(eBook PDF) Data Analysis and Decision Making

4th Edition pdf download

https://ebooksecure.com/product/ebook-pdf-data-analysis-and-
decision-making-4th-edition/

Download more ebook from https://ebooksecure.com

We believe these products will be a great fit for you. Click
the link to download now, or visit ebooksecure.com
to discover even more!

(eBook PDF) Business Analytics Data Analysis Decision

Making 6th

http://ebooksecure.com/product/ebook-pdf-business-analytics-data-
analysis-decision-making-6th/

Business Analytics: Data Analysis & Decision Making 6th

Edition (eBook PDF)

http://ebooksecure.com/product/business-analytics-data-analysis-
decision-making-6th-edition-ebook-pdf/

(eBook PDF) Business Analytics: Data Analysis &

Decision Making 7th Edition

http://ebooksecure.com/product/ebook-pdf-business-analytics-data-
analysis-decision-making-7th-edition/

Business Analytics: Data Analysis & Decision Making

(MindTap Course List) 7th Edition Albright - eBook PDF

https://ebooksecure.com/download/business-analytics-data-
analysis-decision-making-mindtap-course-list-ebook-pdf/
(eBook PDF) Statistics, Data Analysis, and Decision
Modeling 5th Edition

http://ebooksecure.com/product/ebook-pdf-statistics-data-
analysis-and-decision-modeling-5th-edition/

(Original PDF) Statistics for Business: Decision Making

and Analysis 3rd Edition

http://ebooksecure.com/product/original-pdf-statistics-for-
business-decision-making-and-analysis-3rd-edition/

(eBook PDF) Financial Accounting Reporting, Analysis

Decision Making 5th

http://ebooksecure.com/product/ebook-pdf-financial-accounting-
reporting-analysis-decision-making-5th/

(eBook PDF) Statistics for Business Decision Making

Analysis 2nd

http://ebooksecure.com/product/ebook-pdf-statistics-for-business-
decision-making-analysis-2nd/

Modern Business Analytics: Practical Data Science for

Decision-making - eBook PDF

https://ebooksecure.com/download/modern-business-analytics-
practical-data-science-for-decision-making-ebook-pdf/
 Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 Brief Contents
Preface xii
1 Introduction to Data Analysis and Decision Making 1
Part 1 Exploring Data 19
2 Describing the Distribution of a Single Variable 21
3 Finding Relationships among Variables 85
Part 2 Probability and Decision Making under Uncertainty 153
4 Probability and Probability Distributions 155
5 Normal, Binomial, Poisson, and Exponential Distributions 209
6 Decision Making under Uncertainty 273
Part 3 Statistical Inference 349
7 Sampling and Sampling Distributions 351
8 Confidence Interval Estimation 387
9 Hypothesis Testing 455
Part 4 Regression Analysis and Time Series Forecasting 527
10 Regression Analysis: Estimating Relationships 529
11 Regression Analysis: Statistical Inference 601
12 Time Series Analysis and Forecasting 669
Part 5 Optimization and Simulation Modeling 743
13 Introduction to Optimization Modeling 745
14 Optimization Models 811
15 Introduction to Simulation Modeling 917
16 Simulation Models 987
Part 6 Online Bonus Material
2 Using the Advanced Filter and Database Functions 2-1
17 Importing Data into Excel 17-1
Appendix A Statistical Reporting A-1
References 1055
Index 1059

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 Contents
Preface xii 2.7 Excel Tables for Filtering, Sorting, and
Summarizing 66
1 Introduction to Data Analysis and
2.7.1 Filtering 70
Decision Making 1
2.8 Conclusion 75
1.1 Introduction 2
CASE 2.1 Correct Interpretation of Means 81
1.2 An Overview of the Book 4
CASE 2.2 The Dow Jones Industrial Average 82
1.2.1 The Methods 4
CASE 2.3 Home and Condo Prices 83
1.2.2 The Software 7
1.3 Modeling and Models 11 3 Finding Relationships among Variables 85
1.3.1 Graphical Models 11 3.1 Introduction 87
1.3.2 Algebraic Models 12 3.2 Relationships among Categorical Variables 88
1.3.3 Spreadsheet Models 12 3.3 Relationships among Categorical Variables
1.3.4 A Seven-Step Modeling Process 14 and a Numerical Variable 92
1.4 Conclusion 16 3.3.1 Stacked and Unstacked Formats 93
CASE 1.1 Entertainment on a Cruise Ship 17 3.4 Relationships among Numerical Variables 101
3.4.1 Scatterplots 102
3.4.2 Correlation and Covariance 106
PART 1 E XPLORING DATA 19 3.5 Pivot Tables 114
3.6 An Extended Example 137
2 Describing the Distribution of a
Single Variable 21 3.7 Conclusion 144
CASE 3.1 Customer Arrivals at Bank98 149
2.1 Introduction 23
CASE 3.2 Saving, Spending, and Social
2.2 Basic Concepts 24
Climbing 150
2.2.1 Populations and Samples 24
CASE 3.3 Churn in the Cellular Phone
2.2.2 Data Sets, Variables, and Observations 25
Market 151
2.2.3 Types of Data 27
2.3 Descriptive Measures for Categorical P ROBABILITY AND D ECISION
Variables 30 PART 2 M AKING UNDER
2.4 Descriptive Measures for Numerical U NCERTAINTY 153
Variables 33
2.4.1 Numerical Summary Measures 34 4 Probability and Probability Distributions 155
2.4.2 Numerical Summary Measures with 4.1 Introduction 156
StatTools 43 4.2 Probability Essentials 158
2.4.3 Charts for Numerical Variables 48 4.2.1 Rule of Complements 159
2.5 Time Series Data 57 4.2.2 Addition Rule 159
2.6 Outliers and Missing Values 64 4.2.3 Conditional Probability and the
2.6.1 Outliers 64 Multiplication Rule 160
2.6.2 Missing Values 65 4.2.4 Probabilistic Independence 162

vi

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 4.2.5 Equally Likely Events 163 5.8 Conclusion 261
4.2.6 Subjective Versus Objective CASE 5.1 EuroWatch Company 269
Probabilities 163 CASE 5.2 Cashing in on the Lottery 270
4.3 Distribution of a Single Random Variable 166
4.3.1 Conditional Mean and Variance 170 6 Decision Making under Uncertainty 273
4.4 An Introduction to Simulation 173 6.1 Introduction 274
4.5 Distribution of Two Random Variables: Scenario 6.2 Elements of Decision Analysis 276
Approach 177 6.2.1 Payoff Tables 276
4.6 Distribution of Two Random Variables: Joint 6.2.2 Possible Decision Criteria 277
Probability Approach 183 6.2.3 Expected Monetary Value (EMV) 278
4.6.1 How to Assess Joint Probability 6.2.4 Sensitivity Analysis 280
Distributions 187 6.2.5 Decision Trees 280
4.7 Independent Random Variables 189 6.2.6 Risk Profiles 282
4.8 Weighted Sums of Random Variables 193 6.3 The PrecisionTree Add-In 290
4.9 Conclusion 200 6.4 Bayes’ Rule 303
CASE 4.1 Simpson’s Paradox 208 6.5 Multistage Decision Problems 307
5 Normal, Binomial, Poisson, and Exponential 6.5.1 The Value of Information 311
Distributions 209 6.6 Incorporating Attitudes Toward Risk 323
5.1 Introduction 211 6.6.1 Utility Functions 324
5.2 The Normal Distribution 211 6.6.2 Exponential Utility 324
5.2.1 Continuous Distributions and 6.6.3 Certainty Equivalents 328
Density Functions 211 6.6.4 Is Expected Utility Maximization
5.2.2 The Normal Density 213 Used? 330
5.2.3 Standardizing: Z-Values 214 6.7 Conclusion 331
5.2.4 Normal Tables and Z-Values 216 CASE 6.1 Jogger Shoe Company 345
5.2.5 Normal Calculations in Excel 217 CASE 6.2 Westhouser Parer Company 346
5.2.6 Empirical Rules Revisited 220 CASE 6.3 Biotechnical Engineering 347
5.3 Applications of the Normal Distribution 221
5.4 The Binomial Distribution 233
5.4.1 Mean and Standard Deviation of the
Binomial Distribution 236 PART 3 S TATISTICAL I NFERENCE 349
5.4.2 The Binomial Distribution in the
Context of Sampling 236 7 Sampling and Sampling Distributions 351
5.4.3 The Normal Approximation to the 7.1 Introduction 352
Binomial 237 7.2 Sampling Terminology 353
5.5 Applications of the Binomial Distribution 238 7.3 Methods for Selecting Random Samples 354
5.6 The Poisson and Exponential Distributions 250 7.3.1 Simple Random Sampling 354
5.6.1 The Poisson Distribution 250 7.3.2 Systematic Sampling 360
5.6.2 The Exponential Distribution 252 7.3.3 Stratified Sampling 361
5.7 Fitting a Probability Distribution to Data with 7.3.4 Cluster Sampling 364
@RISK 255 7.3.5 Multistage Sampling Schemes 365

