p, x 
n x

x ! n  x !
NOTE: You are never going to use this formula. This is just in the book so that you know
what the calculator is actually computing when we use binompdf.

There are two built-in functions in the distribution menu on the calculator for computing
binomial probabilities:
1. P  X  x   binompdf  n, p, x 
2. P  X  x   binomcdf  n, p, x 
Both binompdf and binomcdf commands are found in the DISTR menu.

TECHNOLOGY: BINOMIAL PROBABILITIES

Using your TI84:
 First push 2nd VARS to open the distribution menu and then scroll down until you find
binompdf or binomcdf (depending on what you are wanting to compute)
o binompdf computes the probability that x is equal to a number
o binomcdf computes the probability that x is less than or equal to a number
 You will get one of the screens below (depending on your operating system). For the screen
on the left you would enter n,p,x (where the comma key is the key above the 7 key), For the
screen on the right, you would enter n next to “trials”, p next to “p” and x next to “x value”.

or
 Then push ENTER or highlight “Paste” and push ENTER ENTER
Reminder: Wording of a binomial random variable
rv X = the number of n randomly selected objects that are in some category of interest

Example #5.2.2: Using the Binomial Command on the TI-84

When looking at a person’s eye color, it turns out that 1% of people in the world have
green eyes ("What percentage of," 2013). Consider a group of 20 randomly selected
people.

a.) Explain why this is a binomial experiment

Solution:
1.) There are 20 people, and each person is a trial, so there are a fixed number of
trials. In this case, n = 20.
2.) If you assume that each person in the group is chosen at random the eye color of
one person doesn’t affect the eye color of the next person, thus the trials are
independent.
3.) Either a person has green eyes or they do not have green eyes, so there are only
two outcomes. In this case, the success is a person has green eyes.
4.) The probability of a person having green eyes is 0.01. This is the same for every
trial since each person has the same chance of having green eyes. p  0.01
b.) State the random variable.
Solution:
rv X = number of people with green eyes out of 20 randomly selected people
(this can also be stated as “the number of 20 r.s. people who have green eyes”)
Find the probability that …
c.) None have green eyes.
Solution:
You are looking for P(X = 0). Since this problem has the event X = 0, you use the
binompdf command on the TI-84. On the TI-84, you go to the DISTR menu, select
the binompdf, and then enter the values for n = 20, p = 0.01 and x = 0 and the press
ENTER ENTER.

Figure #5.2.1: Calculator Results for binompdf

.
Interpret: There is about an 81.8% chance that in a group of 20 randomly selected
people that none of them will have green eyes.

d.) Nine have green eyes.

Solution:
In this case you want to find the P(X = 9). Again, you will use the binompdf
command. Following the procedure above, you will have binompdf  20,.01,9 on the
TI-84.

Your answer is P  X  9  1.50 1013 . (Remember when the calculator gives you
1.50E 13 this is how it displays scientific notation.)
Interpret: The probability that out of twenty randomly selected people, nine of them
have green eyes is a very small chance.

e.) At most three have green eyes.

Solution:
At most three means that three is the highest value you will have. Find the
probability of being less than or equal to three, which is P  X  3 . On the TI-84,
you go to the DISTR menu, select the binomcdf, and then enter the values for n = 20,
p = 0.01 and x = 3 and the press ENTER ENTER.
Figure #5.2.2: Calculator Results for binomcdf

Interpret: Thus there is a really good chance that in a group of 20 randomly selected
people that at most three will have green eyes. (Note: don’t round this to one, since
one means that the event will certainly happen, when in reality there is a slight chance
that it won’t happen. It is best to write the answer out to enough decimal points so it
doesn’t round off to one.)

f.) Less than three have green eyes.

Solution:
You are looking for P( X  3) . Since the values of the random variable in this case
can only be whole numbers such as 0, 1, 2, 3, etc., that means to have less than 3 you
must have less than or equal to 2. So we are really looking for P  X  2 . Again use
binomcdf. Following the procedure above you will have binomcdf  20,.01, 2 on the
TI-84, with P  X  2  0.998996 .

Interpret: Again, there is a really good chance that at most two people in the room
will have green eyes.

g.) At least four have green eyes.

