0% found this document useful (0 votes)

539 views38 pages

Chapter 5 Some Important Discrete Probability Distributions PDF

Uploaded by

Mishel

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

539 views38 pages

Chapter 5 Some Important Discrete Probability Distributions PDF

Uploaded by

Mishel

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 38

CHAPTER 5

Some Important Discrete

Probability Distributions
USING STATISTICS @ Saxon Home Improvement

5.1 THE PROBABILITY DISTRIBUTION 5.5 HYPERGEOMETRIC DISTRIBUTION

FOR A DISCRETE RANDOM VARIABLE
5.6 (CD-ROM TOPIC) USING THE POISSON
Expected Value of a Discrete Random Variable
DISTRIBUTION TO APPROXIMATE THE
Variance and Standard Deviation of a Discrete
BINOMIAL DISTRIBUTION
Random Variable
EXCEL COMPANION TO CHAPTER 5
5.2 COVARIANCE AND ITS APPLICATION E5.1 Computing the Expected Value of a Discrete
IN FINANCE Random Variable
Covariance E5.2 Computing Portfolio Expected Return
Expected Value, Variance, and Standard Deviation and Portfolio Risk
of the Sum of Two Random Variables E5.3 Computing Binomial Probabilities
Portfolio Expected Return and Portfolio Risk E5.4 Computing Poisson Probabilities
5.3 BINOMIAL DISTRIBUTION E5.5 Computing Hypergeometric Probabilities
E5.6 Creating Histograms for Discrete Probability
5.4 POISSON DISTRIBUTION Distributions

LEARNING OBJECTIVES
In this chapter, you learn:
* The properties of a probability distribution
* To compute the expected value and variance of a probability distribution

* To calculate the covariance and understand its use in finance

* To compute probabilities from binomial, hypergeometric, and Poisson distributions

* How to use the binomial, hypergeometric, and Poisson distributions to solve business problems

USING STATISTICS @ Saxon Home Improvement

Accounting information systems collect, process, store, transform, and distribute
financial information to decision makers both internal and external to a business
organization (see reference 6). These systems continuously audit accounting infor-
mation, looking for errors or incomplete or improbable information. For example,
when customers of the Saxon Home Improvement Company submit online orders,
the company s accounting information system reviews the order forms for possible
mistakes. Any questionable invoices are tagged and included in a daily exceptions
report. Recent data collected by the company show that the likelihood is 0.10 that
an order form will be tagged. Saxon would like to determine the likelihood of find-
ing a certain number of tagged forms in a sample of a specific size. For example,
what would be the likelihood that none of the order forms are tagged in a sample of
four forms? That one of the order forms is tagged?

H ow could the Saxon Home Improvement Company determine the solution to this type of
probability problem? One way is to use a model, or small-scale representation, that
approximates the process. By using such an approximation, Saxon managers could make infer-
ences about the actual order process. Model building is a difficult task for some endeavors, and
in this case, the Saxon managers can use probability distributions, mathematical models suited
for solving the type of probability problems the managers are facing. Reading this chapter will
help you learn about characteristics of a probability distribution and how to specifically apply
the binomial, Poisson, and hypergeometric distributions to business problems.

5.1 THE PROBABILITY DISTRIBUTION FOR A DISCRETE

RANDOM VARIABLE
In Section 1.5, a numerical variable was defined as a variable that yielded numerical responses,
such as the number of magazines you subscribe to or your height, in inches. Numerical vari-
ables are classified as discrete or continuous. Continuous numerical variables produce out-
comes that come from a measuring process (for example, your height). Discrete numerical
variables produce outcomes that come from a counting process (for example, the number of
magazines you subscribe to). This chapter deals with probability distributions that represent
discrete numerical variables.

PROBABILITY DISTRIBUTION FOR A DISCRETE RANDOM VARIABLE

A probability distribution for a discrete random variable is a mutually exclusive listing
of all possible numerical outcomes for that variable such that a particular probability of
occurrence is associated with each outcome.

For example, Table 5.1 gives the distribution of the number of mortgages approved per week at
the local branch office of a bank. The listing in Table 5.1 is collectively exhaustive because all
possible outcomes are included. Thus, the probabilities must sum to 1. Figure 5.1 is a graphical
representation of Table 5.1.

TAB LE 5 .1 Home Mortgages Approved per Week Probability

Probability Distribution 0 0.10
of the Number of Home 1 0.10
Mortgages Approved 2 0.20
per Week 3 0.30
4 0.15
5 0.10
6 0.05

FIGURE 5.1
P (X )
Probability distribution
of the number of home
mortgages approved .3
per week
.2

0 1 2 3 4 5 6 X
Home Mortgages Approved per Week

Expected Value of a Discrete Random Variable

The mean, , of a probability distribution is the expected value of its random variable. To cal-
culate the expected value, you multiply each possible outcome, X, by its corresponding proba-
bility, P(X), and then sum these products.

EXPECTED VALUE, , OF A DISCRETE RANDOM VARIABLE

N
= E( X ) = X i P( X i ) (5.1)
i =1

where

Xi = the ith outcome of the discrete random variable X

P(Xi) = probability of occurrence of the ith outcome of X

For the probability distribution of the number of home mortgages approved per week
(Table 5.1), the expected value is computed using Equation (5.1) below and is also shown in
Table 5.2.

N
= E( X ) = X i P( X i )
i =1
= (0 )(0.1) + (1)( 0.1) + ( 2 )(0.2 ) + (3)(0.3) + ( 4 )( 0.15) + (5)( 0.1) + ( 6 )( 0.05)
= 0 + 0.1 + 0.4 + 0.9 + 0.6 + 0.5 + 0.3
= 2.8

TA B L E 5 .2 Home Mortgages
Computing the Approved per Week (Xi ) P(Xi ) Xi P(Xi )
Expected Value of 0 0.10 (0)(0.10) = 0.0
the Number of Home
1 0.10 (1)(0.10) = 0.1
Mortgages Approved
per Week 2 0.20 (2)(0.20) = 0.4
3 0.30 (3)(0.30) = 0.9
4 0.15 (4)(0.15) = 0.6
5 0.10 (5)(0.10) = 0.5
6 0.05 (6)(0.05) = 0.3
1.00 = E(X) = 2.8

The expected value of 2.8 for the number of mortgages approved is not a possible outcome
because the actual number of mortgages approved in a given week must be an integer value.
The expected value represents the mean number of mortgages approved per week.

Variance and Standard Deviation of a Discrete Random Variable

You compute the variance of a probability distribution by multiplying each possible squared
difference [Xi E(X)]2 by its corresponding probability, P(Xi), and then summing the resulting
products. Equation (5.2) defines the variance of a discrete random variable.

VARIANCE OF A DISCRETE RANDOM VARIABLE

N
2
= [ Xi E ( X )]2 P ( X i ) (5.2)
i =1

where

Xi = the ith outcome of the discrete random variable X

P(Xi) = probability of occurrence of the ith outcome of X

Equation (5.3) defines the standard deviation of a discrete random variable.

STANDARD DEVIATION OF A DISCRETE RANDOM VARIABLE

N
2
= = [Xi E ( X )]2 P ( X i ) (5.3)
i =1

In Table 5.3, the variance and the standard deviation of the number of home mortgages
approved per week are computed using Equations (5.2) and (5.3):

TA BL E 5.3 Home Mortgages

Approved per Week
Computing the Variance
and Standard Deviation
(Xi ) P(Xi ) Xi P(Xi ) [Xi E(X)]2P(Xi )
of the Number of Home 0 0.10 (0)(0.10) = 0.0 (0 2.8)2(0.10) = 0.784
Mortgages Approved 1 0.10 (1)(0.10) = 0.1 (1 2.8)2(0.10) = 0.324
per Week
2 0.20 (2)(0.20) = 0.4 (2 2.8)2(0.20) = 0.128
3 0.30 (3)(0.30) = 0.9 (3 2.8)2(0.30) = 0.012
4 0.15 (4)(0.15) = 0.6 (4 2.8)2(0.15) = 0.216
5 0.10 (5)(0.10) = 0.5 (5 2.8)2(0.10) = 0.484
6 0.05 (6)(0.05) = 0.3 (6 2.8)2(0.05) = 0.512
1.00 = E(X ) = 2.8 2 = 2.46

N
2
= [ Xi E ( X )]2 P ( X i )
i =1
= (0 2.8 ) 2 (0.10 ) + (1 2.8 ) 2 ( 0.10 ) + ( 2 2.8 ) 2 (0.20 ) + (3 2.8 ) 2 ( 0.30 )
+ ( 4 2.8 ) 2 ( 0.15) + (5 2.8 ) 2 ( 0.10 ) + ( 6 2.8 ) 2 ( 0.05)
= 0.784 + 0.324 + 0.128 + 0.012 + 0.216 + 0.484 + 0.512
= 2.46

and

2
= = 2.46 = 1.57

Thus, the mean number of mortgages approved per week is 2.8, the variance is 2.46, and the
standard deviation is 1.57.

PROBLEMS FOR SECTION 5.1

Learning the Basics
PH Grade 5.1 Given the following probability distributions: PH Grade 5.2 Given the following probability distributions:
ASSIST ASSIST

Distribution A Distribution B Distribution C Distribution D

X P(X ) X P(X ) X P(X ) X P(X )

0 0.50 0 0.05 0 0.20 0 0.10
1 0.20 1 0.10 1 0.20 1 0.20
2 0.15 2 0.15 2 0.20 2 0.40
3 0.10 3 0.20 3 0.20 3 0.20
4 0.05 4 0.50 4 0.20 4 0.10

a. Compute the expected value for each distribution. a. Compute the expected value for each distribution.
b. Compute the standard deviation for each distribution. b. Compute the standard deviation for each distribution.
c. Compare the results of distributions A and B. c. Compare the results of distributions C and D.

Applying the Concepts a. Compute the mean number of accidents per day.
b. Compute the standard deviation.
5.3 How many credit cards do you have in your wallet?
According to a survey by Ipsos, a large survey research 5.5 The manager of a large computer network has devel-
company, 26% of adults in the United States reported hav- oped the following probability distribution of the number
ing no credit cards; 38% reported having one or two; 20% of interruptions per day:
three or four; 15% five or more; and 1% reported not
sure ( Snapshots, usatoday.com, April 18, 2006). Interruptions (X ) P(X )
Suppose that the following table contains the complete 0 0.32
probability distribution for the number of credit cards 1 0.35
owned by adults in the United States: 2 0.18
3 0.08
Number of Credit Cards (X ) P(X ) 4 0.04
5 0.02
0 0.26
6 0.01
1 0.22
2 0.16 a. Compute the expected number of interruptions per day.
3 0.12 b. Compute the standard deviation.
4 0.08
5 0.06 5.6 In the carnival game Under-or-Over-Seven, a pair of
6 0.04 fair dice is rolled once, and the resulting sum determines
7 0.03 whether the player wins or loses his or her bet. For exam-
8 0.02 ple, the player can bet $1 that the sum will be under 7
9 0.01 that is, 2, 3, 4, 5, or 6. For this bet, the player loses $1 if the
outcome equals or exceeds 7 and wins $1 if the result is
a. Compute the mean number of credit cards owned by a under 7. Similarly, the player can bet $1 that the sum will
U.S. adult. be over 7 that is, 8, 9, 10, 11, or 12. Here, the player wins
b. Compute the standard deviation. $1 if the result is over 7 but loses $1 if the result is 7 or
under. A third method of play is to bet $1 on the outcome
SELF 5.4 The following table contains the probability 7. For this bet, the player wins $4 if the result of the roll is
Test distribution for the number of traffic accidents 7 and loses $1 otherwise.
daily in a small city: a. Construct the probability distribution representing the
different outcomes that are possible for a $1 bet on
Number of Accidents Daily (X ) P(X ) being under 7.
b. Construct the probability distribution representing the
0 0.10
different outcomes that are possible for a $1 bet on
1 0.20
being over 7.
2 0.45
c. Construct the probability distribution representing the
3 0.15
different outcomes that are possible for a $1 bet on 7.
4 0.05
d. Show that the expected long-run profit (or loss) to the
5 0.05
player is the same, no matter which method of play is used.

5.2 COVARIANCE AND ITS APPLICATION IN FINANCE

In Section 5.1, the expected value, variance, and standard deviation of a discrete random variable
of a probability distribution were discussed. In this section, the covariance between two variables
is introduced and applied to portfolio management, a topic of great interest to financial analysts.

Covariance
The covariance, *XY, is a measure of the strength of the relationship between two discrete ran-
dom variables, X and Y. A positive covariance indicates a positive relationship. A negative
covariance indicates a negative relationship. A covariance of 0 indicates that the two variables
are independent. Equation (5.4) defines the covariance.