Contents vii

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 7.4 An Introduction to Estimation 366 9.2 Concepts in Hypothesis Testing 457
7.4.1 Sources of Estimation Error 367 9.2.1 Null and Alternative Hypotheses 458
7.4.2 Key Terms in Sampling 368 9.2.2 One-Tailed Versus Two-Tailed Tests 459
7.4.3 Sampling Distribution of the Sample 9.2.3 Types of Errors 459
Mean 369 9.2.4 Significance Level and Rejection
7.4.4 The Central Limit Theorem 374 Region 460
7.4.5 Sample Size Determination 379 9.2.5 Significance from p -values 461
7.4.6 Summary of Key Ideas for Simple Random 9.2.6 Type II Errors and Power 462
Sampling 380 9.2.7 Hypothesis Tests and Confidence
7.5 Conclusion 382 Intervals 463
CASE 7.1 Sampling from DVD Movie Renters 386 9.2.8 Practical Versus Statistical Significance 463
9.3 Hypothesis Tests for a Population Mean 464
8 Confidence Interval Estimation 387 9.4 Hypothesis Tests for Other Parameters 472
8.1 Introduction 388 9.4.1 Hypothesis Tests for a Population
8.2 Sampling Distributions 390 Proportion 472
8.2.1 The t Distribution 390 9.4.2 Hypothesis Tests for Differences between
8.2.2 Other Sampling Distributions 393 Population Means 475
8.3 Confidence Interval for a Mean 394 9.4.3 Hypothesis Test for Equal Population
8.4 Confidence Interval for a Total 400 Variances 485
8.5 Confidence Interval for a Proportion 403 9.4.4 Hypothesis Tests for Differences between
8.6 Confidence Interval for a Standard Population Proportions 486
Deviation 409 9.5 Tests for Normality 494
8.7 Confidence Interval for the Difference 9.6 Chi-Square Test for Independence 500
between Means 412 9.7 One-Way ANOVA 505
8.7.1 Independent Samples 413 9.8 Conclusion 513
8.7.2 Paired Samples 421 CASE 9.1 Regression Toward the Mean 519
8.8. Confidence Interval for the Difference between CASE 9.2 Baseball Statistics 520
Proportions 427 CASE 9.3 The Wichita Anti–Drunk Driving
8.9. Controlling Confidence Interval Length 433 Advertising Campaign 521
8.9.1 Sample Size for Estimation of the CASE 9.4 Deciding Whether to Switch to a
Mean 434 New Toothpaste Dispenser 523
8.9.2 Sample Size for Estimation of CASE 9.5 Removing Vioxx from the Market 526
Other Parameters 436
8.10 Conclusion 441
CASE 8.1 Harrigan University Admissions 449
CASE 8.2 Employee Retention at D&Y 450 R EGRESSION A NALYSIS
CASE 8.3 Delivery Times at SnowPea PART 4 AND T IME S ERIES
Restaurant 451 F ORECASTING 527
CASE 8.4 The Bodfish Lot Cruise 452
10 Regression Analysis: Estimating
9 Hypothesis Testing 455 Relationships 529
9.1 Introduction 456 10.1 Introduction 531

viii Contents

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 10.2 Scatterplots: Graphing Relationships 533 11.4 Multicollinearity 616
10.2.1 Linear Versus Nonlinear Relationships 538 11.5 Include/Exclude Decisions 620
10.2.2 Outliers 538 11.6 Stepwise Regression 625
10.2.3 Unequal Variance 539 11.7 The Partial F Test 630
10.2.4 No Relationship 540 11.8 Outliers 638
10.3 Correlations: Indicators of Linear 11.9 Violations of Regression Assumptions 644
Relationships 540 11.9.1 Nonconstant Error Variance 644
10.4 Simple Linear Regression 542 11.9.2 Nonnormality of Residuals 645
10.4.1 Least Squares Estimation 542 11.9.3 Autocorrelated Residuals 645
10.4.2 Standard Error of Estimate 549 11.10 Prediction 648
10.4.3 The Percentage of Variation 11.11 Conclusion 653
Explained: R2 550 CASE 11.1 The Artsy Corporation 663
10.5 Multiple Regression 553 CASE 11.2 Heating Oil at Dupree Fuels
10.5.1 Interpretation of Regression Coefficients 554 Company 665
10.5.2 Interpretation of Standard Error of CASE 11.3 Developing a Flexible Budget at
Estimate and R2 556 the Gunderson Plant 666
10.6 Modeling Possibilities 560 CASE 11.4 Forecasting Overhead at Wagner
10.6.1 Dummy Variables 560 Printers 667
10.6.2 Interaction Variables 566
10.6.3 Nonlinear Transformations 571 12 Time Series Analysis and Forecasting 669
10.7 Validation of the Fit 586 12.1 Introduction 671
10.8 Conclusion 588 12.2 Forecasting Methods: An Overview 671
CASE 10.1 Quantity Discounts at the Firm 12.2.1 Extrapolation Methods 672
Chair Company 596 12.2.2 Econometric Models 672
CASE 10.2 Housing Price Structure in 12.2.3 Combining Forecasts 673
Mid City 597 12.2.4 Components of Time Series
CASE 10.3 Demand for French Bread at Data 673
Howie’s Bakery 598 12.2.5 Measures of Accuracy 676
CASE 10.4 Investing for Retirement 599 12.3 Testing for Randomness 678
12.3.1 The Runs Test 681
11 Regression Analysis: Statistical Inference 601 12.3.2 Autocorrelation 683
11.1 Introduction 603 12.4 Regression-Based Trend Models 687
11.2 The Statistical Model 603 12.4.1 Linear Trend 687
11.3 Inferences about the Regression 12.4.2 Exponential Trend 690
Coefficients 607 12.5 The Random Walk Model 695
11.3.1 Sampling Distribution of the Regression 12.6 Autoregression Models 699
Coefficients 608 12.7 Moving Averages 704
11.3.2 Hypothesis Tests for the Regression 12.8 Exponential Smoothing 710
Coefficients and p-Values 610 12.8.1 Simple Exponential Smoothing 710
11.3.3 A Test for the Overall Fit: The ANOVA 12.8.2 Holt’s Model for Trend 715
Table 611 12.9 Seasonal Models 720

