5 Discrete Probability

Distributions

Copyright © Cengage Learning. All rights reserved.

5.1 Discrete Random Variables and
Their Probability Distributions

Copyright © Cengage Learning. All rights reserved.

Random Variables

3
Random Variables (1 of 3)
A quantitative variable x will vary or change depending on
the particular outcome of the experiment being measured.
For example, suppose you toss a die and measure x, the
number observed on the upper face.

The variable x can take on any of six values—1, 2, 3, 4, 5,

6—depending on the random outcome of the experiment.
For this reason, we refer to the variable x as a random
variable.

4
Random Variables (2 of 3)

DEFINITION
A variable x is a random variable if the value that it
assumes, corresponding to the outcome of an experiment,
is a chance or random event.

As in earlier chapter, quantitative random variables are

classified as either discrete or continuous, according to the
values that x can assume.

5
Random Variables (3 of 3)
It is important to distinguish between discrete and
continuous random variables because different techniques
are used to describe their distributions.

6
Probability Distributions

7
Probability Distributions (1 of 3)
We defined probability as the limiting value of the relative
frequency as the experiment is repeated over and over
again.

Now we define the probability distribution for a random

variable x as the relative frequency distribution constructed
for the entire population of measurements.

8
Probability Distributions (2 of 3)

DEFINITION
The probability distribution for a discrete random
variable is a formula, table, or graph that gives all the
possible values of x, and the probability p(x) associated
with each value.

The values of x are mutually exclusive events; summing p (x)

over all values of x is the same as adding the probabilities of
all simple events and therefore equals 1.

9
Probability Distributions (3 of 3)
Requirements for a Discrete Probability Distribution

• 0 ≤ p(x) ≤ 1

• Σp(x) = 1

10
Example 5.1
Toss two fair coins and let x equal the number of heads
observed. Find the probability distribution for x.

11
Example 5.1 – Solution (1 of 6)
The simple events and their probabilities are listed in table.

Simple
Event Coin 1 Coin 2 P(Ei) x
E1 H H 1∕4 2
E2 H T 1∕4 1
E3 T H 1∕4 1
E4 T T 1∕4 0

Simple Events and Probabilities in Tossing Two Coins

Table 5.1

12
Example 5.1 – Solution (2 of 6)
Since E1 = HH results in two heads, this simple event
results in the value x = 2. Similarly, the value x = 1 is
assigned to E2, and so on.

For each value of x, you can calculate p(x) by adding the

probabilities of the simple events in that event.

13
Example 5.1 – Solution (3 of 6)
For example, when x = 0, simple event E4 occurs, so that

and when x = 1,

14
Example 5.1 – Solution (4 of 6)
The values of x and their respective probabilities, p(x), are
listed in table. Notice that the probabilities add to 1.

Simple
x Events in x p(x)
0 E4 1∕4
1 E2,E3 1∕2
2 E1 1∕4
Σp(x) = 1
Probability Distribution for x (x = Number of Heads)
Table 5.2

15
Example 5.1 – Solution (5 of 6)
The probability distribution in Table 5.2 can be graphed in
several ways.

Figure 5.1

16
Example 5.1 – Solution (6 of 6)
The three values of the random variable x are located on
the horizontal axis, and the probabilities p(x) are located on
the vertical axis. Consider Figure 5.1(b), which looks like the
relative frequency histogram.

Since the width of each bar is 1, the area under the bar is
the probability of observing the particular value of x and the
total area under the bars equals 1.

17
The Mean and Standard Deviation for
a Discrete Random Variable

18
The Mean and Standard Deviation for a Discrete Random Variable (1 of 6)

The probability distribution for a discrete random variable

looks very similar to the relative frequency distribution.

The difference is that the relative frequency distribution

describes a sample of n measurements, while the
probability distribution is constructed as a model for the
entire population of measurements.

19
The Mean and Standard Deviation for a Discrete Random Variable (2 of 6)

Just as the mean and the standard deviation s measured

the center and spread of the sample data, you can calculate
similar measures to describe the center and spread of the
population.

The population mean, which measures the average value of

x in the population, is also called the expected value of the
random variable x and is written as E(x). It is the value that
you would expect to observe on average if the experiment is
repeated over and over again.

