Chapter 68

The binomial, hypergeometric, and

negative binomial random variables
Questions answered in this chapter:

• What is a binomial random variable?

• How do I use the BINOM.DIST and BINOM.DIST.RANGE functions to compute binomial

probabilities?

• If equal numbers of people prefer Coke to Pepsi and Pepsi to Coke, and I ask 100 people
whether they prefer Coke to Pepsi, what is the probability that exactly 60 people prefer Coke
to Pepsi and the probability that between 40 and 60 people prefer Coke to Pepsi?

• Of all the elevator rails my company produces, 3 percent are considered defective. We are
about to ship a batch of 10,000 elevator rails to a customer. To determine whether the batch is
acceptable, the customer will randomly choose a sample of 100 rails and check whether each
sampled rail is defective. If two or fewer sampled rails are defective, the customer will accept
the batch. How can I determine the probability that the batch will be accepted?

• Airlines do not like flights with empty seats. Suppose that, on average, 95 percent of all ticket
purchasers show up for a flight. If the airline sells 105 tickets for a 100-seat flight, what is the
probability that the flight will be overbooked?

• The local Village Deli knows that 1,000 customers come for lunch each day. On average, 20
percent order the specialty vegetarian sandwich. These sandwiches are made in advance.
How many should the deli make if they want to have a 5 percent chance of running out of
vegetarian sandwiches?

• What is the hypergeometric random variable?

• What is the negative binomial random variable?

Answers to this chapter’s questions

What is a binomial random variable?

A binomial random variable is a discrete random variable used to calculate probabilities in a situation
in which all three of the following apply:

© 2016 Microsoft Corporation. All Rights Reserved. Page 1 3/3/2017

 • n independent trials occur.

• Each trial results in one of two outcomes: success or failure.

• In each trial, the probability of success (p) remains constant.

In such a situation, the binomial random variable can be used to calculate probabilities related to
the number of successes in a given number of trials. I let x be the random variable denoting the
number of successes occurring in n independent trials, when the probability of success on each trial
is p. Here are some examples in which the binomial random variable is relevant.

Coke or Pepsi Assume that equal numbers of people prefer Coke to Pepsi and Pepsi to Coke.
You ask 100 people whether they prefer Coke to Pepsi. You’re interested in the probability that
exactly 60 people prefer Coke to Pepsi and the probability that from 40 through 60 people prefer
Coke to Pepsi. In this situation, you have a binomial random variable defined by the following:

• Trial: Survey individuals

• Success: Prefer Coke

• p equals 0.50

• n equals 100

Let x equal the number of people sampled who prefer Coke. You want to determine the probability
that x=60 and also the probability that 40 ≤ x ≤ 60.

Elevator rails Of all the elevator rails you produce, 3 percent are considered defective. You are
about to ship a batch of 10,000 elevator rails to a customer. To determine whether the batch is
acceptable, the customer will randomly choose a sample of 100 rails and check whether each
sampled rail is defective. If two or fewer sampled rails are defective, the customer will accept the
batch. You want to determine the probability that the batch will be accepted.

You have a binomial random variable defined by the following:

• Trial: Look at a sampled rail

• Success: Rail is defective

• p equals 0.03

• n equals 100

Let x equal the number of defective rails in the sample. You want to find the probability that x ≤ 2.

Airline overbooking Airlines don’t like flights with empty seats. Suppose that, on average, 95
percent of all ticket purchasers show up for a flight. If the airline sells 105 tickets for a 100-seat flight,
what is the probability that the flight will be overbooked?

© 2016 Microsoft Corporation. All Rights Reserved. Page 2 3/3/2017

 You have a binomial random variable defined by the following:

• Trial: Individual ticket holders

• Success: Ticket holder shows up

• p equals 0.95

• n equals 105

Let x equal the number of ticket holders who show up. Then you want to find the probability that x
≥ 101.

How do I use the BINOM.DIST and BINOM.DIST.RANGE functions to compute binomial

probabilities?
Microsoft Excel 2016 includes the BINOM.DIST and BINOM.DIST.RANGE functions, which you can
use to compute binomial probabilities. If you want to compute the probability of x or fewer successes,
for a binomial random variable having n trials with probability of success p, simply enter
BINOM.DIST(x,n, p,1). If you want to compute the probability of exactly x successes for a binomial
random variable having n trials with probability of success of p, enter BINOM.DIST(x,n,p,0). Entering
1 as the last argument of BINOM.DIST yields a “cumulative” probability; entering 0 yields the
“probability mass function” for any particular value. (Note that a last argument of True can be used
instead of a 1, and a last argument of False can be used instead of a 0.)