COVARIANCE
N
XY = [Xi E ( X )][Yi E (Y )]P ( X iYi ) (5.4)
i =1

where

X = discrete random variable X

Xi = ith outcome of X
P(XiYi) = probability of occurrence of the ith outcome of X
and the ith outcome of Y
Y = discrete random variable Y
Yi = ith outcome of Y
i = 1, 2, . . . , N

To illustrate the covariance, suppose that you are deciding between two alternative invest-
ments for the coming year. The first investment is a mutual fund that consists of the stocks that
comprise the Dow Jones Industrial Average. The second investment is a mutual fund that is
expected to perform best when economic conditions are weak. Your estimate of the returns for
each investment (per $1,000 investment) under three economic conditions, each with a given
probability of occurrence, is summarized in Table 5.4.

TA BL E 5.4 Investment
Estimated Returns P(XiYi) Economic Condition Dow Jones Fund Weak-Economy Fund
for Each Investment
Under Three Economic 0.2 Recession $100 +$200
Conditions 0.5 Stable economy +100 +50
0.3 Expanding economy +250 100

The expected value and standard deviation for each investment and the covariance of the
two investments are computed as follows:

Let X = Dow Jones fund, and Y = weak-economy fund

E( X ) = X = ( 100)(0.2) + (100)(0.5) + ( 250)(0.3) = $105
E (Y ) = Y = ( +200)(0.2 ) + (50)(0.5) + ( 100)(0.3) = $35
2
Var ( X ) = X = ( 100 105) 2 (0.2 ) + (100 105) 2 (0.5) + ( 250 105) 2 (0.3)
= 14, 725
X = $121.35
2
Var (Y ) = Y = ( 200 35) 2 (0.2 ) + (50 35) 2 (0.5) + ( 100 35) 2 (0.3)
= 11,025
Y = $105.00
XY = ( 100 105)(200 35)(0.2) + (100 105)(50 35)(0.5)
+ (250 105)( 100 35)(0.3)
= 6, 765 37.5 5, 782.5
= 12, 675

Thus, the Dow Jones fund has a higher expected value (that is, larger expected return) than the
weak-economy fund but has a higher standard deviation (that is, more risk). The covariance of
12,675 between the two investments indicates a negative relationship in which the two invest-
ments are varying in the opposite direction. Therefore, when the return on one investment is
high, typically, the return on the other is low.

Expected Value, Variance, and Standard Deviation

of the Sum of Two Random Variables
Equations (5.1) (5.3) defined the expected value, variance, and standard deviation of a proba-
bility distribution while Equation (5.4) defines the covariance between two variables, X and Y.
The expected value of the sum of two random variables is equal to the sum of the expected
values. The variance of the sum of two random variables is equal to the sum of the variances
plus twice the covariance. The standard deviation of the sum of two random variables is the
square root of the variance of the sum of two random variables.

EXPECTED VALUE OF THE SUM OF TWO RANDOM VARIABLES

E(X + Y ) = E(X ) + E(Y ) (5.5)

VARIANCE OF THE SUM OF TWO RANDOM VARIABLES

Var( X + Y ) = 2X + Y = 2X + Y2 + 2 XY (5.6)

STANDARD DEVIATION OF THE SUM OF TWO RANDOM VARIABLES

2
X +Y = X +Y (5.7)

To illustrate the expected value, variance, and standard deviation of the sum of two ran-
dom variables, consider the two investments previously discussed. If X = Dow Jones fund and
Y = weak-economy fund, using Equations (5.5), (5.6), and (5.7),

E ( X + Y ) = E ( X ) + E (Y ) = 105 + 35 = $140
2 2 2
X +Y = X + Y +2 XY
= 14,725 + 11,025 + ( 2 )( 12,675)
= 400
X +Y = $20

The expected return of the sum of the Dow Jones fund and the weak-economy fund is $140,
with a standard deviation of $20. The standard deviation of the sum of the two investments is
much less than the standard deviation of either single investment because there is a large nega-
tive covariance between the investments.

Portfolio Expected Return and Portfolio Risk

Now that the covariance and the expected return and standard deviation of the sum of two ran-
dom variables have been defined, these concepts can be applied to the study of a group of
assets referred to as a portfolio. Investors combine assets into portfolios to reduce their risk
(see references 1 and 2). Often, the objective is to maximize the return while minimizing the
risk. For such portfolios, rather than studying the sum of two random variables, each invest-
ment is weighted by the proportion of assets assigned to that investment. Equations (5.8) and
(5.9) define the portfolio expected return and portfolio risk.

PORTFOLIO EXPECTED RETURN

The portfolio expected return for a two-asset investment is equal to the weight assigned to
asset X multiplied by the expected return of asset X plus the weight assigned to asset Y
multiplied by the expected return of asset Y.

E(P) = wE(X ) + (1 w)E(Y ) (5.8)

where

E(P) = portfolio expected return

w = portion of the portfolio value assigned to asset X
(1 w) = portion of the portfolio value assigned to asset Y
E(X ) = expected return of asset X
E(Y ) = expected return of asset Y

PORTFOLIO RISK

p = w2 2
X + (1 w )2 2
Y + 2w(1 w) XY (5.9)

In the previous example, you evaluated the expected return and risk of two different
investments, a Dow Jones fund and a weak-economy fund. You also computed the covariance
of the two investments. Now suppose that you wish to form a portfolio of these two invest-
ments that consists of an equal investment in each of these two funds. To compute the port-
folio expected return and the portfolio risk, using Equations (5.8) and (5.9), with w = 0.50,
E(X ) = $105, E(Y ) = $35, 2X = 14,725, Y2 = 11,025, and XY = 12,675,

E ( P ) = ( 0.5)(105) + (1 0.5)(35) = $70

p = (0.5) 2 (14,725) + (1 0.5) 2 (11,025) + 2( 0.5)(1 0.5)( 12,675)

= 100 = $10

Thus, the portfolio has an expected return of $70 for each $1,000 invested (a return of 7%) and
has a portfolio risk of $10. The portfolio risk here is small because there is a large negative
covariance between the two investments. The fact that each investment performs best under dif-
ferent circumstances reduces the overall risk of the portfolio.

PROBLEMS FOR SECTION 5.2

Learning the Basics
PH Grade 5.7 Given the following probability distributions Compute
ASSIST for variables X and Y:
a. E(X ) and E(Y ).
P(XiYi ) X Y b. X and Y.
0.4 100 200 c. XY.
0.6 200 100
d. E(X + Y ).

PH Grade 5.8 Given the following probability distribu- stock under four different economic conditions has the fol-
ASSIST tions for variables X and Y: lowing probability distribution:

P(XiYi ) X Y Returns
0.2 100 50 Probability Economic Condition Stock X Stock Y
0.4 50 30 0.1 Recession $100 $50
0.3 200 20 0.3 Slow growth 0 150
0.1 300 20 0.3 Moderate growth 80 20
0.3 Fast growth 150 100
Compute
a. E(X ) and E(Y ). Compute the
b. X and Y. a. expected return for stock X and for stock Y.
c. XY. b. standard deviation for stock X and for stock Y.
d. E(X + Y ). c. covariance of stock X and stock Y.
PH Grade 5.9 Two investments, X and Y, have the following d. Would you invest in stock X or stock Y? Explain.
ASSIST characteristics: 5.13 Suppose that in Problem 5.12 you wanted to create a
2 portfolio that consists of stock X and stock Y. Compute the
E ( X ) = $50, E (Y ) = $100, X = 9,000, portfolio expected return and portfolio risk for each of the
2
= 15,000, and = 7,500. following percentages invested in stock X:
Y XY
a. 30%
If the weight of portfolio assets assigned to investment X b. 50%
is 0.4, compute the c. 70%
a. portfolio expected return. d. On the basis of the results of (a) through (c), which port-
b. portfolio risk. folio would you recommend? Explain.
5.14 You are trying to develop a strategy for investing in
Applying the Concepts
two different stocks. The anticipated annual return for a
5.10 The process of being served at a bank consists of two $1,000 investment in each stock under four different eco-
independent parts the time waiting in line and the time it nomic conditions has the following probability distribution:
takes to be served by the teller. Suppose that the time wait-
ing in line has an expected value of 4 minutes, with a stan- Returns
dard deviation of 1.2 minutes, and the time it takes to be Probability Economic Condition Stock X Stock Y
served by the teller has an expected value of 5.5 minutes, 0.1 Recession $50 $100
with a standard deviation of 1.5 minutes. Compute the 0.3 Slow growth 20 50
a. expected value of the total time it takes to be served at 0.4 Moderate growth 100 130
the bank. 0.2 Fast growth 150 200
b. standard deviation of the total time it takes to be served
at the bank. Compute the
a. expected return for stock X and for stock Y.
PH Grade 5.11 In the portfolio example in this section (see
b. standard deviation for stock X and for stock Y.
ASSIST page 187), half the portfolio assets are invested in
c. covariance of stock X and stock Y.
the Dow Jones fund and half in a weak-economy
d. Would you invest in stock X or stock Y? Explain.
fund. Recalculate the portfolio expected return and the port-
folio risk if 5.15 Suppose that in Problem 5.14 you wanted to create a
a. 30% of the portfolio assets are invested in the Dow portfolio that consists of stock X and stock Y. Compute the
Jones fund and 70% in a weak-economy fund. portfolio expected return and portfolio risk for each of the
b. 70% of the portfolio assets are invested in the Dow following percentages invested in stock X:
Jones fund and 30% in a weak-economy fund. a. 30%
c. Which of the three investment strategies (30%, 50%, b. 50%
or 70% in the Dow Jones fund) would you recom- c. 70%
mend? Why? d. On the basis of the results of (a) through (c), which port-
folio would you recommend? Explain.
SELF 5.12 You are trying to develop a strategy for
Test investing in two different stocks. The anticipated 5.16 You are trying to set up a portfolio that consists of a
annual return for a $1,000 investment in each corporate bond fund and a common stock fund. The fol-

lowing information about the annual return (per $1,000) of b. standard deviation for the corporate bond fund and for
each of these investments under different economic condi- the common stock fund.
tions is available, along with the probability that each of c. covariance of the corporate bond fund and the common
these economic conditions will occur: stock fund.
d. Would you invest in the corporate bond fund or the com-
Corporate Common
mon stock fund? Explain.
Economic Bond Stock
Probability Conditions Fund Fund 5.17 Suppose that in Problem 5.16 you wanted to create a
portfolio that consists of a corporate bond fund and a com-
0.10 Recession *$30 *$150
mon stock fund. Compute the portfolio expected return and
0.15 Stagnation 50 *20
portfolio risk for each of the following percentages
0.35 Slow growth 90 120
invested in a corporate bond fund:
0.30 Moderate growth 100 160
a. 30%
0.10 High growth 110 250
b. 50%
Compute the c. 70%
a. expected return for the corporate bond fund and for the d. On the basis of the results of (a) through (c), which port-
common stock fund. folio would you recommend? Explain.

5.3 BINOMIAL DISTRIBUTION

This section and the two that follow use mathematical models to solve business problems.

MATHEMATICAL MODEL
A mathematical model is a mathematical expression that represents a variable of interest.

When a mathematical expression is available, you can compute the exact probability of occur-
rence of any particular outcome of the variable.
The binomial distribution is one of the most useful mathematical models. You use the
binomial distribution when the discrete variable of interest is the number of successes in a sam-
ple of n observations. The binomial distribution has four essential properties:
* The sample consists of a fixed number of observations, n.
* Each observation is classified into one of two mutually exclusive and collectively exhaus-
tive categories, usually called success and failure.
* The probability of an observation being classified as success, p, is constant from obser-
vation to observation. Thus, the probability of an observation being classified as failure,
1 * p, is constant over all observations.
* The outcome (i.e., success or failure) of any observation is independent of the outcome of
any other observation. To ensure independence, the observations can be randomly selected
either from an infinite population without replacement or from a finite population with
replacement.

Returning to the Using Statistics scenario presented on page 180 concerning the account-
ing information system, suppose success is defined as a tagged order form and failure as any
other outcome. You are interested in the number of tagged order forms in a given sample of
orders.
What results can occur? If the sample contains four orders, there could be none, one, two,
three, or four tagged order forms. The binomial random variable, the number of tagged order
forms, cannot take on any other value because the number of tagged order forms cannot be
more than the sample size, n, and cannot be less than zero. Therefore, the binomial random
variable has a range from 0 to n.