Contents ix

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 12.9.1 Winters’ Exponential Smoothing 14 Optimization Models 811
Model 721 14.1 Introduction 812
12.9.2 Deseasonalizing: The Ratio-to-Moving- 14.2 Worker Scheduling Models 813
Averages Method 725 14.3 Blending Models 821
12.9.3 Estimating Seasonality with Regression 729 14.4 Logistics Models 828
12.10 Conclusion 735 14.4.1 Transportation Models 828
CASE 12.1 Arrivals at the Credit Union 740 14.4.2 Other Logistics Models 837
CASE 12.2 Forecasting Weekly Sales at 14.5 Aggregate Planning Models 848
Amanta 741
14.6 Financial Models 857
14.7 Integer Programming Models 868
14.7.1 Capital Budgeting Models 869
O PTIMIZATION AND
PART 5 14.7.2 Fixed-Cost Models 875
S IMULATION M ODELING 743
14.7.3 Set-Covering Models 883
13 Introduction to Optimization Modeling 745 14.8 Nonlinear Programming Models 891
13.1 Introduction 746 14.8.1 Basic Ideas of Nonlinear
13.2 Introduction to Optimization 747 Optimization 891
13.3 A Two-Variable Product Mix Model 748 14.8.2 Managerial Economics Models 891
13.4 Sensitivity Analysis 761 14.8.3 Portfolio Optimization Models 896
13.4.1 Solver’s Sensitivity Report 761 14.9 Conclusion 905
13.4.2 SolverTable Add-In 765 CASE 14.1 Giant Motor Company 912
13.4.3 Comparison of Solver’s Sensitivity Report CASE 14.2 GMS Stock Hedging 914
and SolverTable 770
13.5 Properties of Linear Models 772 15 Introduction to Simulation Modeling 917
13.5.1 Proportionality 773 15.1 Introduction 918
13.5.2 Additivity 773 15.2 Probability Distributions for Input
13.5.3 Divisibility 773 Variables 920
13.5.4 Discussion of Linear Properties 773 15.2.1 Types of Probability Distributions 921
13.5.5 Linear Models and Scaling 774 15.2.2 Common Probability Distributions 925
13.6 Infeasibility and Unboundedness 775 15.2.3 Using @RISK to Explore Probability
13.6.1 Infeasibility 775 Distributions 929
13.6.2 Unboundedness 775 15.3 Simulation and the Flaw of
13.6.3 Comparison of Infeasibility and Averages 939
Unboundedness 776 15.4 Simulation with Built-In Excel Tools 942
13.7 A Larger Product Mix Model 778 15.5 Introduction to the @RISK Add-in 953
13.8 A Multiperiod Production Model 786 15.5.1 @RISK Features 953
13.9 A Comparison of Algebraic and Spreadsheet 15.5.2 Loading @RISK 954
Models 796 15.5.3 @RISK Models with a Single Random
13.10 A Decision Support System 796 Input Variable 954
13.11 Conclusion 799 15.5.4 Some Limitations of @RISK 963
CASE 13.1 Shelby Shelving 807 15.5.5 @RISK Models with Several Random
CASE 13.2 Sonoma Valley Wines 809 Input Variables 964

x Contents

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 15.6 The Effects of Input Distributions on
PART 6 O NLINE B ONUS M ATERIAL
Results 969
15.6.1 Effect of the Shape of the Input 2 Using the Advanced Filter and
Distribution(s) 969 Database Functions 2-1
15.6.2 Effect of Correlated Input
Variables 972 17 Importing Data into Excel 17-1
15.7 Conclusion 978 17.1 Introduction 17-3
CASE 15.1 Ski Jacket Production 985 17.2 Rearranging Excel Data 17-4
CASE 15.2 Ebony Bath Soap 986 17.3 Importing Text Data 17-8
17.4 Importing Relational Database
16 Simulation Models 987 Data 17-14
16.1 Introduction 989 17.4.1 A Brief Introduction to Relational
Databases 17-14
16.2 Operations Models 989
17.4.2 Using Microsoft Query 17-15
16.2.1 Bidding for Contracts 989
17.4.3 SQL Statements 17-28
16.2.2 Warranty Costs 993
17.5 Web Queries 17-30
16.2.3 Drug Production with Uncertain
Yield 998 17.6 Cleansing Data 17-34
16.3 Financial Models 1004 17.7 Conclusion 17-42
CASE 17.1 EduToys, Inc. 17-46
16.3.1 Financial Planning Models 1004
16.3.2 Cash Balance Models 1009 Appendix A: Statistical Reporting A-1
16.3.3 Investment Models 1014 A.1 Introduction A-1
16.4 Marketing Models 1020 A.2 Suggestions for Good Statistical
16.4.1 Models of Customer Loyalty 1020 Reporting A-2
16.4.2 Marketing and Sales Models 1030 A.2.1 Planning A-2
16.5 Simulating Games of Chance 1036 A.2.2 Developing a Report A-3
16.5.1 Simulating the Game of Craps 1036 A.2.3 Be Clear A-4
16.5.2 Simulating the NCAA Basketball A.2.4 Be Concise A-5
Tournament 1039 A.2.5 Be Precise A-5
16.6 An Automated Template for @RISK A.3 Examples of Statistical Reports A-6
Models 1044 A.4 Conclusion A-18
16.7 Conclusion 1045
CASE 16.1 College Fund Investment 1053
References 1055
CASE 16.2 Bond Investment Strategy 1054 Index 1059

Contents xi

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 Preface
With today’s technology, companies are able to 1. Integrated coverage and applications.
collect tremendous amounts of data with relative The book provides a unified approach to
ease. Indeed, many companies now have more data business-related problems by integrating
than they can handle. However, the data are usually methods and applications that have been
meaningless until they are analyzed for trends, traditionally taught in separate courses,
patterns, relationships, and other useful information. specifically statistics and management
This book illustrates in a practical way a variety of science.
methods, from simple to complex, to help you ana- 2. Practical in approach. The book emphasizes
lyze data sets and uncover important information. In realistic business examples and the processes
many business contexts, data analysis is only the managers actually use to analyze business
first step in the solution of a problem. Acting on the problems. The emphasis is not on abstract
solution and the information it provides to make theory or computational methods.
good decisions is a critical next step. Therefore,
3. Spreadsheet-based. The book provides
there is a heavy emphasis throughout this book on
students with the skills to analyze business
analytical methods that are useful in decision mak-
problems with tools they have access to and
ing. Again, the methods vary considerably, but the
will use in their careers. To this end, we have
objective is always the same—to equip you with
adopted Excel and commercial spreadsheet
decision-making tools that you can apply in your
add-ins.
business careers.
We recognize that the majority of students in
this type of course are not majoring in a quantitative Integrated coverage and applications
area. They are typically business majors in finance,
marketing, operations management, or some other In the past, many business schools, including ours at
business discipline who will need to analyze data and Indiana University, have offered a required statistics
make quantitative-based decisions in their jobs. We course, a required decision-making course, and a
offer a hands-on, example-based approach and required management science course—or some subset
introduce fundamental concepts as they are needed. of these. One current trend, however, is to have only
Our vehicle is spreadsheet software—specifically, one required course that covers the basics of statistics,
Microsoft Excel. This is a package that most students some regression analysis, some decision making
already know and will undoubtedly use in their under uncertainty, some linear programming, some
careers. Our MBA students at Indiana University are simulation, and possibly others. Essentially, we fac-
so turned on by the required course that is based on ulty in the quantitative area get one opportunity to
this book that almost all of them (mostly finance and teach all business students, so we attempt to cover a
marketing majors) take at least one of our follow-up variety of useful quantitative methods. We are not nec-
elective courses in spreadsheet modeling. We are essarily arguing that this trend is ideal, but rather that
convinced that students see value in quantitative it is a reflection of the reality at our university and,
analysis when the course is taught in a practical and we suspect, at many others. After several years of
example-based approach. teaching this course, we have found it to be a great
opportunity to attract students to the subject and more
advanced study.
The book is also integrative in another important
Rationale for writing this book aspect. It not only integrates a number of analytical
Data Analysis and Decision Making is different from methods, but it also applies them to a wide variety
the many fine textbooks written for statistics and man- of business problems—that is, it analyzes realistic
agement science. Our rationale for writing this book is examples from many business disciplines. We include
based on three fundamental objectives. examples, problems, and cases that deal with portfolio