The function BINOM.DIST.RANGE(n,p,s1,s2) gives the probability of obtaining between s1 and s2

successes (inclusive) in n independent trials with probability of success p on each trial.

Here are a few examples of using the BINOM.DIST function to calculate probabilities of interest.
You’ll find the data and analysis in the file Binomialexamples.xlsx, which is shown in Figure 68-1.

F68xx01
FIGURE 68-1 Using the binomial random variable.

F68xx01: This figure shows examples of calculations involving the binomial random variable.

If equal numbers of people prefer Coke to Pepsi and Pepsi to Coke, and I ask 100 people whether
they prefer Coke to Pepsi, what is the probability that exactly 60 people prefer Coke to Pepsi and the

© 2016 Microsoft Corporation. All Rights Reserved. Page 3 3/3/2017

probability that between 40 and 60 people prefer Coke to Pepsi?
You have n=100 and p=0.5. You seek the probability that x=60 and the probability that 40 ≤ x ≤ 60,
where x equals the number of people who prefer Coke to Pepsi. First, you find the probability that
x=60 by entering in cell C4 the formula =BINOM.DIST(60,100,0.5,0). Excel returns the value 0.011.

To use the BINOM.DIST function to compute the probability that 40 ≤ x ≤ 60, you can note that the
probability that 40 ≤ x ≤ 60 equals the probability that x ≤ 60 minus the probability that x ≤ 39. Thus,
you can obtain the probability that from 40 through 60 people prefer Coke by entering in cell C5 the
formula =BINOM.DIST(60,100,0.5,1)–BINOM.DIST(39,100,0.5,1). Excel returns the value 0.9648. So,
if Coke and Pepsi are equally preferred, it is very unlikely that in a sample of 100 people, Coke or
Pepsi would be more than 10 percent ahead. If a sample of 100 people shows Coke or Pepsi to be
more than 10 percent ahead, you should probably doubt that Coke and Pepsi are equally preferred.
Alternatively, in cell E5 I used the formula =BINOM.DIST.RANGE(100,0.5,40,60) to compute the
same probability.

Of all the elevator rails my company produces, 3 percent are considered defective. We are about to
ship a batch of 10,000 elevator rails to a customer. To determine whether the batch is acceptable, the
customer will randomly choose a sample of 100 rails and check whether each sampled rail is
defective. If two or fewer sampled rails are defective, the customer will accept the batch. How can I
determine the probability that the batch will be accepted?
If you let x equal the number of defective rails in a batch, you have a binomial random variable with
n=100 and p=0.03. You seek the probability that x ≤ 2. Simply enter in cell C8 the formula
=BINOM.DIST(2,100,0.03,1). Excel returns the value 0.42 Thus, the batch will be accepted 42
percent of the time. Alternatively, in cell E7 I used the formula =BINOM.DIST.RANGE(100,0.03,0,2)
to compute the same probability.

Really, your chance of success is not exactly 3 percent on each trial. For example, if the first 10
rails are defective, the chance the next rail is defective has dropped to 290/9,990; if the first 10 rails
are not defective, the chance the next rail is defective is 300/9,990. Therefore, the probability of
success on the eleventh trial is not independent of the probability of success on one of the first 10
trials. Despite this fact, the binomial random variable can be used as an approximation when a
sample is drawn and the sample size is less than 10 percent of the total population. Here, the
population equals 10,000, and the sample size is 100. Exact probabilities involving sampling from a
finite population can be calculated with the hypergeometric random variable, which I’ll discuss later in
this chapter.