Suppose that you observe the following result in a sample of four orders:
First Order Second Order Third Order Fourth Order
Tagged Tagged Not tagged Tagged
What is the probability of having three successes (tagged order forms) in a sample of four
orders in this particular sequence? Because the historical probability of a tagged order is 0.10,
the probability that each order occurs in the sequence is
First Order Second Order Third Order Fourth Order
p = 0.10 p = 0.10 1 p = 0.90 p = 0.10
Each outcome is independent of the others because the order forms were selected from an
extremely large or practically infinite population without replacement. Therefore, the probabil-
ity of having this particular sequence is

pp(1 p ) p = p3 (1 p )1
= (0.10 )(0.10 )(0.10 )( 0.90 )
= (0.10 )3 (0.90 )1
= 0.0009

This result indicates only the probability of three tagged order forms (successes) from a
sample of four order forms in a specific sequence. To find the number of ways of selecting
X objects from n objects, irrespective of sequence, you use the rule of combinations given in
Equation (5.10).

COMBINATIONS
The number of combinations of selecting X objects out of n objects is given by

n!
nCX = (5.10)
X !( n X )!

where

n! = (n)(n 1) . . . (1) is called n factorial. By definition, 0! = 1.

With n = 4 and X = 3, there are

n! 4! 4 3 2 1
nCX = = = = 4
X !( n X )! 3!( 4 3)! (3 2 1)(1)

such sequences. The four possible sequences are:

Sequence 1 = tagged, tagged, tagged, not tagged, with probability
ppp(1 p) = p3(1 p)1 = 0.0009
Sequence 2 = tagged, tagged, not tagged, tagged, with probability
pp(1 p)p = p3(1 p)1 = 0.0009
Sequence 3 = tagged, not tagged, tagged, tagged, with probability
p(1 p)pp = p3(1 p)1 = 0.0009
Sequence 4 = not tagged, tagged, tagged, tagged, with probability
(1 p)ppp = p3(1 p)1 = 0.0009

Therefore, the probability of three tagged order forms is equal to

( Number of possible sequences) ( Probability of a particular sequence)

= ( 4) ( 0.0009 ) = 0.0036

You can make a similar, intuitive derivation for the other possible outcomes of the random
variable zero, one, two, and four tagged order forms. However, as n, the sample size, gets
large, the computations involved in using this intuitive approach become time-consuming. A
mathematical model provides a general formula for computing any binomial probability.
Equation (5.11) is the mathematical model representing the binomial probability distribution
for computing the number of successes, X, given the values of n and p.

BINOMIAL DISTRIBUTION
n!
P( X ) = p X (1 p)n X
(5.11)
X !(n X )!

where

P(X) = probability of X successes, given n and p

n = number of observations
p = probability of success
1 p = probability of failure
X = number of successes in the sample (X = 0, 1, 2, . . . , n)

Equation (5.11) restates what you had intuitively derived. The binomial variable X can have
any integer value X from 0 through n. In Equation (5.11), the product

pX(1 p)n X

indicates the probability of exactly X successes from n observations in a particular sequence.

The term

n!
X !(n X )!

indicates how many combinations of the X successes from n observations are possible. Hence,
given the number of observations, n, and the probability of success, p, the probability of X
successes is:

P( X ) = ( Number of possible sequences) ( Probability of a particular sequence)

n!
= p X (1 p) n X
X !( n X )!

Example 5.1 illustrates the use of Equation (5.11).

EX A MP LE 5 .1 DETERMINING P(X = 3), GIVEN n = 4 AND p = 0.1

If the likelihood of a tagged order form is 0.1, what is the probability that there are three tagged
order forms in the sample of four?
SOLUTION Using Equation (5.11), the probability of three tagged orders from a sample of
four is

4!
P ( X = 3) = (0.1)3 (1 0.1)4 3
3!( 4 3)!
4!
= (0.1)3 ( 0.9 )1
3!( 4 3)!
= 4( 0.1)(0.1)( 0.1)( 0.9 ) = 0.0036

Examples 5.2 and 5.3 show the computations for other values of X.

EXA MPL E 5.2 DETERMINING P(X 3), GIVEN n = 4 AND p = 0.1

If the likelihood of a tagged order form is 0.1, what is the probability that there are three or
more (that is, at least three) tagged order forms in the sample of four?
SOLUTION In Example 5.1, you found that the probability of exactly three tagged order
forms from a sample of four is 0.0036. To compute the probability of at least three tagged order
forms, you need to add the probability of three tagged order forms to the probability of four
tagged order forms. The probability of four tagged order forms is

4!
P( X = 4 ) = (0.1)4 (1 0.1)4 4
4!( 4 4 )!
4!
= (0.1)4 (0.9 )0
4!(0 )!
= 1(0.1)(0.1)(0.1)(0.1) = 0.0001

Thus, the probability of at least three tagged order forms is

P( X 3) = P ( X = 3) + P ( X = 4 )
= 0.0036 + 0.0001
= 0.0037

There is a 0.37% chance that there will be at least three tagged order forms in a sample of four.

EXA MP LE 5 .3 DETERMINING P(X < 3), GIVEN n = 4 AND p = 0.1

If the likelihood of a tagged order form is 0.1, what is the probability that there are less than
three tagged order forms in the sample of four?
SOLUTION The probability that there are less than three tagged order forms is

P(X < 3) = P(X = 0) + P(X = 1) + P(X = 2)

Using Equation (5.11) on page 191, these probabilities are

4!
P( X = 0 ) = ( 0.1)0 (1 0.1)4 0
= 0.6561
0!( 4 0 )!
4!
P ( X = 1) = (0.1)1(1 0.1)4 1
= 0.2916
1!( 4 1)!
4!
P( X = 2 ) = ( 0.1) 2 (1 0.1)4 2
= 0.0486
2!( 4 2 )!

Therefore, P(X < 3) = 0.6561 + 0.2916 + 0.0486 = 0.9963.

P(X < 3) could also be calculated from its complement, P(X 3), as follows:

P ( X < 3) = 1 P( X 3)
=1 0.0037 = 0.9963

Computations such as those in Example 5.3 can become tedious, especially as n gets large. To
avoid computational drudgery, you can find many binomial probabilities directly from Table E.6,
a portion of which is reproduced in Table 5.5. Table E.6 provides binomial probabilities for
X = 0, 1, 2, . . . , n for various selected combinations of n and p. For example, to find the proba-
bility of exactly two successes in a sample of four when the probability of success is 0.1, you
first find n = 4 and then look in the row X = 2 and column p = 0.10. The result is 0.0486.

TAB LE 5 .5 p
Finding a Binomial n X 0.01 0.02 .... 0.10
Probability for n = 4,
X = 2, and p = 0.1 4 0 0.9606 0.9224 .... 0.6561
1 0.0388 0.0753 .... 0.2916
2 0.0006 0.0023 .... 0.0486
3 0.0000 0.0000 .... 0.0036
4 0.0000 0.0000 .... 0.0001
Source: Table E.6.

You can also compute the binomial probabilities given in Table E.6 by using Microsoft
Excel as shown in Figure 5.2.

FIGURE 5.2
Microsoft Excel
worksheet for
computing binomial
probabilities

See Section E5.3 to create

this.

The shape of a binomial probability distribution depends on the values of n and p.

Whenever p = 0.5, the binomial distribution is symmetrical, regardless of how large or small
the value of n. When p 0.5, the distribution is skewed. The closer p is to 0.5 and the larger
the number of observations, n, the less skewed the distribution becomes. For example, the dis-
tribution of the number of tagged order forms is highly skewed to the right because p = 0.1
and n = 4 (see Figure 5.3).

FIGURE 5.3
Microsoft Excel
histogram of the
binomial probability
distribution with n = 4
and p = 0.1

See Section E5.6 to create

this.

The mean of the binomial distribution is equal to the product of n and p. Instead of using
Equation (5.1) on page 181 to compute the mean of the probability distribution, you use
Equation (5.12) to compute the mean for variables that follow the binomial distribution.

MEAN OF THE BINOMIAL DISTRIBUTION

The mean, , of the binomial distribution is equal to the sample size, n, multiplied by the
probability of success, p.

= E(X ) = np (5.12)

On the average, over the long run, you theoretically expect = E(X) = np = (4)(0.1) = 0.4
tagged order form in a sample of four orders.
The standard deviation of the binomial distribution is calculated using Equation (5.13).

STANDARD DEVIATION OF THE BINOMIAL DISTRIBUTION

2
= = Var( X ) = np(1 p) (5.13)

The standard deviation of the number of tagged order forms is

= 4( 0.1)(0.9 ) = 0.60

You get the same result if you use Equation (5.3) on page 182.
Example 5.4 applies the binomial distribution to service at a fast-food restaurant.

EX A MP LE 5 .4 COMPUTING BINOMIAL PROBABILITIES

Accuracy in taking orders at a drive-through window is an important feature for fast-food
chains. Each month QSR Magazine, www.qsrmagazine.com, publishes the results of its sur-
veys. Accuracy is measured as the percentage of orders consisting of a main item, side item,
and drink (but omitting one standard item, such as a pickle) that are filled correctly. In a recent
month, suppose that the percentage of correct orders of this type filled at Burger King was
approximately 88%. If a sample of three orders is taken, what are the mean and standard devi-
ation of the binomial distribution for the number of orders filled accurately? Suppose that you
and two friends go to the drive-through window at Burger King, and each of you places an
order of the type just mentioned. What are the probabilities that all three, that none of the three,
and that at least two of the three orders will be filled accurately?
SOLUTION Because there are three orders and the probability of an accurate order is 0.88,
n = 3 and p = 0.88. Using Equations (5.12) and (5.13),
= E ( X ) = np = 3( 0.88 ) = 2.64
2
= = Var( X ) = np(1 p)
= 3( 0.88 )(0.12 )
= 0.3168 = 0.563

Using Equation (5.11),

3!
P ( X = 3) = (0.88 )3 (1 0.88 )3 3
3!(3 3)!
3!
= (0.88 )3 ( 0.12 )0
3!(3 3)!
= 1( 0.88 )(0.88 )( 0.88 )(1) = 0.6815
3!
P( X = 0) = (0.88 )0 (1 0.88 )3 0
0!(3 0 )!
3!
= ( 0.88 )0 (0.12 )3
0!(3 0 )!
= 1(1)(0.12 )( 0.12 )(0.12 ) = 0.0017
3!
P( X = 2) = ( 0.88 ) 2 (1 0.88 )3 2
2!( 3 2 )!
3!
= ( 0.88 ) 2 ( 0.12 )1
2!( 3 2 )!
= 3(0.88 )(0.88 )(0.12 ) = 0.2788
P( X 2 ) = P(( X = 2 ) + P ( X = 3)
= 0.2788 + 0.6815
= 0.9603

The mean number of accurate orders filled in a sample of three orders is 2.64, and the standard
deviation is 0.563. The probability that all three orders are filled accurately is 0.6815, or
68.15%. The probability that none of the orders are filled accurately is 0.0017, or 0.17%. The
probability that at least two orders are filled accurately is 0.9603, or 96.03%.

In this section, you have been introduced to the binomial distribution. The binomial distri-
bution is an important mathematical model in many business situations. It is also used to esti-
mate or test hypotheses about proportions (see Chapters 8 and 9).

PROBLEMS FOR SECTION 5.3

Learning the Basics question and replaces the ball in the box. The marking on
the ball will determine her answer to the question. There
PH Grade 5.18 Determine the following: are five multiple-choice questions on the exam. What is the
ASSIST a. For n = 4 and p = 0.12, what is P(X = 0)? probability that she will get
b. For n = 10 and p = 0.40, what is P(X = 9)? a. five questions correct?
c. For n = 10 and p = 0.50, what is P(X = 8)? b. at least four questions correct?
d. For n = 6 and p = 0.83, what is P(X = 5)? c. no questions correct?
5.19 If n = 5 and p = 0.40, what is the probability that d. no more than two questions correct?
a. X = 4?
SELF 5.24 In Example 5.4 on page 195, you and two
b. X * 3? Test friends decided to go to Burger King. Instead,
c. X < 2?
suppose that you went to McDonald s, which last
d. X > 1?
month filled 90% of the orders accurately. What is the
PH Grade 5.20 Determine the mean and standard devia- probability that
ASSIST tion of the random variable X in each of the fol- a. all three orders will be filled accurately?
lowing binomial distributions: b. none of the three will be filled accurately?
a. n = 4 and p = 0.10 c. at least two of the three will be filled accurately?
b. n = 4 and p = 0.40 d. What are the mean and standard deviation of the bino-
c. n = 5 and p = 0.80 mial distribution used in (a) through (c)? Interpret these
d. n = 3 and p = 0.50 values.