xii

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 optimization, workforce scheduling, market share What we hope to accomplish
analysis, capital budgeting, new product analysis, and
in this book
many others.
Condensing the ideas in the above paragraphs, we
hope to:
Practical in approach
■ Reverse negative student attitudes about
We want this book to be very example-based and prac- statistics and quantitative methods by making
tical. We strongly believe that students learn best by these topics real, accessible, and interesting;
working through examples, and they appreciate the ■ Give students lots of hands-on experience with
material most when the examples are realistic and inter-
real problems and challenge them to develop
esting. Therefore, our approach in the book differs in
their intuition, logic, and problem-solving skills;
two important ways from many competitors. First, there
■ Expose students to real problems in many
is just enough conceptual development to give students
an understanding and appreciation for the issues raised business disciplines and show them how these
in the examples. We often introduce important con- problems can be analyzed with quantitative
cepts, such as multicollinearity in regression, in the methods;
context of examples, rather than discussing them in the ■ Develop spreadsheet skills, including
abstract. Our experience is that students gain greater experience with powerful spreadsheet add-ins,
intuition and understanding of the concepts and appli- that add immediate value in students’ other
cations through this approach. courses and their future careers.
Second, we place virtually no emphasis on hand
calculations. We believe it is more important for
New in the fourth edition
students to understand why they are conducting an
analysis and what it means than to emphasize the There are two major changes in this edition.
tedious calculations associated with many analytical ■ We have completely rewritten and reorganized
techniques. Therefore, we illustrate how powerful
Chapters 2 and 3. Chapter 2 now focuses on
software can be used to create graphical and numeri-
the description of one variable at a time, and
cal outputs in a matter of seconds, freeing the
Chapter 3 focuses on relationships between
rest of the time for in-depth interpretation of the
variables. We believe this reorganization is
output, sensitivity analysis, and alternative modeling
more logical. In addition, both of these
approaches. In our own courses, we move directly
chapters have more coverage of categorical
into a discussion of examples, where we focus
variables, and they have new examples with
almost exclusively on interpretation and modeling
more interesting data sets.
issues and let the software perform the number
■ We have made major changes in the problems,
crunching.
particularly in Chapters 2 and 3. Many of
the problems in previous editions were either
Spreadsheet-based teaching uninteresting or outdated, so in most cases
We are strongly committed to teaching spreadsheet- we deleted or updated such problems, and we
based, example-driven courses, regardless of whether added a number of brand-new problems. We
the basic area is data analysis or management science. also created a file, essentially a database of prob-
We have found tremendous enthusiasm for this lems, that is available to instructors. This file,
approach, both from students and from faculty around Problem Database.xlsx, indicates the context
the world who have used our books. Students learn of each of the problems, and it also shows the
and remember more, and they appreciate the material correspondence between problems in this edition
more. In addition, instructors typically enjoy teaching and problems in the previous edition.
more, and they usually receive immediate reinforce-
Besides these two major changes, there are a number
ment through better teaching evaluations. We were
of smaller changes, including the following:
among the first to move to spreadsheet-based teaching
almost two decades ago, and we have never regretted ■ Due to the length of the book, we decided to
the move. delete the old Chapter 4 (Getting the Right

Preface xiii

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 Data) from the printed book and make DecisionTools® add-in. The textbook Web site for
it available online as Chapter 17. This Data Analysis and Decision Making provides a link to the
chapter, now called “Importing Data into powerful DecisionTools® Suite by Palisade Corporation.
Excel,” has been completely rewritten, This suite includes seven separate add-ins, the first three
and its section on Excel tables is now in of which we use extensively:
Chapter 2. (The old Chapters 5–17 were
renumbered 4–16.) ■ @RISK, an add-in for simulation
■ The book is still based on Excel 2007, but ■ StatTools, an add-in for statistical data
where it applies, notes about changes in Excel analysis
2010 have been added. Specifically, there is a ■ PrecisionTree, a graphical-based add-in for
small section on the new slicers for pivot creating and analyzing decision trees
tables, and there are several mentions of the ■ TopRank, an add-in for performing what-if
new statistical functions (although the old
analyses
functions still work).
■ RISKOptimizer, an add-in for performing
■ Each chapter now has 10–20 “Conceptual
optimization on simulation models
Questions” in the end-of-chapter section.
There were a few “Conceptual Exercises” in ■ NeuralTools®, an add-in for finding complex,
some chapters in previous editions, but the new nonlinear relationships
versions are more numerous, consistent, and ■ EvolverTM, an add-in for performing optimiza-
relevant. tion on complex “nonsmooth” models
■ The first two linear programming (LP) Online access to the DecisionTools® Suite, avail-
examples in Chapter 13 (the old Chapter 14) able with new copies of the book, is an academic ver-
have been replaced by two product mix sion, slightly scaled down from the professional version
models, where the second is an extension of that sells for hundreds of dollars and is used by many
the first. Our thinking was that the previous leading companies. It functions for two years when
diet-themed model was overly complex as a properly installed, and it puts only modest limitations on
first LP example. the size of data sets or models that can be analyzed.
■ Several of the chapter-opening vignettes have (Visit www.kelley.iu.edu/albrightbooks for specific
been replaced by newer and more interesting details on these limitations.) We use @RISK and
ones. PrecisionTree extensively in the chapters on simulation
■ There are now many short “fundamental and decision making under uncertainty, and we use
insights” throughout the chapters. We hope StatTools throughout all of the data analysis chapters.
these allow the students to step back from the SolverTable add-in. We also include SolverTable,
details and see the really important ideas. a supplement to Excel’s built-in Solver for optimiza-
tion. If you have ever had difficulty understanding
Solver’s sensitivity reports, you will appreciate
Software SolverTable. It works like Excel’s data tables, except
that for each input (or pair of inputs), the add-in runs
This book is based entirely on Microsoft Excel, the
Solver and reports the optimal output values.
spreadsheet package that has become the standard
SolverTable is used extensively in the optimization
analytical tool in business. Excel is an extremely
chapters. The version of SolverTable included in this
powerful package, and one of our goals is to convert
book has been revised for Excel 2007. (Although
casual users into power users who can take full
SolverTable is available on this textbook’s Web site, it
advantage of its features. If we accomplish no more
is also available for free from the first author’s Web site,
than this, we will be providing a valuable skill for the
www.kelley.iu.edu/albrightbooks.)
business world. However, Excel has some limitations.
Therefore, this book includes several Excel add-ins
that greatly enhance Excel’s capabilities. As a group,
these add-ins comprise what is arguably the most
Possible sequences of topics
impressive assortment of spreadsheet-based software Although we use the book for our own required one-
accompanying any book on the market. semester course, there is admittedly more material