Airlines do not like flights with empty seats. Suppose that, on average, 95 percent of all ticket
purchasers show up for a flight. If the airline sells 105 tickets for a 100-seat flight, what is the
probability that the flight will be overbooked?
Let x equal the number of ticket holders who show up for the flight. You have n=105 and p=0.95. You
seek the probability that x≥101. Note that the probability that x≤101 equals 1 minus the probability
that x≤100. So, to compute the probability that the flight is overbooked, you enter in cell C10 the
© 2016 Microsoft Corporation. All Rights Reserved. Page 4 3/3/2017
formula =1–BINOM.DIST(100,105,0.95,1). Excel yields 0.392, which means there is a 39.2 percent
chance that the flight will be overbooked. Alternatively, in cell E10 I computed the same probability by
using the following formula:

=BINOM.DIST.RANGE(105,0.95,101,105)

The local Village Deli knows that 1,000 customers come for lunch each day. On average, 20 percent
order the specialty vegetarian sandwich. These sandwiches are made in advance. How many should
the deli make if they want to have a 5 percent chance of running out of vegetarian sandwiches?
In Excel 2016, the function BINOM.INV, with the syntax BINOM.INV(trials, probability of success,
alpha), determines the smallest number x, for which the probability of less than or equal to x
successes is at least alpha. In earlier versions of Excel, the function CRITBINOM(trials, probability of
success, alpha) yielded the same results as BINOM.INV. In this example, trials equals 1,000,
probability of success equals 0.2, and alpha equals 0.95. As shown in Figure 68-2, if the deli orders
221 sandwiches, the probability that demand will be less than or equal to 221 is at least 0.95. Also,
the probability that 220 or fewer sandwiches will be demanded is less than 0.95.

F68xx02
FIGURE 68-2 An example of the BINOM.INV function.

F68xx02: This figure shows how the BINOM.INV function can be used to determine how to meet 95 percent of the
demand.

What is the hypergeometric random variable?

The hypergeometric random variable governs a situation such as the following:

• A bowl contains N balls.

• Each ball is one of two types (called success or failure).

• There are s successes in the bowl.

• A sample of size n is drawn from the bowl.

Let’s look at an example in the file Hypergeom.dist.xlsx, which is shown in Figure 68-3. The Excel
2016 formula HYPERGEOM.DIST(x,n,s,N,0) gives the probability of x successes if n balls are drawn
from a bowl containing N balls, of which s are marked as success. The Excel 2016 formula
HYPERGEOM.DIST(x,n,s,N,1) gives the probability of less than or equal to x successes if n balls are

© 2016 Microsoft Corporation. All Rights Reserved. Page 5 3/3/2017

drawn from a bowl containing N balls, of which s are marked as success. (As with the BINOM.DIST
function, True can be used to replace 1 and False to replace 0.)

For example, suppose that 40 of the Fortune 500 companies have a woman CEO. The 500 CEOs
are analogous to the balls in the bowl (N=500) and the 40 women are representative of the s
successes in the bowl. Then, copying from D8 to D9:D18 the formula
=HYPERGEOM.DIST(C8,Sample_size,Population_women,Population_size,FALSE) gives the
probability that a sample of 10 Fortune 500 companies will have 0, 1, 2,…, 10 women CEOs. Here
Sample_size equals 10, Population_women equals 40, and Population_size equals 500. You can
substitute FALSE for 0 in the formula.

Finding a woman CEO is a success. In the sample of 10, for example, there’s a probability of
0.431 that no women CEOs will be in the sample. By the way, you could have approximated this
probability with the formula BINOMDIST(0,10,0.08,0), yielding 0.434, which is very close to the true
probability of 0.431. In cell F10, I computed the probability that at most 2 of the 10 people in the
sample would be women with the formula
=HYPGEOM.DIST(2,Sample_Size,Population_women,Population_size,TRUE). Thus there is a 96.2
percent chance that at most two people in the sample will be women. Of course, I also could have
obtained this answer by adding together the highlighted cells (D8:D10).

F68xx03
FIGURE 68-3 Using the hypergeometric random variable.

F68xx03: This figure illustrates the use of the hypergeometric random variable to compute probabilities when
sampling without replacement.

What is the negative binomial random variable?