Solution:
At least four means four or more. Find the probability of X being greater than or
equal to four. This is the complement of being less than or equal to 3.
This random variable has the following possible values: 0, 1, 2, 3, 4, 5, …, 20
We want the probabilities for the following values: 4, 5, …., 20
binomcdf can give you the probabilities for the following values: 0, 1, 2, 3

0 1 2 3 4 5 . 20
binomcdf(20,0.01,3) 1-binomcdf(20,0.01,3)

P  X  4  1  P  X  3  1  binomcdf  20,0.01,3  1  0.99996

P  X  4  0.00004
 Interpret: It is very unlikely when you randomly pick 20 people to have at least 4 of
them have green eyes.
h.) Between 3 and 10, inclusive, have green eyes.
Solution:
This random variable has the following possible values: 0, 1, 2, 3, 4, 5, …, 20
We want the probabilities for the following values: 3, 4, …., 10
binomcdf can give you the probabilities for intervals of values starting at 0

binomcdf (20, 0.01,10) - binomcdf(20,0.01,2)

0 1 2 3 4 5 6 7 8 9 10 1120
binomcdf(20, 0.01, 2)

binomcdf(20, 0.01, 10)

P  3  X  10  binomcdf  20,0.01,10  binomcdf  20,0.01, 2  0.00100

Interpret: If you randomly pick 20 people, there is about 1 chance out of 1000 that
between 3 and 10, inclusive, have green eyes.

Example #5.2.4: Calculating Binomial Probabilities

According to the Center for Disease Control (CDC), about 1 in 88 children in the U.S.
have been diagnosed with autism ("CDC-data and statistics,” 2013). Suppose you
consider a group of 10 randomly selected children.

a.) State the random variable.

Solution:
rv X = number of children with autism out of 10 randomly selected children.

b.) Explain why this is a binomial experiment

Solution:
1.) There are 10 children, and each child is a trial, so there are a fixed number of
trials. In this case, n = 10.
2.) If you assume that each child in the group is chosen at random, then whether a
child has autism does not affect the chance that the next child has autism. Thus
the trials are independent.
3.) Either a child has autism or they do not have autism, so there are two outcomes.
In this case, the success is a child has autism.
4.) The probability of a child having autism is 1/88. This is the same for every trial
1
since each child has the same chance of having autism so p  .
88
So this experiment meets all 4 conditions of a binomial experiment.
Find the probability that
c.) None have autism.
Solution:
P  X  0  binompdf 10,1  88,0  0.892

Interpret: If we randomly select 10 children, there is about an 89.2% chance that

none of them have autism.

d.) Seven have autism.

Solution:
P  X  7   binompdf 10,1  88,7   2.84 1012
P  X  7   0.00000000000284  0.000
Notice, the answer is given as 0.000. Don’t write 0, since 0 means that the event is
impossible to happen. The event of exactly seven is very improbable, but not
impossible.

Interpret: If we randomly select 10 children, there is almost no chance that exactly 7

of them have autism.

e.) At least five have autism.

Solution:
To use the calculator you need to use the complement.
P  X  5  1  P  X  5   1  P  X  4 
P  X  5  1  binomcdf 10,1  88, 4
P  X  5  1  0.9999999  0.000
Notice, the answer is given as 0.000. Don’t write 0, since 0 means that the event is
impossible to happen. The event of five or more is improbable, but not impossible.
Interpret: If we randomly select 10 children, there is almost no chance that at least 5
of them have autism.

f.) Suppose five children out of ten have autism. Is this unusual? What does that tell
you?
Solution:
To determine if x = 5 is an unusual value of X, we need to compute two probabilities
and compare each of them to 0.05: P  X  5 and P  X  5
From part e, the probability of five or more children in a group of ten having autism is
much less than 5%, 5 out of 10 with autism is an unusually high number if the
probability of autism really is 1/88. If this does happen, then one may think that the
proportion of children diagnosed with autism is actually more than 1/88.
g.) At most two have autism.
Solution:
P  X  2  binomcdf 10,1  88, 2  0.9998

Interpret: If we randomly select 10 children, there is about a 99.98% chance (almost

certain) that at most two of them have autism.

h.) Between 1 and 5 have autism.