Applying the Concepts 5.25 In April 2006, Gallup News Service reported that
just 25% of U.S. adults view the country s economic out-
5.21 The increase or decrease in the price of a stock look as positive. Gallup further reports that this pessimistic
between the beginning and the end of a trading day is view of the economy is relatively unchanged since early
assumed to be an equally likely random event. What is the 2001. During this five-year period, Gallup has surveyed
probability that a stock will show an increase in its closing more than 100,000 people (F. Newport and J. Carroll,
price on five consecutive days? Public s View of Economy Has Never Recovered After Dot-
5.22 Sixty percent of Americans read their employment Com Bust, galluppoll.com, April 18, 2006.). Thus the
contracts, including the fine print ( Snapshots, probability that a randomly selected adult in the United
usatoday.com, January 20, 2004). Assume that the number States views the economic outlook as positive is 0.25.
of employees who read every word of their contract can be a. You select a random sample of 10 adults in the United
modeled using the binomial distribution. For a group of States. Assume that the number of the 10 adults having a
five employees, what is the probability that positive outlook on the economy is distributed as a bino-
a. all five will have read every word of their contracts? mial random variable. What are the mean and standard
b. at least three will have read every word of their contracts? deviation of this distribution?
c. less than two will have read every word of their contracts? b. What assumptions are necessary in (a)?
d. What are your answers in (a) through (c) if the probabil-
5.26 Referring to Problem 5.25, find the probability that
ity is 0.80 that an employee reads every word of his or
of the 10 adults:
her contract?
a. 0 have a positive outlook on the economy.
PH Grade 5.23 A student is taking a multiple-choice exam b. exactly 5 have a positive outlook on the economy.
ASSIST in which each question has four choices. c. 5 or less have a positive outlook on the economy.
Assuming that she has no knowledge of the cor- d. 6 or more have a positive outlook on the economy.
rect answers to any of the questions, she has decided on a e. If you took a random sample of 10 adults from the state
strategy in which she will place four balls (marked A, B, C, of California and found that 6 had a positive outlook on
and D) into a box. She randomly selects one ball for each the economy, what could you infer about Californians

views of the economy compared to those in the United 5.28 In a survey conducted by the Society for Human
States as a whole? Resource Management, 68% of workers said that employers
have the right to monitor their telephone use. ( Snapshots,
PH Grade 5.27 When a customer places an order with
usatoday.com, April 18, 2006). Suppose that a random
ASSIST Rudy s On-Line Office Supplies, a computerized
sample of 20 workers is selected, and they are asked if
accounting information system (AIS) automati-
employers have the right to monitor telephone use. What is
cally checks to see if the customer has exceeded his or her
the probability that:
credit limit. Past records indicate that the probability of
a. 5 or less of the workers agree?
customers exceeding their credit limit is 0.05. Suppose
b. 10 or less of the workers agree?
that, on a given day, 20 customers place orders. Assume
c. 15 or less of the workers agree?
that the number of customers that the AIS detects as having
exceeded their credit limit is distributed as a binomial ran- 5.29 Referring to Problem 5.28, when the same workers
dom variable. were asked if employers have the right to monitor their cell
a. What are the mean and standard deviation of the number phone use, the percentage dropped to 52%. Suppose that
of customers exceeding their credit limits? the 20 workers are asked if employers have the right to
b. What is the probability that 0 customers will exceed monitor cell phone use. What is the probability that:
their limits? a. 5 or less of the workers agree?
c. What is the probability that 1 customer will exceed his b. 10 or less of the workers agree?
or her limit? c. 15 or less of the workers agree?
d. What is the probability that 2 or more customers will d. Compare the results of (a) through (c) to those for
exceed their limits? Problem 5.28.

5.4 POISSON DISTRIBUTION

Many studies are based on counts of the times a particular event occurs in a given area of
opportunity. An area of opportunity is a continuous unit or interval of time, volume, or such
area in which more than one occurrence of an event can occur. Examples are the surface
defects on a new refrigerator, the number of network failures in a day, and the number of fleas
on the body of a dog. When you have situations such as these, you can use the Poisson distri-
bution to calculate probabilities if
* You are interested in counting the number of times a particular event occurs in a given area
of opportunity. The area of opportunity is defined by time, length, surface area, and so
forth.
* The probability that an event occurs in a given area of opportunity is the same for all the
areas of opportunity.
* The number of events that occur in one area of opportunity is independent of the number
of events that occur in any other area of opportunity.
* The probability that two or more events will occur in an area of opportunity approaches
zero as the area of opportunity becomes smaller.
Consider the number of customers arriving during the lunch hour at a bank located in the
central business district in a large city. You are interested in the number of customers that arrive
each minute. Does this situation match the four properties of the Poisson distribution given
above? First, the event of interest is a customer arriving, and the given area of opportunity is
defined as a 1-minute interval. Will zero customers arrive, one customer arrive, two customers
arrive, and so on? Second, it is reasonable to assume that the probability that a customer arrives
during a 1-minute interval is the same as the probability for all the other 1-minute intervals.
Third, the arrival of one customer in any 1-minute interval has no effect on (that is, is statisti-
cally independent of ) the arrival of any other customer in any other 1-minute interval. Finally,
the probability that two or more customers will arrive in a given time period approaches zero as
the time interval becomes small. For example, the probability is virtually zero that two cus-
tomers will arrive in a time interval with a width of 1/100 second. Thus, you can use the
Poisson distribution to determine probabilities involving the number of customers arriving at
the bank in a 1-minute time interval during the lunch hour.

The Poisson distribution has one parameter, called (the Greek lowercase letter lambda),
which is the mean or expected number of events per unit. The variance of a Poisson distribution
is also equal to , and the standard deviation is equal to . The number of events, X, of the
Poisson random variable ranges from 0 to infinity ( ).
Equation (5.14) presents the mathematical expression for the Poisson distribution for com-
puting the probability of X events, given that events are expected.

POISSON PROBABILITY DISTRIBUTION

X
e
P( X ) = (5.14)
X!

where

P(X ) = the probability of X events in an area of opportunity

= expected number of events
e = mathematical constant approximated by 2.71828
X = number of events

To demonstrate the Poisson distribution, suppose that the mean number of customers who
arrive per minute at the bank during the noon-to-1 p.m. hour is equal to 3.0. What is the proba-
bility that in a given minute, exactly two customers will arrive? And what is the probability that
more than two customers will arrive in a given minute?
Using Equation (5.14) and = 3, the probability that in a given minute exactly two cus-
tomers will arrive is

3.0
e (3.0) 2 9
P( X = 2 ) = = = 0.2240
2! (2.71828)3 ( 2)

To determine the probability that in any given minute more than two customers will arrive,

P(X > 2) = P(X = 3) + P(X = 4) + + P(X = )

Because all the probabilities in a probability distribution must sum to 1, the terms on the right
side of the equation P(X > 2) also represent the complement of the probability that X is less
than or equal to 2 [that is, 1 P(X 2))]. Thus,

P(X > 2) = 1 P(X 2) = 1 [P(X = 0) + P(X = 1) + P(X = 2)]

Now, using Equation (5.14),

3.0
e ( 3.0 )0 e 3.0
(3.0 )1 e 3.0
(3.0 ) 2
P( X > 2 ) = 1 + +
0! 1! 2!
= 1 [0.0498 + 0.1494 + 0.2240 ]
=1 0.4232 = 0.5768

Thus, there is a 57.68% chance that more than two customers will arrive in the same minute.
To avoid computational drudgery involved in these computations, you can find Poisson
probabilities directly from Table E.7, a portion of which is reproduced in Table 5.6. Table E.7
provides the probabilities that the Poisson random variable takes on values of X = 0, 1, 2, . . . ,

for selected values of the parameter *. To find the probability that exactly two customers will
arrive in a given minute when the mean number of customers arriving is 3.0 per minute, you
can read the probability corresponding to the row X = 2 and column * = 3.0 from the table. The
result is 0.2240, as demonstrated in Table 5.6.

TAB LE 5 .6 *
Finding a Poisson X 2.1 2.2 .... 3.0
Probability for * = 3
0 .1225 .1108 .... .0498
1 .2572 .2438 .... .1494
2 .2700 .2681 .... .2240
3 .1890 .1966 .... .2240
4 .0992 .1082 .... .1680
5 .0417 .0476 .... .1008
6 .0146 .0174 .... .0504
7 .0044 .0055 .... .0216
8 .0011 .0015 .... .0081
9 .0003 .0004 .... .0027
10 .0001 .0001 .... .0008
11 .0000 .0000 .... .0002
12 .0000 .0000 .... .0001
Source: Table E.7.

You can also compute the Poisson probabilities given in Table E.7 by using Microsoft
Excel, as illustrated by the worksheet in Figure 5.4.

FIGURE 5.4
Microsoft Excel
worksheet for
computing Poisson
probabilities with * = 3

See Section E5.4 to create

this.
200 CHAPTER FIVE Some Important Discrete Probability Distributions

EX A MP LE 5 .5 COMPUTING POISSON PROBABILITIES

The number of work-related injuries per month in your manufacturing plant is known to follow a
Poisson distribution with a mean of 2.5 work-related injuries a month. What is the probability that
in a given month no work-related injuries occur? That at least one work-related injury occurs?
SOLUTION Using Equation (5.14) on page 198 with = 2.5 (or using Table E.7 or Microsoft
Excel), the probability that in a given month no work-related injuries occur is
2.5
e (2.5) 0 1
P( X = 0 ) = = = 0.0821
0! (2.71828 ) 2.5 (1)

The probability that there will be no work-related injuries in a given month is 0.0821 or 8.21%.
Thus,

P( X 1) = 1 P( X = 0 )
=1 0.0821
= 0.9179

The probability that there will be at least one work-related injury is 0.9179 or 91.79%.

PROBLEMS FOR SECTION 5.4

Learning the Basics c. two or more network errors will occur?
d. less than three network errors will occur?
PH Grade 5.30 Assume a Poisson distribution.
ASSIST a. If = 2.5, find P(X = 2). 5.34 The quality control manager of Marilyn s
SELF
b. If = 8.0, find P(X = 8). Cookies is inspecting a batch of chocolate-chip
Test
c. If = 0.5, find P(X = 1). cookies that has just been baked. If the produc-
d. If = 3.7, find P(X = 0). tion process is in control, the mean number of chip parts
per cookie is 6.0. What is the probability that in any partic-
PH Grade 5.31 Assume a Poisson distribution.
ular cookie being inspected
ASSIST a. If = 2.0, find P(X 2).
a. less than five chip parts will be found?
b. If = 8.0, find P(X 3).
b. exactly five chip parts will be found?
c. If = 0.5, find P(X 1).
c. five or more chip parts will be found?
d. If = 4.0, find P(X 1).
d. either four or five chip parts will be found?
e. If = 5.0, find P(X 3).
5.32 Assume a Poisson distribution with = 5.0. What is 5.35 Refer to Problem 5.34. How many cookies in a batch
the probability that of 100 should the manager expect to discard if company
a. X = 1? policy requires that all chocolate-chip cookies sold have at
b. X < 1? least four chocolate-chip parts?
c. X > 1? 5.36 The U.S. Department of Transportation maintains
d. X 1? statistics for mishandled bags per 1,000 airline passengers.
Applying the Concepts In 2005, Jet Blue had 4.06 mishandled bags per 1,000 pas-
sengers (extracted from M. Mullins, Out of Place, USA
5.33 Assume that the number of network errors experi- Today, March 24, 2006, p. 10A). What is the probability
enced in a day on a local area network (LAN) is distributed that in the next 1,000 passengers, Jet Blue will have
as a Poisson random variable. The mean number of net- a. no mishandled bags?
work errors experienced in a day is 2.4. What is the proba- b. at least one mishandled bag?
bility that in any given day c. at least two mishandled bags?
a. zero network errors will occur? d. Compare the results in (a) through (c) to those of Delta
b. exactly one network error will occur? in Problem 5.37 (a) through (c).