The negative binomial random variable applies to the same situation as the binomial random variable,
but the negative binomial random variable gives the probability of f failures occurring before the sth
success. Thus =NEGBINOM.DIST(f,s,p,0) gives the probability that exactly f failures will occur before
the sth success when the probability of success is p for each trial, and =NEGBINOM.DIST(f,s,p,1)
gives the probability that at most f failures will occur before the sth success when the probability of
success is p for each trial. For example, consider a baseball team that wins 40 percent of their games
(see the file Negbinom.dist.xlsx and Figure 68-4). Copying from E9 to E34 the formula
=NEGBINOM.DIST(D9,2,.4,False) gives the probability of 0, 1, 2,…, 25 losses occurring before the
© 2016 Microsoft Corporation. All Rights Reserved. Page 6 3/3/2017
 second win. Note here that success equals a game won. For example, there is a 19.2 percent chance
the team will lose exactly one game before winning two games. In cell G10, I used the formula
=NEGBINOM.DIST(3,2,0.4,TRUE) to compute the chance that at most three losses will occur before
the team wins two games (0.663). Of course, I could have obtained this answer by simply adding up
the shaded cells (E9:E12).

F68xx04
FIGURE 68-4 Using the negative binomial random variable.

F68xx04: This figure shows calculations involving the negative binomial random variable.

Problems

1. Suppose that, on average, 4 percent of all CD drives received by a computer company are
defective. The company has adopted the following policy: Sample 50 CD drives in each
shipment, and accept the shipment if none are defective. Using this information, determine the
following:

• What fraction of shipments will be accepted?

• If the policy changes so that a shipment is accepted if only one CD drive in the sample is
defective, what fraction of shipments will be accepted?

• What is the probability that a sample size of 50 will contain at least 10 defective CD
drives?

2. Use the airline overbooking data to do the following:

• Determine how the probability of overbooking varies as the number of tickets sold varies
from 100 through 115. Hint: Use a one-way data table.

• Show how the probability of overbooking varies as the number of tickets sold varies from
100 through 115 and the probability that a ticket holder shows up varies from 80 percent
© 2016 Microsoft Corporation. All Rights Reserved. Page 7 3/3/2017
 through 95 percent. Hint: Use a two-way data table.

3. Suppose that during each year, a given mutual fund has a 50 percent chance of beating the
Standard & Poor’s 500 Stock Index (S&P Index). In a group of 100 mutual funds, what is the
probability that at least 10 funds will beat the S&P Index during at least 8 out of 10 years?

4. Professional basketball player Steve Nash is a 90 percent foul shooter. Answer the following
questions:

• If he shoots 100 free throws, what is the probability that he will miss more than 15 shots?

• How good a foul shooter would Steve Nash be if he had only a 5 percent chance of
making fewer than 90 free throws out of 100 attempts? Hint: Use Goal Seek in the What-
If Analysis options.

5. When tested for extra sensory perception (ESP), participants are asked to identify the shape
of a card from a 25-card deck. The deck consists of five cards, of each of five shapes. If a
person identifies 12 cards correctly, what would you conclude?

6. Suppose that in a group of 100 people, 20 have the flu and 80 do not. If you randomly select
30 people, what is the chance that at least 10 people have the flu?

7. A student is selling magazines for a school fundraiser. There is a 20 percent chance that a
given house will buy a magazine. He needs to sell five magazines. Determine the probability
that he will need to visit 5, 6, 7,…, 100 houses to sell five magazines.

8. Use the BINOM.DIST function to verify that the BINOM.INV function yields the correct answer
to my Village Deli example.

9. In the seventeenth century, French mathematicians Pierre de Fermat and Blaise Pascal were
inspired to formulate the modern probability theory after trying to solve the problem of points.
Here is a simple example: Pascal and Fermat take turns tossing coins. Fermat wins a point if a
head is tossed, and Pascal wins a point if a tail is tossed. If Pascal is ahead 8-7 and the first
player with 10 points wins, what is the chance that Pascal will win?

10. Suppose that each time the Houston Astros play the New York Yankees, the Astros have a 35
percent chance of winning the game. If the Astros play the Yankees 10 times, what is the
chance the Astros win at least half the games?

11. I make 55 percent of my free throws. If I shoot 400 free throws, what is the chance that I make
between 200 and 300 free throws inclusive?

12. Suppose 10 percent of all staplers are defective. If 60 staplers are sold, what is the chance
that at least 10 staplers are defective?

13. A factory has five assembly lines. Each assembly line is down (not working) p percent of the
time. What must p equal so that there is a 95 percent chance that at least one assembly line is

© 2016 Microsoft Corporation. All Rights Reserved. Page 8 3/3/2017

 working?

© 2016 Microsoft Corporation. All Rights Reserved. Page 9 3/3/2017