20
The Mean and Standard Deviation for a Discrete Random Variable (3 of 6)

Toss those two fair coins again, and let x be the number of
heads observed. We constructed this probability distribution
for x:

x 0 1 2
p(x) 1∕4 1∕2 1∕4

21
The Mean and Standard Deviation for a Discrete Random Variable (4 of 6)

DEFINITION
Let x be a discrete random variable with probability
distribution p(x). The mean or expected value of x is
given as

μ = E(x) = Σxp(x)

summing over all the values of x.

22
The Mean and Standard Deviation for a Discrete Random Variable (5 of 6)

We could use a similar argument to justify the formulas for

the population variance and the population standard
deviation σ.

These numerical measures describe the spread or

variability of the random variable using the “average” or
“expected value” of the squared deviations of the
x-values from their mean μ.

23
The Mean and Standard Deviation for a Discrete Random Variable (6 of 6)

DEFINITION
Let x be a discrete random variable with probability
distribution p(x) and mean μ. The variance of x is

summing over all the values of x.

DEFINITION
The standard deviation σ of a random variable x is
equal to the positive square root of its variance.

24
Example 5.2 (1 of 2)
A “big-box” store sells a particular laptop, but has only four
in stock. The manager wonders what today’s demand for
this particular laptop will be.

She learns from the marketing department that the

probability distribution for x, the daily demand for the laptop,
is as shown in the table.
x 0 1 2 3 4 5
p(x) .10 .40 .20 .15 .10 .05

25
Example 5.2 (2 of 2)
Find the mean, variance, and standard deviation of x. Is it
likely that five or more customers will want to buy the laptop
today?

26
Example 5.2 – Solution (1 of 4)
Table shows the values of x and p(x), along with the
individual terms used in the formulas for μ and

Table 5.3

27
Example 5.2 – Solution (2 of 4)
The sum of the values in the third column is

μ = Σxp(x) = (0)(.10)+(1)(.40)+ ... +(5)(.05) = 1.90

while the sum of the values in the fifth column is

28
Example 5.2 – Solution (3 of 4)
The graph of the probability distribution is shown in figure.

Figure 5.2

29
Example 5.2 – Solution (4 of 4)
Since the distribution is approximately mound-shaped,
approximately 95% of all measurements should lie within two
standard deviations of the mean—that is,

μ ± 2σ ⇒1.90 ± 2(1.34) or −.78 to 4.58

Since x = 5 lies outside this interval, you can say it is unlikely

that five or more customers will want to buy the laptop today.
In fact, P(x ≥ 5) is exactly .05, or 1 time in 20.

30
Example 5.4
An insurance company needs to know how much to charge
for a $100,000 policy insuring an event against cancellation
due to inclement weather.

The probability of inclement weather during the time of the

event is assessed as 2 in 100. Once they find C, the cost of
the policy to break even, they can add administrative costs
and profit to this amount.

Find the value of C so that their expected gain is zero.

31
Example 5.4 – Solution (1 of 4)
Define:
x = insurance company’s gain
C = premium charged for the policy

Next, determine the possible values for x and the

associated probabilities p(x).

If the event is not cancelled due to inclement weather, the

insurance company will gain an amount equal to C with
probability 98 ∕ 100.

32
Example 5.4 – Solution (2 of 4)
If the event is cancelled because of inclement weather, the
insurance company will receive $C, but will pay out
$100,000, so that the gain is (−100,000 + C) with probability
2 ∕ 100.

The distribution for the gain is given in the next table.

x = Gain p(x)
C 98 ∕ 100
−(−100,000 + C) 2 ∕ 100

33
Example 5.4 – Solution (3 of 4)
Since the company wants to set the premium C so that in
the long run, the average gain will be zero, set the expected
value of x equal to zero and solve for C.
E(x) = Σxp(x)

and C = $2,000.

34
Example 5.4 – Solution (4 of 4)
If the insurance company charged a premium of $2,000, the
average gain for a large number of similar policies would
equal zero.

The actual premium would equal $2,000 plus administrative

costs and profit.

35
5.2 The Binomial Probability
Distribution

Copyright © Cengage Learning. All rights reserved.

The Binomial Probability Distribution (1 of 9)

DEFINITION
A binomial experiment is one that has these five
characteristics:
1. The experiment consists of n identical trials.
2. Each trial results in one of two outcomes. For lack of a
better name, one outcome is called a success, S, and
the other a failure, F.
3. The probability of success on a single trial is equal to p
and remains the same from trial to trial. The probability
of failure is equal to (1 − p) = q.