Solution1
Notice that this does not say inclusive.
This random variable has the following possible values: 0, 1, 2, 3, 4, 5, …, 10
The only numbers in this list that are between 1 and 5 are 2, 3 and 4
binomcdf can give you the probabilities for intervals of values starting at 0

binomcdf (10, 1/88, 4) - binomcdf(10, 1/88, 1)

0 1 2 3 4 5 6 . 10

binomcdf(10,1/88,1)

binomcdf (10,1/88,4)

P 1  X  5  P  2  X  4  P  X  4  P  X  1
P 1  X  5  binomcdf 10,1  88, 4  binomcdf 10,1  88,1
Interpret: If we randomly select 10 children, there is about a 0.55% chance that
between 1 and 5 of them have autism.
Section 5.2: Homework
1.) Suppose a random variable, X, arises from a binomial experiment. If n = 14, and p =
0.13, find the following probabilities using binompdf or binomcdf.
a.) P  X  5
b.) P  X  8
c.) P  X  12
d.) P  X  4
e.) P  X  8
f.) P ( X  13)

2.) Suppose a random variable, X, arises from a binomial experiment. If n = 22, and p =
0.85, find the following probabilities using using binompdf or binomcdf.
a.) P  X  18
b.) P  X  5
c.) P  X  20
d.) P  X  3
e.) P  X  7 
f.) P( X  5)

3.) Suppose a random variable, X, arises from a binomial experiment. If n = 10, and p =
0.70, find the following probabilities using using binompdf or binomcdf.
a.) P  X  2
b.) P  X  8
c.) P  X  7 
d.) P  X  3
e.) P( X  6)
f.) P( X  5)
g.) P  5  X  8

4.) Suppose a random variable, X, arises from a binomial experiment. If n = 6, and p = 0.30,
find the following probabilities using the using binompdf or binomcdf.
a.) P  X  1
b.) P  X  5
c.) P  X  3
d.) P  X  3
e.) P( X  4)
f.) P( X  5)
g.) P 1  X  5
5.) Suppose a random variable, X, arises from a binomial experiment. If n = 17, and p =
0.63, find the following probabilities using using binompdf or binomcdf.
a.) P  X  8
b.) P  X  15
c.) P  X  14
d.) P  X  12
e.) P( X  9)
f.) P( X  8)

6.) Suppose a random variable, x, arises from a binomial experiment. If n = 23, and p =
0.22, find the following probabilities using using binompdf or binomcdf.
a.) P  X  21
b.) P  X  6
c.) P  X  12
d.) P  X  14
e.) P ( X  16)
f.) P ( X  10) .

7.) Approximately 10% of all people are left-handed ("11 little-known facts," 2013).
Consider fifteen randomly selected people.
a.) State the random variable and list the given numbers with correct symbols.
b.) plain why this is a binomial experiment
Find the probability that
c.) None are left-handed.
d.) Seven are left-handed.
e.) At least two are left-handed.
f.) At most three are left-handed.
g.) At least seven are left-handed.
h.) Seven of the last 15 U.S. Presidents were left-handed. Is this unusual? What does
that tell you?

8.) According to an article in the American Heart Association’s publication Circulation, 24%
of patients who had been hospitalized for an acute myocardial infarction did not fill their
cardiac medication by the seventh day of being discharged (Ho, Bryson & Rumsfeld,
2009). Suppose there are twelve people who have been hospitalized for an acute
myocardial infarction.
a.) State the random variable and list the given numbers with correct symbols.
b.) Explain why this is a binomial experiment
Find the probability that
c.) All filled their cardiac medication.
d.) Seven did not fill their cardiac medication.
e.) None filled their cardiac medication.
f.) At most two did not fill their cardiac medication.
g.) At least ten did not fill their cardiac medication.
h.) Suppose of the next twelve patients discharged, ten did not fill their cardiac
medication, would this be unusual? What does this tell you
9.) Eyeglassomatic manufactures eyeglasses for different retailers. In March 2010, they
tested to see how many defective lenses they made, and there were 16.9% defective
lenses due to scratches. Suppose Eyeglassomatic examined twenty pairs of eyeglasses.
a.) State the random variable and list the given numbers with correct symbols.
b.) Explain why this is a binomial experiment
Find the probability that
c.) None are scratched.
d.) All are scratched.
e.) At least three are scratched.
f.) At most five are scratched.
g.) At least ten are scratched.
h.) Is it unusual for ten lenses to be scratched? If it turns out that ten lenses out of twenty
are scratched, what might that tell you about the manufacturing process?

10.) The proportion of brown M&M’s in a milk chocolate packet is approximately 14%
(Madison, 2013). Suppose a package of M&M’s typically contains 52 M&M’s.
a.) State the random variable and list the given numbers with correct symbols.
b.) Explain why this is a binomial experiment
Find the probability that
c.) Six M&M’s are brown.
d.) Twenty-five M&M’s are brown.
e.) All of the M&M’s are brown.
f.) Would it be unusual for a package to have only brown M&M’s? If this were to
happen, what would you think is the reason?