xiv Preface

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 than can be covered adequately in one semester. We Student ancillaries
have tried to make the book as modular as possible,
allowing an instructor to cover, say, simulation Textbook Web Site
before optimization or vice versa, or to omit either Every new student edition of this book comes with an
of these topics. The one exception is statistics. Due Instant Access Code (bound inside the book). The code
to the natural progression of statistical topics, the provides access to the Data Analysis and Decision
basic topics in the early chapters should be covered Making, 4e textbook Web site that links to all of the
before the more advanced topics (regression and following files and tools:
time series analysis) in the later chapters. With this
in mind, there are several possible ways to cover the ■ DecisionTools® Suite software by Palisade
topics. Corporation (described earlier)
■ Excel files for the examples in the chapters
■ For a one-semester required course, with no (usually two versions of each—a template, or
statistics prerequisite (or where MBA students data-only version, and a finished version)
have forgotten whatever statistics they learned
■ Data files required for the problems and cases
years ago): If data analysis is the primary focus
of the course, then Chapters 2–5, 7–11, and ■ Excel Tutorial.xlsx, which contains a useful
possibly the online Chapter 17 (all statistics tutorial for getting up to speed in Excel 2007
and probability topics) should be covered. Students who do not have a new book can purchase
Depending on the time remaining, any of the access to the textbook Web site at www.
topics in Chapters 6 (decision making under CengageBrain.com.
uncertainty), 12 (time series analysis), 13–14
(optimization), or 15–16 (simulation) can be
covered in practically any order. Student Solutions
■ For a one-semester required course, with a Student Solutions to many of the odd-numbered prob-
statistics prerequisite: Assuming that students lems (indicated in the text with a colored box on the
know the basic elements of statistics (up problem number) are available in Excel format.
through hypothesis testing, say), the material Students can purchase access to Student Solutions
in Chapters 2–5 and 7–9 can be reviewed files on www.CengageBrain.com. (ISBN-10: 1-111-
quickly, primarily to illustrate how Excel and 52905-1; ISBN-13: 978-1-111-52905-5).
add-ins can be used to do the number
crunching. Then the instructor can choose
among any of the topics in Chapters 6, 10–11, Instructor ancillaries
12, 13–14, or 15–16 (in practically any order)
Adopting instructors can obtain the Instructors’ Reso-
to fill the remainder of the course.
urce CD (IRCD) from your regional Cengage Learning
■ For a two-semester required sequence: Given Sales Representative. The IRCD includes:
the luxury of spreading the topics over two
■ Problem Database.xlsx file (contains informa-
semesters, the entire book can be covered.
The statistics topics in Chapters 2–5 and 7–9 tion about all problems in the book and the
should be covered in order before other correspondence between them and those in the
statistical topics (regression and time series previous edition)
analysis), but the remaining chapters can be ■ Example files for all examples in the book,
covered in practically any order. including annotated versions with addi-
tional explanations and a few extra examples
that extend the examples in the book
Custom publishing ■ Solution files (in Excel format) for all of the
If you want to use only a subset of the text, or add problems and cases in the book and solution
chapters from the authors’ other texts or your own shells (templates) for selected problems in the
materials, you can do so through Cengage Learning modeling chapters
Custom Publishing. Contact your local Cengage ■ PowerPoint® presentation files for all of the
Learning representative for more details. examples in the book

Preface xv

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 ■ Test Bank in Word format and now also in We also extend our sincere appreciation to the
ExamView® Testing Software (new to this reviewers who provided feedback on the authors’ pro-
edition). posed changes that resulted in this fourth edition:
The book’s password-protected instructor Web site, Henry F. Ander, Arizona State University
www.cengage.com/decisionsciences/albright, includes James D. Behel, Harding University
the above items (Test Bank in Word format only), as
Dan Brooks, Arizona State University
well as software updates, errata, additional problems
and solutions, and additional resources for both stu- Robert H. Burgess, Georgia Institute of Technology
dents and faculty. The first author also maintains his George Cunningham III, Northwestern State University
own Web site at www.kelley.iu.edu/albrightbooks. Rex Cutshall, Indiana University
Robert M. Escudero, Pepperdine University
Acknowledgments Theodore S. Glickman, George Washington University
The authors would like to thank several people who John Gray, The Ohio State University
helped make this book a reality. First, the authors are Joe Hahn, Pepperdine University
indebted to Peter Kolesar, Mark Broadie, Lawrence Max Peter Hoefer, Pace University
Lapin, and William Whisler for contributing some of
Tim James, Arizona State University
the excellent case studies that appear throughout the
book. Teresa Jostes, Capital University
There are more people who helped to produce Jeffrey Keisler, University of Massachusetts – Boston
this book than we can list here. However, there are a David Kelton, University of Cincinnati
few special people whom we were happy (and lucky)
Shreevardhan Lele, University of Maryland
to have on our team. First, we would like to thank our
editor Charles McCormick. Charles stepped into this Ray Nelson, Brigham Young University
project after two editions had already been published, William Pearce, Geneva College
but the transition has been smooth and rewarding. Thomas R. Sexton, Stony Brook University
We appreciate his tireless efforts to make the book a
Malcolm T. Whitehead, Northwestern State University
continued success.
We are also grateful to many of the professionals Laura A. Wilson-Gentry, University of Baltimore
who worked behind the scenes to make this book a Jay Zagorsky, Boston University
success: Adam Marsh, Marketing Manager; Laura
S. Christian Albright
Ansara, Senior Developmental Editor; Nora Heink,
Editorial Assistant; Tim Bailey, Senior Content Project Wayne L. Winston
Manager; Stacy Shirley, Senior Art Director; and
Christopher J. Zappe
Gunjan Chandola, Senior Project Manager at MPS
Limited. May 2010

xvi Preface

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 CHAPTER

1 Introduction to Data Analysis and

Decision Making

George Doyle/Jupiter Images

HOTTEST NEW JOBS: STATISTICS AND
MATHEMATICS

M uch of this book, as the title implies, is about data analysis.The term
data analysis has long been synonymous with the term statistics, but
in today’s world, with massive amounts of data available in business and
many other fields such as health and science, data analysis goes beyond the
more narrowly focused area of traditional statistics. But regardless of what
we call it, data analysis is currently a hot topic and promises to get even
hotter in the future.The data analysis skills you learn here, and possibly in
follow-up quantitative courses, might just land you a very interesting and
lucrative job.
This is exactly the message in a recent New York Times article,“For
Today’s Graduate, Just One Word: Statistics,” by Steve Lohr. (A similar article,
“Math Will Rock Your World,” by Stephen Baker, was the cover story for