37
The Binomial Probability Distribution (2 of 9)

DEFINITION
4. The trials are independent.
5. We are interested in the binomial random variable x,
the number of successes in n trials, for x = 0,1,2, ..., n.

38
Example 5.5
Suppose there are approximately 1,000,000 adults in a
county and an unknown proportion p favors term limits for
politicians. A sample of 1000 adults will be chosen in such a
way that every one of the 1,000,000 adults has an equal
chance of being selected, and each adult is asked whether
he or she favors term limits.

Is this a binomial experiment?

39
Example 5.5 – Solution (1 of 3)
Does the experiment have the five binomial characteristics?

1. A “trial” is the choice of a single adult from the 1,000,000

adults in the county. This sample consists of n = 1000
identical trials.
2. Since each adult will either favor or not favor term limits,
there are two outcomes that represent the “successes”
and “failures” in the binomial experiment.

40
Example 5.5 – Solution (2 of 3)
3. The probability of success, p, is the probability that an
adult favors term limits. Does this probability remain the
same for each adult in the sample? For all practical
purposes, the answer is yes. For example, if 500,000
adults in the population favor term limits, then the
probability of a “success” when the first adult is chosen is
500,000 ∕ 1,000,000 = 1 ∕ 2. When the second adult is
chosen, the probability p changes slightly, depending on
the first choice. That is, there will be either 499,999 or
500,000 successes left among the 999,999 adults. In
either case, p is still approximately equal to 1 ∕ 2.

41
Example 5.5 – Solution (3 of 3)
4. The independence of the trials is guaranteed because of
the large group of adults from which the sample is
chosen. The probability of an adult favoring term limits
does not change depending on the responses of
previously chosen people.
5. The random variable x is the number of adults in the
sample who favor term limits.

Because the survey satisfies the five characteristics

reasonably well, for all practical purposes it can be viewed
as a binomial experiment.

42
The Binomial Probability Distribution (3 of 9)

Rule of Thumb
If the sample size is large relative to the population size—in
particular, if n ∕ N ≥ .05—then the resulting experiment is not
binomial.

The Binomial Probability Distribution

A binomial experiment consists of n identical trials with
probability of success p on each trial. The probability of k
successes in n trials is

for values of k = 0, 1, 2, ..., n.

43
The Binomial Probability Distribution (4 of 9)

The symbol equals

44
The Binomial Probability Distribution (5 of 9)

Mean and Standard Deviation for the Binomial Random

Variable
The random variable x, the number of successes in n trials,
has a probability distribution with this center and spread:

45
Example 5.7
Find P(x = 2) for a binomial random variable with n = 10 and
p = .1.

Solution:
P(x = 2) is the probability of observing 2 successes and 8
failures in a sequence of 10 trials. You might observe the 2
successes first, followed by 8 consecutive failures:

S, S, F, F, F, F, F, F, F, F

46
Example 5.7 – Solution
Since p is the probability of success and q is the probability
of failure, this particular sequence has probability

However, many other sequences also result in x = 2

successes. The binomial formula uses to count the
number of sequences and gives the exact probability when
you use it with k = 2:

47
The Binomial Probability Distribution (6 of 9)

Cumulative binomial probabilities differ from the individual

binomial probabilities that you calculated with the binomial
formula.

Once you find the column of probabilities for the correct

values of n and p in Table 1, the row marked k gives the
sum of all the binomial probabilities from x = 0 to x = k.

48
The Binomial Probability Distribution (7 of 9)

Table shows part of Table 1 for n = 5 and p = .6.

Table 5.4

If you look in the row marked k = 3, you will find

P(x ≤ 3) = p(0) + p(1) + p(2) + p(3) = .663

49
The Binomial Probability Distribution (8 of 9)

How to Use Table 1 to Calculate Binomial Probabilities

1. Find the necessary values of n and p. Isolate the
appropriate column in Table 1.
2. Table 1 gives P(x ≤ k) in the row marked k. Rewrite the
probability you need so that it is in this form.

• List the values of x in your event.

50
The Binomial Probability Distribution (9 of 9)

• From the list, write the event as either the difference of

two probabilities:
P(x ≤ a) − P(x ≤ b) for a > b
or the complement of the event:
1 − P(x ≤ a)
or just the event itself:
P(x ≤ a) or P(x < a) = P(x ≤ a − 1)

51
Example 5.11
A regimen consisting of a daily dose of vitamin C was tested
to see if it might be effective in preventing the common cold.
Ten people followed the prescribed regimen for a year, and
eight survived the winter without a cold.