5.37 The U.S. Department of Transportation maintains 5.40 Refer to Problem 5.39. If you purchased a 2004 Kia,
statistics for mishandled bags per 1,000 airline passengers. what is the probability that the new car will have
In 2005, Delta had 7.09 mishandled bags per 1,000 passen- a. zero problems?
gers (extracted from M. Mullins, Out of Place, USA b. two or less problems?
Today, March 24, 2006, p. 10A). What is the probability c. Compare your answers in (a) and (b) to those for the
that in the next 1,000 passengers, Delta will have Lexus in Problem 5.39 (b) and (c).
a. no mishandled bags?
b. at least one mishandled bag? 5.41 In 2005, both Lexus and Kia improved their perfor-
c. at least two mishandled bags? mance. Lexus had 0.81 problems per car, and Korea s Kia
d. Compare the results in (a) through (c) to those of Jet had 1.40 problems per car (S. S. Carty, Toyota Comes Out
Blue in Problem 5.36 (a) through (c). on Top Again in Quality Study, USA Today, May 19, 2005,
p. 3B). If you purchased a 2005 Lexus, what is the proba-
PH Grade 5.38 Based on past experience, it is assumed bility that the new car will have
ASSIST that the number of flaws per foot in rolls of grade a. zero problems?
2 paper follows a Poisson distribution with a b. two or less problems?
mean of 1 flaw per 5 feet of paper (0.2 flaw per foot). What c. Compare your answers in (a) and (b) to those for the
is the probability that in a 2004 Lexus in Problem 5.39 (b) and (c).
a. 1-foot roll, there will be at least 2 flaws?
b. 12-foot roll, there will be at least 1 flaw? 5.42 Refer to Problem 5.41. If you purchased a 2005 Kia,
c. 50-foot roll, there will be greater than or equal to 5 flaws what is the probability that the new car will have
and less than or equal to 15 flaws? a. zero problems?
b. two or less problems?
5.39 J.D. Power and Associates calculates and publishes c. Compare your answers in (a) and (b) to those for the
various statistics concerning car quality. The initial quality 2004 Kia in Problem 5.40 (a) and (b).
score measures the number of problems per new car sold.
For 2004 model cars, the Lexus had 0.87 problems per car. 5.43 A toll-free phone number is available from 9 a.m. to
Korea s Kia had 1.53 problems per car (D. Hakim, Hyundai 9 p.m. for your customers to register complaints about a
Near Top of a Quality Ranking, The New York Times, April product purchased from your company. Past history indi-
29, 2004, p. C8). Let the random variable X be equal to the cates that an average of 0.4 calls are received per minute.
number of problems with a newly purchased Lexus. a. What properties must be true about the situation
a. What assumptions must be made in order for X to be described here in order to use the Poisson distribution to
distributed as a Poisson random variable? Are these calculate probabilities concerning the number of phone
assumptions reasonable? calls received in a 1-minute period?
Making the assumptions as in (a), if you purchased a 2004 Assuming that this situation matches the properties dis-
Lexus, what is the probability that the new car will have cussed in (a), what is the probability that during a 1-minute
b. zero problems? period
c. two or less problems? b. zero phone calls will be received?
d. Give an operational definition for problem. Why is the c. three or more phone calls will be received?
operational definition important in interpreting the ini- d. What is the maximum number of phone calls that will
tial quality score? be received in a 1-minute period 99.99% of the time?

5.5 HYPERGEOMETRIC DISTRIBUTION

Both the binomial distribution and the hypergeometric distribution are concerned with the
number of successes in a sample containing n observations. One of the differences in these two
probability distributions is in the way that the samples are selected. For the binomial distribu-
tion, the sample data are selected with replacement from a finite population or without replace-
ment from an infinite population. Thus, the probability of success, p, is constant over all obser-
vations, and the outcome of any particular observation is independent of any other. For the
hypergeometric distribution, the sample data are selected without replacement from a finite
population. Thus, the outcome of one observation is dependent on the outcomes of the previous
observations.

Consider a population of size N. Let A represent the total number of successes in the pop-
ulation. The hypergeometric distribution is then used to find the probability of X successes in a
sample of size n, selected without replacement. Equation (5.15) presents the mathematical
expression of the hypergeometric distribution for finding X successes, given a knowledge of n,
N, and A.

HYPERGEOMETRIC DISTRIBUTION
A N A
X n X
P( X ) = (5.15)
N
n
where

P(X) = the probability of X successes, given knowledge

of n, N, and A
n = sample size
N = population size
A = number of successes in the population
N A = number of failures in the population
X = number of successes in the sample
A
= ACX (see Equation (5.10) on p. 190)
X

The number of successes in the sample, represented by X, cannot be greater than the
number of successes in the population, A, or the sample size, n. Thus, the range of the hyper-
geometric random variable is limited to the sample size or to the number of successes in the
population, whichever is smaller.
Equation (5.16) defines the mean of the hypergeometric distribution, and Equation (5.17)
defines the standard deviation.

MEAN OF THE HYPERGEOMETRIC DISTRIBUTION

nA
= E( X ) = (5.16)
N

STANDARD DEVIATION OF THE HYPERGEOMETRIC DISTRIBUTION

nA( N A) N n
= 2 (5.17)
N N 1

N n
In Equation (5.17), the expression is a finite population correction factor that
N 1
results from sampling without replacement from a finite population.
To illustrate the hypergeometric distribution, suppose that you are forming a team of
8 executives from different departments within your company. Your company has a total of
30 executives, and 10 of these people are from the finance department. If members of the team
are to be selected at random, what is the probability that the team will contain 2 executives
from the finance department? Here, the population of N = 30 executives within the company

is finite. In addition, A = 10 are from the finance department. A team of n = 8 members is to

be selected.
Using Equation (5.15),

10 20
2 6
P( X = 2 ) =
30
8
10! ( 20)!
2!(8)! (6)!(14 )!
=
30!
8!(22)!
= 0.298

Thus, the probability that the team will contain two members from the finance department is
0.298, or 29.8%.
Such computations can become tedious, especially as N gets large. However, you can com-
pute the probabilities by using Microsoft Excel. Figure 5.5 presents a Microsoft Excel work-
sheet for the team-formation example, where the number of executives from the finance
department (that is, the number of successes in the sample) can be equal to 0, 1, 2, . . . , 8.

FIGURE 5.5
Microsoft Excel
worksheet for the team
member example

See Section E5.5 to create

this.

PROBLEMS FOR SECTION 5.5

Learning the Basics Applying the Concepts
PH Grade 5.44 Determine the following: PH Grade5.46 An auditor for the Internal Revenue
ASSIST a. If n = 4, N = 10, and A = 5, find P(X = 3). ASSIST Service is selecting a sample of 6 tax returns for
b. If n = 4, N = 6, and A = 3, find P(X = 1). SELF an audit. If 2 or more of these returns are
c. If n = 5, N = 12, and A = 3, find P(X = 0). Test improper, the entire population of 100 tax
d. If n = 3, N = 10, and A = 3, find P(X = 3). returns will be audited. What is the probability that the
entire population will be audited if the true number of
improper returns in the population is
PH Grade 5.45 Referring to Problem 5.44, compute the a. 25?
ASSIST mean and standard deviation for the hyper- b. 30?
geometric distributions described in (a) through (d). c. 5?

d. 10? d. What are your answers to (a) through (c) if 6 cars being
e. Discuss the differences in your results, depending on the shipped are SUVs?
true number of improper returns in the population.
5.49 A state lottery is conducted in which 6 winning
5.47 The dean of a business school wishes to form an
numbers are selected from a total of 54 numbers. What is
executive committee of 5 from among the 40 tenured fac-
the probability that if 6 numbers are randomly selected,
ulty members at the school. The selection is to be random,
a. all 6 numbers will be winning numbers?
and at the school there are 8 tenured faculty members in
b. 5 numbers will be winning numbers?
accounting. What is the probability that the committee will
c. none of the numbers will be winning numbers?
contain
d. What are your answers to (a) through (c) if the 6 win-
a. none of them?
ning numbers are selected from a total of 40 numbers?
b. at least 1 of them?
c. not more than 1 of them?
5.50 In a shipment of 15 sets of golf clubs, 3 are left-
d. What is your answer to (a) if the committee consists of
handed. If 4 sets of golf clubs are selected, what is the prob-
7 members?
ability that
5.48 From an inventory of 30 cars being shipped to a local a. exactly 1 is left-handed?
automobile dealer, 4 are SUVs. What is the probability that b. at least 1 is left-handed?
if 4 cars arrive at a particular dealership, c. no more than 2 are left-handed?
a. all 4 are SUVs? d. What is the mean number of left-handed sets of golf
b. none are SUVs? clubs that you would expect to find in the sample of
c. at least 1 is an SUV? 4 sets of golf clubs?

5.6 (CD-ROM Topic) USING THE POISSON DISTRIBUTION

TO APPROXIMATE THE BINOMIAL DISTRIBUTION
Under certain circumstances, the Poisson distribution can be used to approximate the binomial
distribution. To study this topic, go to the section5.6.pdf file located on the CD-ROM that
accompanies this book.

SUMMARY
In this chapter, you have studied mathematical expectation, Is there a fixed number of observations, n, each of
the covariance, and the development and application of the which is classified as success or failure? Or is there an
binomial, Poisson, and hypergeometric distributions. In the area of opportunity? If there is a fixed number of obser-
Using Statistics scenario, you learned how to calculate prob- vations, n, each of which is classified as success or fail-
abilities from the binomial distribution concerning the ure, you use the binomial or hypergeometric distribu-
observation of tagged invoices in the accounting information tion. If there is an area of opportunity, you use the
system used by the Saxon Home Improvement Company. In Poisson distribution.
the following chapter, you will study several important con- In deciding whether to use the binomial or hypergeo-
tinuous distributions including the normal distribution. metric distribution, is the probability of success constant
To help decide what probability distribution to use for a over all trials? If yes, you can use the binomial distribu-
particular situation, you need to ask the following questions: tion. If no, you can use the hypergeometric distribution.

KEY E Q U AT I O N S
Expected Value, , of a Discrete Random Variable Variance of a Discrete Random Variable
N N
2
= E( X ) = X i P( X i ) (5.1) = [Xi E ( X )]2 P ( X i ) (5.2)
i =1 i =1

Standard Deviation of a Discrete Random Variable Binomial Distribution

n!
N P( X ) = p X (1 p)n X
(5.11)
= 2
= [Xi E ( X )]2 P ( X i ) X !( n X )!
(5.3)
i =1
Mean of the Binomial Distribution
Covariance
N = E(X ) = np (5.12)
XY = [Xi E ( X )][Yi E (Y )]P ( X iYi ) (5.4)
i =1
Standard Deviation of the Binomial Distribution
Expected Value of the Sum of Two Random Variables
2
= = Var( X ) = np(1 p) (5.13)
E(X + Y) = E(X) + E(Y) (5.5)

Poisson Distribution
Variance of the Sum of Two Random Variables
X
Var( X + Y ) = 2
= 2
+ 2
+2 e
X +Y X Y XY (5.6) P( X ) = (5.14)
X!

Standard Deviation of the Sum of Two Random Variables Hypergeometric Distribution

2
X +Y = X +Y (5.7) A N A
X n X
P( X ) = (5.15)
Portfolio Expected Return N
n
E(P) = wE(X) + (1 w)E(Y) (5.8)
Mean of the Hypergeometric Distribution
Portfolio Risk
nA
= E( X ) = (5.16)
p = w 2 2X + (1 w) 2 2
Y + 2w(1 w) XY (5.9) N

Standard Deviation of the Hypergeometric Distribution

Combinations

n! nA( N A) N n
nCX = (5.10) = 2 (5.17)
X !( n X )! N N 1

KEY TERMS
area of opportunity 197 mathematical model 189 standard deviation of a discrete
binomial distribution 189 Poisson distribution 197 random variable 182
covariance, XY 184 portfolio 186 standard deviation of the sum of two
expected value of the sum of two portfolio expected return 186 random variables 186
random variables 186 portfolio risk 186 variance of a discrete random
expected value, , of a discrete random probability distribution for a discrete variable 182
variable 181 random variable 180 variance of the sum of two random
finite population correction factor 202 rule of combinations 190 variables 186
hypergeometric distribution 201