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 BusinessWeek. Both articles are available online by searching for their titles.) The statistics
article begins by chronicling a Harvard anthropology and archaeology graduate, Carrie
Grimes, who began her career by mapping the locations of Mayan artifacts in places like
Honduras. As she states,“People think of field archaeology as Indiana Jones, but much of
what you really do is data analysis.” Since then, Grimes has leveraged her data analysis
skills to get a job with Google, where she and many other people with a quantitative
background are analyzing huge amounts of data to improve the company’s search engine.
As the chief economist at Google, Hal Varian, states,“I keep saying that the sexy job in
the next 10 years will be statisticians.And I’m not kidding.” The salaries for statisticians
with doctoral degrees currently start at $125,000, and they will probably continue to
increase. (The math article indicates that mathematicians are also in great demand.)
Why is this trend occurring? The reason is the explosion of digital data—data
from sensor signals, surveillance tapes,Web clicks, bar scans, public records, financial
transactions, and more. In years past, statisticians typically analyzed relatively small
data sets, such as opinion polls with about 1000 responses.Today’s massive data
sets require new statistical methods, new computer software, and most importantly
for you, more young people trained in these methods and the corresponding
software. Several particular areas mentioned in the articles include (1) improving
Internet search and online advertising, (2) unraveling gene sequencing information
for cancer research, (3) analyzing sensor and location data for optimal handling of
food shipments, and (4) the recent Netflix contest for improving the company’s
recommendation system.
The statistics article mentions three specific organizations in need of data analysts—
and lots of them.The first is government, where there is an increasing need to sift through
mounds of data as a first step toward dealing with long-term economic needs and key policy
priorities.The second is IBM, which created a Business Analytics and Optimization Services
group in April 2009.This group will use the more than 200 mathematicians, statisticians,
and data analysts already employed by the company, but IBM intends to retrain or hire
4000 more analysts to meet its needs.The third is Google, which needs more data analysts
to improve its search engine.You may think that today’s search engines are unbelievably
efficient, but Google knows they can be improved.As Ms. Grimes states,“Even an improve-
ment of a percent or two can be huge, when you do things over the millions and billions
of times we do things at Google.”
Of course, these three organizations are not the only organizations that need to
hire more skilled people to perform data analysis and other analytical procedures. It is a
need faced by all large organizations.Various recent technologies, the most prominent by
far being the Web, have given organizations the ability to gather massive amounts of data
easily. Now they need people to make sense of it all and use it to their competitive
advantage. ■

1.1 INTRODUCTION
We are living in the age of technology. This has two important implications for everyone
entering the business world. First, technology has made it possible to collect huge amounts
of data. Retailers collect point-of-sale data on products and customers every time a trans-
action occurs; credit agencies have all sorts of data on people who have or would like
to obtain credit; investment companies have a limitless supply of data on the historical
patterns of stocks, bonds, and other securities; and government agencies have data on
economic trends, the environment, social welfare, consumer product safety, and virtually

2 Chapter 1 Introduction to Data Analysis and Decision Making

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 everything else imaginable. It has become relatively easy to collect the data. As a result,
data are plentiful. However, as many organizations are now beginning to discover, it is
quite a challenge to analyze and make sense of all the data they have collected.
A second important implication of technology is that it has given many more people
the power and responsibility to analyze data and make decisions on the basis of quantita-
tive analysis. People entering the business world can no longer pass all of the quantitative
analysis to the “quant jocks,” the technical specialists who have traditionally done the
number crunching. The vast majority of employees now have a desktop or laptop computer
at their disposal, access to relevant data, and training in easy-to-use software, particularly
spreadsheet and database software. For these employees, statistics and other quantitative
methods are no longer forgotten topics they once learned in college. Quantitative analysis
is now an integral part of their daily jobs.
A large amount of data already exists, and it will only increase in the future. Many
companies already complain of swimming in a sea of data. However, enlightened compa-
nies are seeing this expansion as a source of competitive advantage. By using quantitative
methods to uncover the information in the data and then acting on this information—again
guided by quantitative analysis—they are able to gain advantages that their less enlight-
ened competitors are not able to gain. Several pertinent examples of this follow.
■ Direct marketers analyze enormous customer databases to see which customers are
likely to respond to various products and types of promotions. Marketers can then
target different classes of customers in different ways to maximize profits—and give
their customers what they want.
■ Hotels and airlines also analyze enormous customer databases to see what their
customers want and are willing to pay for. By doing this, they have been able to
devise very clever pricing strategies, where different customers pay different prices
for the same accommodations. For example, a business traveler typically makes a
plane reservation closer to the time of travel than a vacationer. The airlines know this.
Therefore, they reserve seats for these business travelers and charge them a higher
price for the same seats. The airlines profit from clever pricing strategies, and the
customers are happy.
■ Financial planning services have a virtually unlimited supply of data about security
prices, and they have customers with widely differing preferences for various
types of investments. Trying to find a match of investments to customers is a very
challenging problem. However, customers can easily take their business elsewhere
if good decisions are not made on their behalf. Therefore, financial planners are
under extreme competitive pressure to analyze masses of data so that they can make
informed decisions for their customers.1
■ We all know about the pressures U.S. manufacturing companies have faced from
foreign competition in the past couple of decades. The automobile companies,
for example, have had to change the way they produce and market automobiles
to stay in business. They have had to improve quality and cut costs by orders of
magnitude. Although the struggle continues, much of the success they have had
can be attributed to data analysis and wise decision making. Starting on the shop
floor and moving up through the organization, these companies now measure
almost everything, analyze these measurements, and then act on the results of their
analysis.

1For a great overview of how quantitative techniques have been used in the financial world, read the book The
Quants, by Scott Patterson (Random House, 2010). It describes how quantitative models made millions for a lot
of bright young analysts, but it also describes the dangers of relying totally on quantitative models, at least in the
complex and global world of finance.

1.1 Introduction 3

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 We talk about companies analyzing data and making decisions. However, companies don’t
really do this; people do it. And who will these people be in the future? They will be you! We
know from experience that students in all areas of business, at both the undergraduate and
graduate level, will soon be required to describe large complex data sets, run regression
analyses, make quantitative forecasts, create optimization models, and run simulations. You
are the person who will soon be analyzing data and making important decisions to help your
company gain a competitive advantage. And if you are not willing or able to do so, there will
be plenty of other technically trained people who will be more than happy to replace you.
Our goal in this book is to teach you how to use a variety of quantitative methods to
analyze data and make decisions. We will do so in a very hands-on way. We will discuss
a number of quantitative methods and illustrate their use in a large variety of realistic
business situations. As you will see, this book includes many examples from finance,
marketing, operations, accounting, and other areas of business. To analyze these examples,
we will take advantage of the Microsoft Excel spreadsheet software, together with a number
of powerful Excel add-ins. In each example we will provide step-by-step details of the
method and its implementation in Excel.
This is not a “theory” book. It is also not a book where you can lean comfortably back
in your chair, prop your legs up on a table, and read about how other people use quantita-
tive methods. It is a “get your hands dirty” book, where you will learn best by actively
following the examples throughout the book at your own PC. In short, you will learn by
doing. By the time you have finished, you will have acquired some very useful skills for
today’s business world.

1.2 AN OVERVIEW OF THE BOOK

This book is packed with quantitative methods and examples, probably more than can
be covered in any single course. Therefore, we purposely intend to keep this introductory
chapter brief so that you can get on with the analysis. Nevertheless, it is useful to
introduce the methods you will be learning and the tools you will be using. In this section
we provide an overview of the methods covered in this book and the software that is used
to implement them. Then in the next section we present a brief discussion of models and
the modeling process. Our primary purpose at this point is to stimulate your interest in
what is to follow.

1.2.1 The Methods

This book is rather unique in that it combines topics from two separate fields: statistics
and management science. In a nutshell, statistics is the study of data analysis, whereas
management science is the study of model building, optimization, and decision making. In
the academic arena these two fields have traditionally been separated, sometimes widely.
Indeed, they are often housed in separate academic departments. However, from a user’s
standpoint it makes little sense to separate them. Both are useful in accomplishing what the
title of this book promises: data analysis and decision making.
Therefore, we do not distinguish between the statistics and the management science
parts of this book. Instead, we view the entire book as a collection of useful quantitative
methods that can be used to analyze data and help make business decisions. In addition, our
choice of software helps to integrate the various topics. By using a single package, Excel,
together with a number of add-ins, you will see that the methods of statistics and manage-
ment science are similar in many important respects. Most importantly, their combination
gives you the power and flexibility to solve a wide range of business problems.