Suppose that, without vitamin C, the probability of surviving

the winter without a cold is .5. What is the probability of
observing eight or more survivors, given that the regimen is
ineffective in increasing resistance to colds?

52
Example 5.11 – Solution (1 of 5)
If you assume that the vitamin C regimen is ineffective, then
the probability p of surviving the winter without a cold is .5.

The probability distribution for x, the number of survivors, is

53
Example 5.11 – Solution (2 of 5)
1. The binomial formula:

2. The cumulative binomial tables: Find the column

corresponding to p = .5 in the table for n = 10:
P(8 or more) = P(x ≥ 8) = 1 − P(x ≤ 7)
= 1 − .945 = .055

54
Example 5.11 – Solution (3 of 5)
3. Output from MINITAB, MS Excel, or the TI-83 or TI-84
Plus: The outputs shown in figures give the cumulative
distribution function (cdf), which are the same
probabilities you found in the cumulative binomial tables.

Figure 5.5(a)
Figure 5.5(b)

55
Example 5.11 – Solution (4 of 5)
The probability density
function (pdf) gives the
individual binomial
probabilities, which you
found using the binomial
formula. The output from
the TI-84 Plus calculator
in Figure 5.5(c) shows the
binomial cdf in list L2 and
the pdf in list L3. TI-84 Plus screen captures for Example 5.11
Figure 5.5(c)

56
Example 5.11 – Solution (5 of 5)
Using the cumulative distribution function, calculate
P(x ≥ 8) = 1 − P(x ≤ 7)
= 1 − .94531 = .05469

Or, using the probability density function, calculate

P(x ≥ 8) = p(8) + p(9) + p(10)
= .043945 + .009766 + .000977
= .05469

57
Example 5.12
Would you rather take a multiple-choice or a full recall test?
If you have absolutely no knowledge of the material, you will
score zero on a full recall test. However, if you are given five
choices for each question, you have at least one chance in
five of guessing correctly!

If a multiple-choice exam contains 100 questions, each with

five possible answers, what is the expected score for a
student who is guessing on each question?

Within what limits will the “no-knowledge” scores fall?

58
Example 5.12 – Solution (1 of 3)
If x is the number of correct answers on the 100-question
exam, the probability of a correct answer, p, is one in five,
so that p = .2. Since the student is randomly selecting
answers, the n = 100 answers are independent, and the
expected score for this binomial random variable is

μ = np = 100(.2) = 20 correct answers

To evaluate the spread or variability of the scores, you can

calculate

59
Example 5.12 – Solution (2 of 3)
Then, using your knowledge of variation from Tchebysheff’s
Theorem and the Empirical Rule, you can make these
statements:
• A large proportion of the scores will lie within two standard
deviations of the mean, or from 20 − 8 = 12 to 20 + 8 = 28.
• Almost all the scores will lie within three standard
deviations of the mean, or from 20 − 12 = 8 to 20 + 12 = 32.

60
Example 5.12 – Solution (3 of 3)
The “guessing” option gives the student a better score than
the zero score on the full recall test, but the student still will
not pass the exam.

61
5.3 The Poisson Probability Distribution

Copyright © Cengage Learning. All rights reserved.

The Poisson Probability Distribution (1 of 7)

Another discrete random variable that has many practical

applications is the Poisson random variable.

Its probability distribution provides a good model for data

that represent the number of occurrences of a specified
event in a given unit of time or space.

63
The Poisson Probability Distribution (2 of 7)

For example,

• The number of calls received by a technical support

specialist during a given period of time
• The number of bacteria per small volume of fluid
• The number of traffic accidents on a section of freeway
during a given time period

64
The Poisson Probability Distribution (3 of 7)

In each example, x represents the number of events that

occur in a period of time or space during which an
average of μ such events can be expected to occur.

The only assumptions needed when one uses the Poisson

distribution to model experiments such as these are that the
counts or events occur randomly and independently of
one another.

65
The Poisson Probability Distribution (4 of 7)

The Poisson Probability Distribution

Let μ be the average number of times that an event occurs
in a certain period of time or space. The probability of k
occurrences of this event is

for values of k = 0, 1, 2, 3,.... The mean and standard

deviation of the Poisson random variable x are

Mean: μ Standard deviation: σ =

66
Example 5.13
The average number of traffic accidents on a certain section
of highway is two per week. Assume that the number of
accidents follows a Poisson distribution with μ = 2.