CHAPTER REVIEW PROBLEMS

Checking Your Understanding tomer-service representative. According to the Center for
5.51 What is the meaning of the expected value of a prob- Client Retention, 40% of all callers to automated customer-
ability distribution? service systems automatically opt to go to a live operator
when given the chance (J. Spencer, In Search of the
5.52 What are the four properties that must be present in Operator, The Wall Street Journal, May 8, 2002, p. D1).
order to use the binomial distribution? If 10 independent callers contact an automated cus-
5.53 What are the four properties that must be present in tomer-service system, what is the probability that
order to use the Poisson distribution? a. 0 will automatically opt to talk to a live operator?
b. exactly 1 will automatically opt to talk to a live operator?
5.54 When do you use the hypergeometric distribution c. 2 or less will automatically opt to talk to a live operator?
instead of the binomial distribution? d. all 10 will automatically opt to talk to a live operator?
e. If all 10 automatically opt to talk to a live operator, do
Applying the Concepts you think that the 40% figure given in the article applies
PH Grade 5.55 Event insurance allows promoters of sport- to this particular system? Explain.
ASSIST ing and entertainment events to protect them-
5.58 One theory concerning the Dow Jones Industrial
selves from financial losses due to uncontrollable
Average is that it is likely to increase during U.S. presiden-
circumstances such as rain-outs. For example, each spring,
tial election years. From 1964 through 2004, the Dow
Cincinnati s Downtown Council puts on the Taste of
Jones Industrial Average increased in 9 of the 11 U.S. pres-
Cincinnati. This is a rainy time of year in Cincinnati, and the
idential election years. Assuming that this indicator is a
chance of receiving an inch or more of rain during a spring
random event with no predictive value, you would expect
weekend is about one out of four. An article in the
that the indicator would be correct 50% of the time.
Cincinnati Enquirer, by Jim Knippenberg ( Chicken Pox
a. What is the probability of the Dow Jones Industrial
Means 3 Dog Night Remedy, Cincinnati Enquirer, May
Average increasing in 9 or more of the 11 U.S. presiden-
28, 1997, p. E1), gave the details for an insurance policy
tial election years if the true probability of an increase in
purchased by the Downtown Council. The policy would pay
the Dow Jones Industrial Average is 0.50?
$100,000 if it rained more than an inch during the weekend
b. Read Problem 5.56 and note that the Dow Jones
festival. The cost of the policy was reported to be $6,500.
Industrial Average increased in 74% of the years stud-
a. Determine whether you believe that these dollar
ied. What is the probability of the Dow Jones Industrial
amounts are correct. (Hint: Calculate the expected value
Average increasing in 9 of the 11 U.S. presidential elec-
of the profit to be made by the insurance company.)
tion years if the probability of an increase in the Dow
b. Assume that the dollar amounts are correct. Is this pol-
Jones Industrial Average is 0.74?
icy a good deal for Cincinnati s Downtown Council?
5.59 Priority Mail is the U.S. Postal Service s alternative
PH Grade 5.56 Between 1872 and 2000, stock prices rose in
to commercial express mail companies such as FedEx. An
ASSIST 74% of the years (M. Hulbert, The Stock Market
article in The Wall Street Journal presented some interest-
Must Rise in 2002? Think Again, The New York
ing conclusions comparing Priority Mail shipments with
Times, December 6, 2001, Business, p. 6). Based on this
the much less expensive first-class shipments (R. Brooks,
information, and assuming a binomial distribution, what do
New Data Reveal Priority Mail Is Slower Than a Stamp,
you think the probability is that the stock market will rise
The Wall Street Journal, May 29, 2002, p. D1). When com-
a. next year?
paring shipments intended for delivery in three days, first-
b. the year after next?
class deliveries failed to deliver on time 19% of the time,
c. in four of the next five years?
while Priority Mail failed 33% of the time. Note that at the
d. in none of the next five years?
time of the article, first-class deliveries started as low as
e. For this situation, what assumption of the binomial dis-
$0.34, and Priority Mail started at $3.50.
tribution might not be valid?
If 10 items are to be shipped first-class to 10 different
5.57 The mean cost of a phone call handled by an auto- destinations claimed to be in a three-day delivery location,
mated customer-service system is $0.45. The mean cost of a what is the probability that
phone call passed on to a live operator is $5.50. However, a. 0 items will take more than three days?
as more and more companies have implemented automated b. exactly 1 will take more than three days?
systems, customer annoyance with such systems has grown. c. 2 or more will take more than three days?
Many customers are quick to leave the automated system d. What are the mean and the standard deviation of the
when given an option such as Press zero to talk to a cus- probability distribution?

5.60 Refer to Problem 5.59. If the shipments are made 5.64 In a survey conducted by the Council for Marketing
using Priority Mail, what is the probability that and Opinion Research (CMOR), a national nonprofit
a. 0 items will take more than three days? research industry trade group based in Cincinnati, 1,628 of
b. exactly 1 will take more than three days? 3,700 adults contacted in the United States refuse to partic-
c. 2 or more will take more than three days? ipate in phone surveys (S. Jarvis, CMOR Finds Survey
d. What are the mean and the standard deviation of the Refusal Rate Still Rising, Marketing News, February 4,
probability distribution? 2002, p. 4). Suppose that you are to randomly call 10 adults
e. Compare the results of (a) through (c) to those of in the United States and ask them to participate in a phone
Problem 5.59 (a) through (c). survey. Using the results of the CMOR study, what is the
probability that
5.61 Cinema advertising is increasing. Normally 60 to a. all 10 will refuse?
90 seconds long, these advertisements are longer and more b. exactly 5 will refuse?
extravagant, and they tend to have more captive audiences c. at least 5 will refuse?
than television advertisements. Thus, it is not surprising d. less than 5 will refuse?
that the recall rates for viewers of cinema advertisements e. less than 5 will agree to be surveyed?
are higher than those for television advertisements. f. What is the expected number of people who will refuse
According to survey research conducted by the ComQUEST to participate? Explain the practical meaning of this
division of BBM Bureau of Measurement in Toronto, the number.
probability a viewer will remember a cinema advertisement
is 0.74, whereas the probability a viewer will remember a 5.65 Credit card companies are increasing their revenues
30-second television advertisement is 0.37 (N. Hendley, by raising the late fees charged to their customers.
Cinema Advertising Comes of Age, Marketing Magazine, According to a study by cardweb.com, late fees represent
May 6, 2002, p. 16). the third largest revenue source for card companies, after
a. Is the 0.74 probability reported by the BBM Bureau of interest charges and payments from the merchants who
Measurement best classified as a priori classical proba- accept their cards. In the preceding year, 58% of all credit
bility, empirical classical probability, or subjective card customers had had to pay late fees (R. Lieber, Credit-
probability? Card Firms Collect Record Levels of Late Fees, The Wall
b. Suppose that 10 viewers of a cinema advertisement are Street Journal, May 21, 2002, p. D1).
randomly sampled. Consider the random variable If a random sample of 20 credit card holders is selected,
defined by the number of viewers who recall the adver- what is the probability that
tisement. What assumptions must be made in order to a. 0 had to pay a late fee?
assume that this random variable is distributed as a bino- b. no more than 5 had to pay late fees?
mial random variable? c. more than 10 had to pay late fees?
c. Assuming that the number of viewers who recall the cin- d. What assumptions did you have to make to answer (a)
ema advertisement is a binomial random variable, what through (c)?
are the mean and standard deviation of this distribution?
d. Based on your answer to (c), if none of the viewers can 5.66 One of the retail industry s biggest frustrations is
recall the ad, what can be inferred about the 0.74 proba- customers who abuse the return and exchange policies
bility given in the article? (S. Kang, New Return Policy: Retailers Say No to
5.62 Refer to Problem 5.61. Compute the probability that Serial Exchangers, The Wall Street Journal, November
of the 10 viewers of the cinema advertisement, 29, 2004, pp. B1, B3). In a recent year, returns were
a. exactly 0 can recall the advertisement. 13% of sales in department stores. Consider a sample of
b. all 10 can recall the advertisement. 20 customers who make a purchase at a department
c. more than half can recall the advertisement. store. Use the binomial model to answer the following
d. 8 or more can recall the advertisement. questions:
a. What is the expected value, or mean, of the binomial
5.63 Refer to Problem 5.61. For television advertisements, distribution?
using the given probability of recall, 0.37, compute the b. What is the standard deviation of the binomial distribu-
probability that of the 10 viewers, tion?
a. exactly 0 can recall the advertisement. c. What is the probability that none of the 20 customers
b. all 10 can recall the advertisement. will make a return?
c. more than half can recall the advertisement. d. What is the probability that no more than 2 of the cus-
d. 8 or more can recall the advertisement. tomers will make a return?
e. Compare the results of (a) through (d) to those of e. What is the probability that 3 or more of the customers
Problem 5.62 (a) through (d). will make a return?

5.67 Refer to Problem 5.66. In the same year, returns 5.70 Worldwide golf ball sales total more than $1 bil-
were 1% of sales in grocery stores. lion annually. One reason for such a large number of golf
a. What is the expected value, or mean, of the binomial ball purchases is that golfers lose them at a rate of 4.5 per
distribution? 18-hole round ( Snapshots, usatoday.com, January 29,
b. What is the standard deviation of the binomial distribu- 2004). Assume that the number of golf balls lost in
tion? an 18-hole round is distributed as a Poisson random
c. What is the probability that none of the 20 customers variable.
will make a return? a. What assumptions need to be made so that the number
d. What is the probability that no more than 2 of the cus- of golf balls lost in an 18-hole round is distributed as a
tomers will make a return? Poisson random variable?
e. What is the probability that 3 or more of the customers Making the assumptions given in (a), what is the probability
will make a return? that
f. Compare the results of (a) through (e) to those of b. 0 balls will be lost in an 18-hole round?
Problem 5.66 (a) through (e). c. 5 or less balls will be lost in an 18-hole round?
d. 6 or more balls will be lost in an 18-hole round?
5.68 One theory concerning the S&P 500 index is that if
it increases during the first five trading days of the year, it 5.71 A study of the home pages of Fortune 500 companies
is likely to increase during the entire year. From 1950 reports that the mean number of bad links per home page is
through 2005, the S&P 500 index had these early gains in 0.4 and the mean number of spelling errors per home page
35 years. In 30 of these 35 years, the S&P 500 index is 0.16 (N. Tamimi, M. Rajan, and R. Sebastianella,
increased. Assuming that this indicator is a random event Benchmarking the Home Pages of Fortune 500
with no predictive value, you would expect that the indica- Companies, Quality Progress, July 2000). Use the Poisson
tor would be correct 50% of the time. What is the probabil- distribution to find the probability that a randomly selected
ity of the S&P 500 index increasing in 30 or more years if home page will contain
the true probability of an increase in the S&P 500 index is a. exactly 0 bad links.
a. 0.50? b. 5 or more bad links.
b. 0.70? c. exactly 0 spelling errors.
c. 0.90? d. 10 or more spelling errors.
d. Based on the results of (a) through (c), what do you
think is the probability that the S&P 500 index will 5.72 Mega Millions is one of the most popular lottery
increase if there is an early gain in the first five trading games in the United States. Participating states in Mega
days of the year? Explain. Millions are Georgia, Illinois, Maryland, Massachusetts,
Michigan, New Jersey, New York, Ohio, and Virginia.
5.69 Spurious correlation refers to the apparent relation- Rules for playing and the list of prizes are given below
ship between variables that either have no true relationship ( Win Megamoney Playing Ohio s Biggest Jackpot Game,
or are related to other variables that have not been mea- Ohio Lottery Headquarters, 2002):
sured. One widely publicized stock market indicator in the
United States that is an example of spurious correlation is
Rules:
the relationship between the winner of the National
Select five numbers from a pool of numbers from 1
Football League Super Bowl and the performance of the
to 52 and one Mega Ball number from a second
Dow Jones Industrial Average in that year. The indicator
pool of numbers from 1 to 52.
states that when a team representing the National Football
Each wager costs $1.
Conference wins the Super Bowl, the Dow Jones Industrial
Average will increase in that year. When a team represent-
ing the American Football Conference wins the Super Prizes:
Bowl, the Dow Jones Industrial Average will decline in that Match all five numbers + Mega Ball win jackpot
year. Since the first Super Bowl was held in 1967 through (minimum of $10,000,000)
2005, the indicator has been correct 32 out of 39 times. Match all five numbers win $175,000
Assuming that this indicator is a random event with no pre- Match four numbers + Mega Ball win $5,000
dictive value, you would expect that the indicator would be Match four numbers win $150
correct 50% of the time. Match three numbers + Mega Ball win $150
a. What is the probability that the indicator would be cor- Match two numbers + Mega Ball win $10
rect 32 or more times in 39 years? Match three numbers win $7
b. What does this tell you about the usefulness of this indi- Match one number + Mega Ball win $3
cator? Match Mega Ball win $2

Find the probability of winning i. nothing.

a. the jackpot. j. All stores selling Mega Millions tickets are required to
b. the $175,000 prize. (Note that this requires matching all have a brochure that gives complete game rules and
five numbers but not matching the Mega Ball.) probabilities of winning each prize (the probability of
c. $5,000. having a losing ticket is not given). The slogan for all
d. $150. lottery games in the state of Ohio is Play Responsibly.
e. $10. Odds Are, You ll Have Fun. Do you think Ohio s slogan
f. $7. and the requirement of making available complete game
g. $3. rules and probabilities of winning is an ethical approach
h. $2. to running the lottery system?