4 Chapter 1 Introduction to Data Analysis and Decision Making

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
 Three important themes run through this book. Two of them are in the title: data analysis
and decision making. The third is dealing with uncertainty.2 Each of these themes has
subthemes. Data analysis includes data description, data inference, and the search for rela-
tionships in data. Decision making includes optimization techniques for problems with no
uncertainty, decision analysis for problems with uncertainty, and structured sensitivity
analysis. Dealing with uncertainty includes measuring uncertainty and modeling uncertainty
explicitly. There are obvious overlaps between these themes and subthemes. When you make
inferences from data and search for relationships in data, you must deal with uncertainty.
When you use decision trees to help make decisions, you must deal with uncertainty. When
you use simulation models to help make decisions, you must deal with uncertainty, and then
you often make inferences from the simulated data.
Figure 1.1 shows where you will find these themes and subthemes in the remaining
chapters of this book. In the next few paragraphs we discuss the book’s contents in more
detail.

Themes Subthemes Chapters Where Emphasized

Figure 1.1
Themes and 2, 3, 10, 12
Subthemes
7−9, 11

3, 10−12

13, 14

6, 13−16

4−12, 15−16

4−6, 10−12, 15−16

We begin in Chapters 2 and 3 by illustrating a number of ways to summarize the infor-

mation in data sets. These include graphical and tabular summaries, as well as numerical
summary measures such as means, medians, and standard deviations. The material in these
two chapters is elementary from a mathematical point of view, but it is extremely important.
As we stated at the beginning of this chapter, organizations are now able to collect huge
amounts of raw data, but what does it all mean? Although there are very sophisticated
methods for analyzing data sets, some of which we cover in later chapters, the “simple”
methods in Chapters 2 and 3 are crucial for obtaining an initial understanding of the data.
Fortunately, Excel and available add-ins now make what was once a very tedious task quite
easy. For example, Excel’s pivot table tool for “slicing and dicing” data is an analyst’s

2 The fact that the uncertainty theme did not find its way into the title of this book does not detract from its impor-
tance. We just wanted to keep the title reasonably short!

1.2 An Overview of the Book 5

Copyright 2010 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
Editorial review has deemed that any suppressed content does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
Another Random Scribd Document
with Unrelated Content
The Project Gutenberg eBook of The Details of
the Rocket System
 This ebook is for the use of anyone anywhere in the United
States and most other parts of the world at no cost and with
almost no restrictions whatsoever. You may copy it, give it away
or re-use it under the terms of the Project Gutenberg License
included with this ebook or online at www.gutenberg.org. If you
are not located in the United States, you will have to check the
laws of the country where you are located before using this
eBook.

Title: The Details of the Rocket System

Author: Sir William Congreve

Release date: August 28, 2018 [eBook #57791]

Language: English

Credits: Produced by Brian Coe, Charlie Howard, and the Online

Distributed Proofreading Team at http://www.pgdp.net
(This
file was produced from images generously made
available
by The Internet Archive)

*** START OF THE PROJECT GUTENBERG EBOOK THE DETAILS OF

THE ROCKET SYSTEM ***
 THE DETAILS
OF

THE ROCKET SYSTEM:

DRAWN UP BY

COLONEL CONGREVE

1814.

Reproduced from an original

edition made available by the
Library of the Royal Artillery
Institute, Woolwich, to whom
British Aircraft Corporation wish to
express their appreciation.

BRITISH AIRCRAFT CORPORATION GUIDED WEAPONS

DIVISION
 THE DETAILS
OF

THE ROCKET SYSTEM:

SHEWING

THE VARIOUS APPLICATIONS OF THIS WEAPON, BOTH FOR

SEA AND LAND SERVICE, AND ITS DIFFERENT USES IN THE
FIELD AND IN SIEGES;

ILLUSTRATED BY

PLATES OF THE PRINCIPAL EQUIPMENTS, EXERCISES, AND

CASES OF ACTUAL SERVICE,

WITH

GENERAL INSTRUCTIONS
FOR ITS APPLICATION,

AND A DEMONSTRATION OF THE COMPARATIVE ECONOMY OF THE

SYSTEM.

DRAWN UP BY

COLONEL CONGREVE,
FOR THE
INFORMATION OF THE OFFICERS OF THE ROCKET CORPS, AND OTHERS WHOM
IT MAY CONCERN.
 London:
PRINTED BY J. WHITING, FINSBURY PLACE.
1814.
 INTRODUCTION.
His Royal Highness the Prince Regent, to whose
gracious patronage the Rocket System owes its existence, having
been pleased to command the formation of a Rocket Corps, on the
1st of January, 1814, by augmentation to the Regiment of Artillery,
as proposed by his Lordship, the Earl of Mulgrave, Master General of
the Ordnance; I have thought it my duty to draw up the following
details of the System, for the Instruction of the Officers of the Corps,
for the information of the General Officers of the British Army, and
that of such departments as it is important for the good of the
service, to make acquainted with the principles of this new branch of
our naval and military means of offence and defence.
I have, indeed, conceived it the more incumbent upon me to
prepare such a document for the use of the Rocket Corps, with as
much expedition as possible, that nothing might be wanting on my
part towards its completion, having been induced to decline the offer
graciously made me of commanding it, with rank in the Regiment of
Artillery; a decision, in which I trust I have sufficiently proved myself
to have been actuated by the most sincere desire of manifesting my
attachment to that Regiment; as, however flattering the offer, it was
sufficient gratification to me to have brought my labours to a
consummation, which enabled me to leave the undivided benefit of
this new Corps in their possession: and to have succeeded in putting
into their hands a weapon, which it is my greatest pride to have
already seen adding to their laurels, in the Plains of Leipsic, and on
the Banks of the Adour; a weapon, which has so early given them
pledges of future and greater successes, and which I hope the
following pages will evince to have already been brought to a state
of organization and perfection, at least commensurate with its age. I
will hope, also, that the further progress and extension of the
powers of the Rocket System will be such as not to discredit the
discernment of the enlightened Prince, who first patronized it, or
that of his Lordship, the Master General, by whose protection it is
now placed on a permanent establishment. It is almost needless to
add, that this volume is intended only for the use and instruction of
such as it may concern, and not in any way for publication.

WILLIAM CONGREVE.
 TABLE OF CONTENTS.

Introduction.

General Instructions.

Formation of a Rocket Troop.

Plate 1.— The Equipment of a Rocket Trooper.

Plate 2.— The Equipment of a Rocket Ammunition Horse.

Plate 3.— Fig. 1.—A Sub-division of Rocket Cavalry, in Line of March.

Fig. 2.—A Sub-division of Rocket Cavalry, in Action.

Plate 4.— Fig. 1.—Rocket Cars, in Line of March.

Fig. 2.—Rocket Cars, in Action.

Plate 5.— Fig. 1.—Rocket Infantry, in Line of March.

Fig. 2.—Rocket Infantry, in Action.

Plate 6.— Fig. 1.—The Conveyance of the Apparatus and Rocket

Ammunition for Bombardment.
Fig. 2.—The Firing of Rockets, in Bombardment.

Plate 7.— Fig. 1, and 2.—The Projecting of Rockets from different

Descriptions of Earth Works, in Bombardment.