1. Find the probability of no accidents on this section of

highway during a 1-week period.

2. Find the probability of at most three accidents on this

section of highway during a 2-week period.

67
Example 5.13 – Solution (1 of 4)
1. The average number of accidents per week is μ = 2.
Therefore, the probability of no accidents on this
section of highway during a given week is

2. During a 2-week period, the average number of

accidents on this section of highway is 2(2) = 4.

68
Example 5.13 – Solution (2 of 4)
The probability of at most three accidents during a 2-
week period is

p(x ≤ 3) = p(0) + p(1) + p(2) + p(3)

where

69
Example 5.13 – Solution (3 of 4)
Therefore,

P(x ≤ 3) = .018316 + .073263 + .146525 + .195367

= .433471

Once the values for p(x) have been calculated, you can
use them to construct a probability histogram for the
random variable x.

70
Example 5.13 – Solution (4 of 4)
Graphs of the Poisson probability distribution for μ = .5, 2,
and 4 are shown in figure.

Figure 5.6

71
The Poisson Probability Distribution (5 of 7)

How to Use Table 2 of AppendixⅠ to Calculate Poisson

Probabilities

1. Find the necessary value of μ. Isolate the appropriate

column in Table 2 of AppendixⅠ.

2. Table 2 of AppendixⅠ gives P(x ≤ k) in the row marked k.

Rewrite the probability you need so that it is in this form.

72
The Poisson Probability Distribution (6 of 7)

• List the values of x in your event.

• From the list, write the event as either the difference of
two probabilities:

P(x ≤ a) − P(x ≤ b) for a > b

or the complement of the event:

1 − P(x ≤ a)

or just the event itself:

P(x < a) = P(x ≤ a − 1)

73
The Poisson Probability Distribution (7 of 7)

The Poisson Approximation to the Binomial

Distribution

The Poisson probability distribution provides a simple,

easy-to-compute, and accurate approximation to binomial
probabilities when n is large and μ = np is small, preferably
with np < 7.

74
Example 5.15
Suppose a life insurance company insures the lives of 5000
men aged 42. If actuarial studies show the probability that
any 42-year-old man will die in a given year to be .001, find
the exact probability that the company will have to pay x = 4
claims during a given year.

Solution:
The exact probability is given by the binomial distribution as

for which binomial tables are not available.

75
Example 5.15 – Solution
Calculating μ = np = (5000)(.001) = 5 and substituting into
the formula for the Poisson probability distribution, we have

The value of p(4) could also be obtained using Table 2 in

Appendix Ⅰ with μ = 5 as

p(4) = P(x ≤ 4) − P(x ≤ 3) = .440 − .265 = .175

76
5.4 The Hypergeometric Probability
Distribution

Copyright © Cengage Learning. All rights reserved.

The Hypergeometric Probability Distribution (1 of 2)

The Hypergeometric Probability Distribution

A population contains M successes and N − M failures. The
probability of exactly k successes in a random sample of
size n is

for values of k that depend on N, M, and n with

78
The Hypergeometric Probability Distribution (2 of 2)

The mean and variance of a hypergeometric random

variable are very similar to those of a binomial random
variable with a correction for the finite population size:

79
Example 5.17
A case of wine has 12 bottles, 3 of which contain spoiled
wine. A sample of 4 bottles is randomly selected from the
case.
1. Find the probability distribution for x, the number of
bottles of spoiled wine in the sample.

2. What are the mean and variance of x?

80
Example 5.17 – Solution (1 of 2)
For this example, N = 12, n = 4, M = 3, and (N − M) = 9.
Then

1. The possible values for x are 0, 1, 2, and 3, with

probabilities

81
Example 5.17 – Solution (2 of 2)
2. The mean is given by

and the variance is

82
Example 5.18
An industrial product is shipped in lots of 20. Testing to
determine whether an item is defective is costly; hence, the
manufacturer samples production rather than using a 100%
inspection plan.

The sampling plan calls for sampling five items from each
lot and rejecting the lot if more than one defective is
observed. (If the lot is rejected, each item in the lot is then
tested to isolate the defectives.) If a lot contains four
defectives, what is the probability that it will be accepted?

83
Example 5.18 – Solution (1 of 1)
Let x be the number of defectives in the sample. Then
N = 20, M = 4, (N − M) = 16, and n = 5. The lot will be
rejected if x = 2, 3, or 4. Then

84