Managing the Springville Herald

The Herald marketing department is seeking to increase EXERCISES
home-delivery sales through an aggressive direct-marketing Review the internal data and propose a reasonable time (to
campaign that includes mailings, discount coupons, and the nearest quarter hour) to guarantee delivery. To help
telephone solicitations. Feedback from these efforts indi- explore the effects of your choice, calculate the following
cates that getting their newspapers delivered early in the probabilities:
morning is a very important factor for both prospective as SH5.1 If a sample of 50 customers is selected on a given
well as existing subscribers. After several brainstorming day, what is the probability, given your selected
sessions, a team consisting of members from the marketing delivery time, that
and circulation departments decided that guaranteeing a. less than 3 customers will receive a free news-
newspaper delivery by a specific time could be an important paper?
selling point in retaining and getting new subscribers. The b. 2, 3, or 4 customers will receive a free newspaper?
team concluded that the Herald should offer a guarantee c. more than 5 customers will receive a free
that customers will receive their newspapers by a certain newspaper?
time or else that day s issue is free. SH5.2 Consider the effects of improving the newspaper
To assist the team in setting a guaranteed delivery time, delivery process so that the percentage of newspa-
Al Leslie, the research director, noted that the circulation pers that go undelivered by your guaranteed deliv-
department had data that showed the percentage of newspa- ery time decreases by 2%. If a sample of 50 cus-
pers yet undelivered every quarter hour from 6 a.m. to tomers is selected on a given day, what is the
8 a.m. Jan Shapiro remembered that customers were asked on probability, given your selected delivery time (and
their subscription forms at what time they would be looking the delivery improvement), that
for their copy of the Herald to be delivered. These data were a. less than 3 customers will receive a free news-
subsequently combined and posted on an internal Herald paper?
Web page. (See Circulation_Data.htm in the HeraldCase b. 2, 3, or 4 customers will receive a free newspaper?
folder on the Student CD or go to www.prenhall.com/ c. more than 5 customers will receive a free
HeraldCase/Circulation_Data.htm). newspaper?

Web Case
Apply your knowledge about expected value and the covari- 2. What subjective data influence the rate-of-return analy-
ance in this continuing Web Case from Chapters 3 and 4. ses of these funds? Could EndRun be accused of making
Visit the EndRun Bulls and Bears Web page, at false and misleading statements? Why or why not?
www.prenhall.com/Springville/ER_BullsandBears.htm 3. The expected-return analysis seems to show that the
(or open the Web page file from the Student CD-ROM Worried Bear Fund has a greater expected return than the
Web Case folder), read the claims, and examine the sup- Happy Bull Fund. Should a rational investor then never
porting data. Then answer the following: invest in the Happy Bull Fund? Why or why not?
1. Are there any catches about the claims the Web site
makes for the rate of return of Happy Bull and Worried
Bear Funds?

REFERENCES
1. Bernstein, P. L., Against the Gods: The Remarkable 5. Microsoft Excel 2007 (Redmond, WA: Microsoft Corp.,
Story of Risk (New York: Wiley, 1996). 2007).
2. Emery, D. R., J. D. Finnerty, and J. D. Stowe, Corporate 6. Moscove, S. A., M. G. Simkin, and A. Bagranoff, Core
Financial Management, 3rd ed. (Upper Saddle River, Concepts of Accounting Information Systems, 8th ed.
NJ: Prentice Hall, 2007). (New York: Wiley, 2003).
3. Kirk, R. L., ed., Statistical Issues: A Reader for the
Behavioral Sciences (Belmont, CA: Wadsworth, 1972).
4. Levine, D. M., P. Ramsey, and R. Smidt, Applied Statistics
for Engineers and Scientists Using Microsoft Excel and
Minitab (Upper Saddle River, NJ: Prentice Hall, 2001).

Excel Companion
to Chapter 5
E5.1 COMPUTING THE EXPECTED Covariance and Portfolio Management procedure or by
VALUE OF A DISCRETE making entries in the Portfolio.xls workbook.
RANDOM VARIABLE
You compute the expected value of a discrete random Using PHStat2 Covariance
variable by making entries in the Discrete worksheet of and Portfolio Management
the Expected Value.xls workbook. This worksheet uses the
Open the workbook in which you want your probabilities
SUM and SQRT (square root) functions to calculate its
worksheet to be placed. Select PHStat * Probability &
statistics.
Prob. Distributions * Covariance and Portfolio
Figure E5.1 shows a completed worksheet using the
Management. In the Covariance and Portfolio Management
mortgage probability distribution of Table 5.1 on page 181.
dialog box (shown below), enter a value for the Number of
To adapt this worksheet to other problems that have more
Outcomes, enter a title as the Title, click Portfolio
or less than seven outcomes, first select the cell range
Management Analysis, and click OK. In the worksheet cre-
A5:E5. To add table rows, right-click and select Insert. (If
ated by PHStat2, enter the values for the probabilities and
a box of options appears, click Shift cells down and then
click OK.) Then, copy the formulas in cell range C4:E4
down through the new table rows and enter the new X and
P(X ) values in columns A and B.
To delete table rows, right-click and select Delete. (If a
box of options appears, click Shift cells up and then click
OK.) Enter a corrected list of X values, starting with 1 in cell
A5 in column A, and enter the new P(X ) values in column B.

E5.2 COMPUTING PORTFOLIO

EXPECTED RETURN AND
PORTFOLIO RISK
You compute the portfolio expected return and the portfo-
lio risk of two investments by either using the PHStat2

FIGURE E5.1 Discrete worksheet

outcomes in the cell range B4:D6 and the weight (w)

assigned to X in cell B8.

Using the Portfolio Worksheet

Open to the Portfolio worksheet of the Portfolio.xls work- FIGURE E5.3 Portfolio worksheet calculations area
book (see Figure E5.2). This worksheet already contains
the entries for the estimated returns for the investment data
of Table 5.4. To adapt this worksheet to other problems,
change the probabilities and outcomes data and the Weight
E5.3 COMPUTING BINOMIAL
Assigned to X value. If your problem has more or fewer PROBABILITIES
than three outcomes, first select row 5 and then add or You compute binomial probabilities either by using the
delete rows one at a time by right-clicking row 5 and click- PHStat2 Binomial procedure or by making entries in the
ing either Insert or Delete. (If you inserted rows, you also Binomial.xls workbook.
have to copy formulas down to those new rows.)
The worksheet features the SUMPRODUCT function,
which computes the sum of the products of corresponding
elements of two cell ranges. In this worksheet, the cell
Using PHStat2 Binomial
range is always the set of P(XiYi) probabilities. To compute Open the workbook in which you want your probabilities
the variance, standard deviation, and covariance, the work- worksheet to be placed. Select PHStat * Probability &
sheet uses a calculation area in columns F through J, shown Prob. Distributions * Binomial. In the Binomial
in Figure E5.3. This area was created by entering the fol- Probability Distribution dialog box (shown at the top of
lowing row 4 formulas: F4: =C4 - $B$11, G4: =D4 - page 213), enter the Sample Size, the Probability of
$B$12, H4: =F4^2, I4: =G4^2, and J4: =F4*G4 and then Success, and the range of the outcomes. Enter a title as the
copying them down to rows 5 and 6. Title, click Cumulative Probabilities, and then click OK.

FIGURE E5.2 Portfolio worksheet

The worksheet features the BINOMDIST(X, n, p,

cumulative) function, in which X is the number of suc-
cesses, n is the sample size, p is the probability of success,
and cumulative is True or False. When cumulative is True,
the function computes the probability of X or fewer suc-
cesses; when cumulative is False, the function computes
the probability of exactly X successes.

Forum Click the ALTERNATE TECHNIQUES link to learn

how to create a table of cumulative probabilities,
similar to the PHStat2 output option.

E5.4 COMPUTING POISSON

PROBABILITIES
You compute Poisson probabilities either by using the
PHStat2 Poisson procedure or by making entries in the
Poisson.xls workbook.
You can create your version of the Binomial worksheet
shown in Figure E5.4 by entering 0 as the Outcomes From
value and 4 as the Outcomes To value. Using PHStat2 Poisson
Open the workbook in which you want your probabilities
Using the Binomial Worksheet worksheet to be placed. Select PHStat * Probability &
Open to the Binomial worksheet of the Binomial.xls work- Prob. Distributions * Poisson. In the Poisson Probability
book (see Figure E5.4). This worksheet already contains Distribution dialog box (shown below), enter the
the entries for the tagged orders example of Section 5.3. To Average/Expected No. of Successes, enter a title as the
adapt this worksheet to other problems, change the Sample Title, click Cumulative Probabilities, and then click OK.
size and Probability of success values in cells B4 and B5.
If your problem has a sample size other than 4, first select
row 15 and then add or delete rows one at a time by right-
clicking row 15 and clicking either Insert or Delete and
adjusting the X values in column A. (If you inserted rows,
you also have to copy formulas down to those new rows.)

Using the Poisson Worksheet

Open to the Poisson worksheet of the Poisson.xls workbook
(see Figure E5.5 on page 214). This worksheet already
contains the entries for the bank customer arrivals problem
of Section 5.4. To adapt this worksheet to other problems,
change the Average/Expected number of successes value
FIGURE E5.4 Binomial worksheet in cell E4.

You can create your version of the Hypergeometric

worksheet shown in Figure E5.6 by entering 8 as the
Sample Size, 10 as the No. of Successes in Population,
and 30 as the Population Size.

Using the Hypergeometric Worksheet

Open to the Hypergeometric worksheet of the
Hypergeometric.xls workbook (see Figure E5.6). This work-
FIGURE E5.5 Poisson worksheet sheet already contains the entries for the team formation
problem of Section 5.5. To adapt this worksheet to other
problems, change the Sample size, No. of successes in
The worksheet features the POISSON(X, lambda,
population, and Population size in the cell range B4:B6.
cumulative) function, in which X is the number of suc-
If your problem has a sample size other than 8, first select
cesses, lambda is the average or expected number of suc- row 11 and then add or delete rows one at a time by right-
cesses, and cumulative is True or False. When cumulative clicking and clicking either Insert or Delete and adjusting
is True, the function computes the probability of X or the X values in column A. (If you inserted rows, you also
fewer successes; when cumulative is False, the function
have to copy formulas down to those new rows.)
computes the probability of exactly X successes.
The worksheet features the HYPERGEOMDIST(X,
n, A, N ) function, in which X is the number of successes,
n is the sample size, A is the number of successes in the
E5.5 COMPUTING HYPERGEOMETRIC population, and N is the population size.
PROBABILITIES
You compute hypergeometric probabilities either by using
the PHStat2 Hypergeometric procedure or by making
entries in the Hypergeometric.xls workbook.

Using PHStat2 Hypergeometric

Open the workbook in which you want your probabilities
worksheet to be placed. Select PHStat * Probability &
Prob. Distributions * Hypergeometric. In the
Hypergeometric Probability Distribution dialog box
(shown at right), enter the Sample Size, the No. of
Successes in Population, and the Population Size. Enter a
title as the Title, and then click OK. FIGURE E5.6 Hypergeometric worksheet
E5.6: Creating Histograms for Discrete Probability Distributions 215

E5.6 CREATING HISTOGRAMS (X) axis title, and enter P(X) as the Value (Y) axis title.
FOR DISCRETE PROBABILITY Use the formatting settings for the Axes, Gridlines,
Legend, Data Labels, and Data Table tabs that are given
DISTRIBUTIONS
in the Creating Charts (97 2003) part of Section E2.2 on
You can create histograms for discrete probability distribu- page 79.
tions using Excel charting features and your copy of the
Binomial, Poisson, or Hypergeometric worksheets dis- Because the histogram is for a discrete probability dis-
cussed in the previous three sections. tribution, the histogram bars should appear as spikes. To
The PHStat2 Binomial, Poisson, and Hypergeometric narrow the histogram bars to approximate spikes, right-
procedures can create a histogram for you when you click click one of the histogram bars. (You will see a ToolTip
the Histogram output option of those procedures. that begins with Series Frequency when your mouse is
To create a histogram, open to your discrete probabil- properly positioned.) Click Format Data Series in the
ity worksheet and use the appropriate set of instructions. shortcut menu. In the Format Data Series dialog box, click
the Options tab, change the value of Gap width to 500,
and click OK.
Creating Histograms (97 2003)
Begin the Chart Wizard (see Section E2.2) and make the
following entries and choices in the step dialog boxes: Creating Histograms (2007)
Step 1 Click the Standard Types tab and then click Select the cell range that contains the P(X ) values (exclu-
Column as the Chart type. Select the first Chart sub- sive of the P(X ) label). Then select Insert * Column *
type, labeled Clustered Column when selected. Clustered Column. Right-click the chart that appears and
click Edit Data Source in the shortcut menu. In the Edit
Step 2 Click the Data Range tab. Enter the cell range of
Data Source dialog box, click the Edit button under the
the P(X ) values as the Data range and click the Columns
Horizontal (Categories) Axis Labels heading, enter the
option in the Series in group. Click the Series tab. Enter the
cell range of the X values (exclusive of the X label) as a for-
cell range of the X values as a formula in the Category (X)
mula in the form =SheetName!CellRange, and click OK.
axis labels box, using the Sheetname!CellRange format. For
Click OK (in the Edit Data Source dialog box) to complete
the Binomial worksheet of Figure E5.4, enter B14:B18 as
this task. Relocate your chart to a chart sheet and cus-
the Data range and =Binomial!A14:A18 as the Category
tomize your chart by using the instructions in Creating
(X) axis labels. For the Poisson worksheet of Figure E5.5,
Charts (2007) in Section E2.2 on page 80.
enter B8:B28 as the Data range and =Poisson!A8:A28 as
For the Binomial worksheet of Figure E5.4, initially
the Category (X) axis labels. For the Hypergeometric
select B14:B18 and then enter =Binomial!A14:A18 as
worksheet of Figure E5.6, enter B10:B18 as the Data range
the Horizontal (Categories) Axis Labels. For the
and =Hypergeometric!A10:A18 as the Category (X) axis
Poisson worksheet of Figure E5.5, select B8:B28 and
labels.
then enter =Poisson!A8:A28. For the Hypergeometric
Step 3 Click the Titles tab. Enter a title as the Chart title worksheet of Figure E5.6, select B10:B18 and then enter
edit box, enter Number of Successes (X) as the Category =Hypergeometric!A10:A18.

Statistics for Managers Using Microsoft Excel, Fifth Edition, by David M. Levine, Mark L. Berenson, and Timothy C. Krehbiel. Published by Prentice Hall.
Copyright 2008 by Pearson Education, Inc.
Statistics for Managers Using Microsoft Excel, Fifth Edition, by David M. Levine, Mark L. Berenson, and Timothy C. Krehbiel. Published by Prentice Hall.
Copyright 2008 by Pearson Education, Inc.

Gemstone Spreadsheet
100% (1)
Gemstone Spreadsheet
10 pages
Tutorial 5: An Introduction To Asset Pricing Models
No ratings yet
Tutorial 5: An Introduction To Asset Pricing Models
49 pages
BIQS Training For Audit
50% (2)
BIQS Training For Audit
115 pages
07 - Requirements Analysis and Design Definition
No ratings yet
07 - Requirements Analysis and Design Definition
61 pages
The Metropolitan Century Understanding Urbanisation and Its Consequences Oecd Download
No ratings yet
The Metropolitan Century Understanding Urbanisation and Its Consequences Oecd Download
39 pages
Singer Prebisch Thesis Explained
100% (2)
Singer Prebisch Thesis Explained
7 pages
Business Combinations and Assesment
No ratings yet
Business Combinations and Assesment
4 pages
Chapter 5 DPD
No ratings yet
Chapter 5 DPD
23 pages
Jaggia5e Chap005 PPT
No ratings yet
Jaggia5e Chap005 PPT
30 pages
The Importance of English in International Business
No ratings yet
The Importance of English in International Business
8 pages
chp2 Econometric
No ratings yet
chp2 Econometric
54 pages
Muhammad Shariq 2171019 Quiz No 2
0% (1)
Muhammad Shariq 2171019 Quiz No 2
2 pages
CCFOASW ESBE 10e PPT CH05
No ratings yet
CCFOASW ESBE 10e PPT CH05
37 pages
Evans Analytics2e PPT 05
No ratings yet
Evans Analytics2e PPT 05
65 pages
Lecture 18
No ratings yet
Lecture 18
5 pages
UNIT 4 Standard Costing and Variance Analysis
No ratings yet
UNIT 4 Standard Costing and Variance Analysis
39 pages
Hope CV
No ratings yet
Hope CV
2 pages
Solution of Business Stat Paper
No ratings yet
Solution of Business Stat Paper
17 pages
Charte Mobilite VF Maj Nov 2021 Web
No ratings yet
Charte Mobilite VF Maj Nov 2021 Web
8 pages
E-Way Bill System - 573
No ratings yet
E-Way Bill System - 573
1 page
Answer:: Chapter 19 - Solution Procedures For Transportation and Assignment Problems True / False
No ratings yet
Answer:: Chapter 19 - Solution Procedures For Transportation and Assignment Problems True / False
13 pages
Chapter 03 Test Bank - Static - Version1
No ratings yet
Chapter 03 Test Bank - Static - Version1
50 pages
Chapter 12
82% (11)
Chapter 12
40 pages
WEF Views From The Manufacturing Front Line 2023
No ratings yet
WEF Views From The Manufacturing Front Line 2023
22 pages
Tax Invoices, Credit and Debit Notes
No ratings yet
Tax Invoices, Credit and Debit Notes
3 pages
Low Profile Bending Beam Low Profile Bending Beam: Model 60040
No ratings yet
Low Profile Bending Beam Low Profile Bending Beam: Model 60040
3 pages
Quiz 1 Ca51013 - It App
No ratings yet
Quiz 1 Ca51013 - It App
9 pages
1
50% (2)
1
26 pages
Acc 115 P1quiz - A
No ratings yet
Acc 115 P1quiz - A
7 pages
Aslam Aswat CV
No ratings yet
Aslam Aswat CV
2 pages
Chapter 9 Ed 16
100% (1)
Chapter 9 Ed 16
73 pages
Math 156 Practice - Midterm - Exam
No ratings yet
Math 156 Practice - Midterm - Exam
80 pages
Fm-Hse-03-02 Major Hazard and Related Activities PDF
100% (1)
Fm-Hse-03-02 Major Hazard and Related Activities PDF
6 pages
Prepared by Iordanis Petsas To Accompany by Paul R. Krugman and Maurice Obstfeld
No ratings yet
Prepared by Iordanis Petsas To Accompany by Paul R. Krugman and Maurice Obstfeld
13 pages
Lec 18
No ratings yet
Lec 18
5 pages
Short Quiz 1-10
No ratings yet
Short Quiz 1-10
40 pages
Forecasting
100% (1)
Forecasting
21 pages
Scope of Merchant Banking in India
50% (2)
Scope of Merchant Banking in India
4 pages
Chapter 8 Risk and Return Presentation
No ratings yet
Chapter 8 Risk and Return Presentation
29 pages
Chapter 05 - Discrete Probability Distributions: F (X) 1 For All Values of X F (X) 0 For All Values of X
No ratings yet
Chapter 05 - Discrete Probability Distributions: F (X) 1 For All Values of X F (X) 0 For All Values of X
25 pages
Quantitative Techniques
No ratings yet
Quantitative Techniques
7 pages
Mahusay Acc227 Module 1
No ratings yet
Mahusay Acc227 Module 1
12 pages
Supplementary Chapter E - Decision Analysis: True/False
100% (1)
Supplementary Chapter E - Decision Analysis: True/False
16 pages
MBA - Financial Management Final Exam
No ratings yet
MBA - Financial Management Final Exam
13 pages
1st Long Exam (Summer 2022) WITHOUT ANSWER
No ratings yet
1st Long Exam (Summer 2022) WITHOUT ANSWER
10 pages
Capital Budgeting Techniques
No ratings yet
Capital Budgeting Techniques
21 pages
End of Season: Spring Summer 2021
No ratings yet
End of Season: Spring Summer 2021
29 pages
World Trade: An Overview: Prepared by Iordanis Petsas To Accompany by Paul R. Krugman and Maurice Obstfeld
No ratings yet
World Trade: An Overview: Prepared by Iordanis Petsas To Accompany by Paul R. Krugman and Maurice Obstfeld
17 pages
Chapter 2: Descriptive Statistics: Tabular and Graphical Methods
100% (1)
Chapter 2: Descriptive Statistics: Tabular and Graphical Methods
7 pages
A220 - Midterm Requirement
No ratings yet
A220 - Midterm Requirement
7 pages
Personality Rights in Sports
No ratings yet
Personality Rights in Sports
3 pages
Test Bank For Quantitative Analysis For Management 12th Edition
No ratings yet
Test Bank For Quantitative Analysis For Management 12th Edition
12 pages
Federal Urdu University of Arts, Science and Technology, Islamabad
No ratings yet
Federal Urdu University of Arts, Science and Technology, Islamabad
5 pages
CH 3
100% (1)
CH 3
31 pages
Break Even Point (Bep) Analysis of Tomato Farming Business in Taraitak I Village, Langowan District, Minahasa District
No ratings yet
Break Even Point (Bep) Analysis of Tomato Farming Business in Taraitak I Village, Langowan District, Minahasa District
8 pages
CHP 15 Fin 13
No ratings yet
CHP 15 Fin 13
14 pages
Chapter 13 - Decision Analysis: Cengage Learning Testing, Powered by Cognero
No ratings yet
Chapter 13 - Decision Analysis: Cengage Learning Testing, Powered by Cognero
38 pages
Presentation ON History of A Successful Entrepreneur
No ratings yet
Presentation ON History of A Successful Entrepreneur
16 pages
Financial MANAGEMENT: (Vip Questions)
No ratings yet
Financial MANAGEMENT: (Vip Questions)
39 pages
CAFC M21 CHP Wise Test Paper+hints
No ratings yet
CAFC M21 CHP Wise Test Paper+hints
2 pages
Dec Analysis
100% (1)
Dec Analysis
19 pages
Probability Distribution
No ratings yet
Probability Distribution
27 pages
Exercise Module 4
No ratings yet
Exercise Module 4
5 pages
Module 2A - CVP Analysis
No ratings yet
Module 2A - CVP Analysis
5 pages
Chapter 10 Decision Trees Theories
No ratings yet
Chapter 10 Decision Trees Theories
28 pages
Senior Year Calendar For Students Applying For Financial Aid
No ratings yet
Senior Year Calendar For Students Applying For Financial Aid
2 pages
This Study Resource Was: A. Determine The Optimal Order Size
No ratings yet
This Study Resource Was: A. Determine The Optimal Order Size
7 pages
OM3 CH 11 Forecasting and Demand Planning
No ratings yet
OM3 CH 11 Forecasting and Demand Planning
17 pages
135 PBTC v. Abasalo Margallo
No ratings yet
135 PBTC v. Abasalo Margallo
2 pages
HR Metrics Dashboarding Certificate Program Syllabus AIHR
100% (1)
HR Metrics Dashboarding Certificate Program Syllabus AIHR
9 pages
The Application of Budgets and Budgetary Control On The Performance of Small and Medium-Sized Enterprises (Smes)
No ratings yet
The Application of Budgets and Budgetary Control On The Performance of Small and Medium-Sized Enterprises (Smes)
18 pages
ch12 TB
No ratings yet
ch12 TB
25 pages
Manual Solution 6-14
No ratings yet
Manual Solution 6-14
5 pages
Cost of Capital
No ratings yet
Cost of Capital
41 pages
Question 1: Describe Difference Between Strategy and Tactics? Ans
No ratings yet
Question 1: Describe Difference Between Strategy and Tactics? Ans
5 pages
Goal Programming
No ratings yet
Goal Programming
14 pages
Chap009 Test Bank 1 Solution
No ratings yet
Chap009 Test Bank 1 Solution
7 pages
Chapter 13
No ratings yet
Chapter 13
66 pages
Ch9 Testbank Handout
100% (2)
Ch9 Testbank Handout
2 pages
FMEA Article
No ratings yet
FMEA Article
4 pages
Vision and Mission: Nestlé S.A. (
No ratings yet
Vision and Mission: Nestlé S.A. (
28 pages
16 Risk and Rates of Return Problems For Online Class
No ratings yet
16 Risk and Rates of Return Problems For Online Class
6 pages
ch4 5 Exercise 11th
No ratings yet
ch4 5 Exercise 11th
10 pages
Current Rate Method
No ratings yet
Current Rate Method
28 pages
Quantitative Techniques (OK Na!)
No ratings yet
Quantitative Techniques (OK Na!)
9 pages
Chapter 25 - Answer
No ratings yet
Chapter 25 - Answer
18 pages
Answers To Study Questions Information Systems For Business and Beyond PDF
No ratings yet
Answers To Study Questions Information Systems For Business and Beyond PDF
7 pages
Final Answer
No ratings yet
Final Answer
15 pages
MAITRI Brochure
No ratings yet
MAITRI Brochure
8 pages
MOF Homework 1
No ratings yet
MOF Homework 1
1 page
TB Chapter20
No ratings yet
TB Chapter20
25 pages
Project Classification:: Advantages of Net Present Value (NPV)
No ratings yet
Project Classification:: Advantages of Net Present Value (NPV)
5 pages
Ch6 Testbank Handout
No ratings yet
Ch6 Testbank Handout
5 pages
Set A
No ratings yet
Set A
9 pages