Plate 8.— Fig. 1.—A Rocket Ambuscade.

Fig. 2.—The Use of Rockets for the Defence of a Post.
Plate 9.— Fig. 1.—The Use of Rockets, in the Attack of a Fortress.
Fig. 2.—The Use of Rockets, in the Defense of a Fortress.

Plate 10.— Fig. 1.—A Repulse of Cavalry by Infantry, with Rockets.

Fig. 2.—Preparation for storming, by Means of Rockets.

Plate 11.— The Throwing of Rockets from Men of War’s Boats.

Plate 12.— Fig. 1.—The Use of Rockets in Fire Ships.

Fig. 2, 3, and 4.—The Equipment of a Rocket Ship, with
Scuttles for throwing Rockets from her Broadside.

Plate 13.— The different Natures of Rocket Ammunition, and the

Implements used for fixing the Sticks.

Conclusion containing Calculations, proving the great comparative

— Economy of the Rocket System in all its Branches.
 General Instructions for the Use of
Rockets, both in the Field and in
Bombardment, shewing the Spirit of
the System, and its comparative
Powers and Facilities.
It must be laid down as a maxim, that “the very essence and spirit
of the Rocket System is the facility of firing a great number of
rounds in a short time, or even instantaneously, with small means,”
arising from this circumstance, that the Rocket is a species of fixed
ammunition which does not require ordnance to project it; and
which, where apparatus is required, admits of that apparatus being
of the most simple and portable kind.
An officer, therefore, having the use of this weapon under his
direction, must ever bear this maxim in mind—and his first
consideration must be—to make his discharges against the enemy in
as powerful vollies as he possibly can.
Thus—if the defence of a post be entrusted to him, and the
ground be at all favourable, he will, independent of the regular
apparatus he may have at his disposal, prepare what may be called
Rocket Batteries, consisting of as many embrasures as his ground
will admit; these embrasures being formed by turning up the sod, so
as to give channels of direction four or five feet long, and three feet
apart: by which a great number of Rockets in a volley may evidently
be arranged to defend any assailable point. In these embrasures, if
liable to surprise, the Rockets may be placed in readiness the vents
not uncovered; though generally speaking, this is not necessary, as
so short a time is required to place them—here and there one, only
being in its embrasure.
In battle also, where there is not, of course, time to prepare the
ground as above stated, but where it is tolerably level, he may, in
addition to the apparatus he possesses, add to his fire by
discharging, from the intervals of his frames or cars, Rockets merely
laid on the ground in the direction required: and, if an enemy be
advancing upon him, there is, in fact, no limit to the volley he may
be prepared thus to give, when at a proper distance, but the
quantity of ammunition he possesses, the extension of his own
ground, and the importance of the object to be fired at. Under these
limits, he may chuse his volley from 50 to 500—a fire which, if
judiciously laid in, must nearly annihilate his enemy: for this purpose
trains are provided. This practice also requires the exposure of only
one or two men, who are to fire the volley, as the remainder, with
the ammunition, may be under cover. And here it should be
remarked, that the length of ranges, and the height of the curve of
the recochét, in this mode of firing, depend on the length of the
stick—the stick of the full length giving the longest range, but rising
the highest from the ground; the reduced stick giving a shorter
range, but keeping closer to the ground. From this application,
therefore, where practicable, by carrying a certain number of the 12-
pounder pouches in the ammunition waggon, an officer, even with a
dismounted brigade, may always manœuvre and detach parties to
get upon the flanks of any approaching or fixed column, square, or
battalion, while he himself remains with the heavier ammunition and
cars in front.
This mode of firing from the ground of course applies only for
moderate distances; the limits of which, with the smaller natures of
Rockets, may be considered from 800 to 1,000 yards, and for the
larger from 1,000 to 1,200; where therefore greater ranges are
required, the apparatus must be resorted to. And here it is proper to
remark, that in the use of the Rocket, at least in the present state of
the system, no certain increase of range can be depended upon by
increasing the elevations from the ground-ranges up to 15°, for the
smaller Rockets; and 20 to 25° for the larger; for in the intermediate
angles, the Rocket is apt to drop in going off, and graze near the
frame; but at the above angles it will always proceed in a single
curve to very greatly increased ranges from 1,500 to 2,000 yards.
In bombardment, as well as in the field, the quantity of
instantaneous fire is equally important, and the greater number of
Rockets that can be thrown, not only increase the number of fires,
but, by distracting the enemy’s attention, prevent their extinction. To
this end, therefore, an officer should always employ as many
bombarding frames as possible; and here again he will find, that in
bombardment, as well as in the field, the weapon affords him the
means of extending his fire beyond the compass of his apparatus.
Thus, he may form a Rocket Battery of any common
epaulement, parallel to the face of the town to be bombarded, by
digging a trench in the rear of it to admit the stick, so as to lay the
Rocket and stick against the slope of the epaulement, that slope
being brought to the desired elevation for projecting the Rocket, or
by boring holes to receive the stick; or he may construct a slope
expressly as a Rocket Battery; and as, in firing these vollies, his
Rockets need not be more than three feet apart, it follows, that from
an epaulement or battery of this description, fifty yards in length, he
may keep up this bombardment by a discharge of fifty Rockets in a
volley, and repeat these vollies every five minutes if desirable; a rate
of firing which must inevitably baffle all attempts of the most active
and numerous enemy to prevent its effect.
It is obvious, therefore, that in any comparison made of the
powers of the Rocket with those of common artillery, whether an
officer be called on merely to demonstrate its powers, or to carry it
actually against an enemy, the foregoing maxim must be his rule; in
fact, every thing should be demonstrated according to the spirit of
its use; a single Rocket is not to be compared with a single gun shot,
by firing it at a target. But the consideration is, whether for general
service, the power of quantity in the fire of Rockets does not at least
counterbalance the greater accuracy of the gun? and for this
purpose the spirit of the demonstration of the Rocket system is to
shew how few men are required to produce the most powerful
vollies with this arm. No demonstration should be made with less
than twenty rounds in a volley; to maintain which, in any fixed
position, at the rate of two or even three vollies a minute, twenty
men may be said to be sufficient, and this with Rockets projecting
cohorn, or 5½-inch howitzer shells, or even 18 and 24-pounder solid
shot. The first point of comparison, therefore, is—How many rounds
of such ammunition in the minute could twenty men project by the
ordinary means of artillery?—or how many in a volley, even if they
had all the means at hand?—And the next point is—what are the
comparative facilities in bringing these different means into action,
where the one system requires only the transport of the ammunition
—the other, not only that of the ammunition, but of the most
massive ordnance, without which it is entirely useless?
But independent of this comparison as to quantity, there are
others in which the Rocket has advantages exclusively its own: there
are situations where artillery cannot by any means be brought into
action, while there is no situation, no nature of ground, which is
passable to an infantry soldier with his musket in his hand, that is
not equally to be passed by the Rocketteer with his arm and
ammunition. For the accomplishment of any particular service, he
may dispense entirely with wheel carriages or even horses; there is
nothing which the men themselves cannot transport and bring into
action; and if any bombardment were required by a coup de main,
1,000 men would not only convey 1,000 rounds of the heaviest
Carcass Rockets, a number sufficient to destroy any place within the
compass of their range, but would perform that service in a few
hours, having neither batteries or platforms to erect, nor mortars to
convey.
Such are the true principles of this new system of artillery, for
(projecting the same ammunition) so it may be called, and the
greater the scale of equipment, the greater in proportion will its
powers appear; thus, if an establishment were formed on the
strength of a cavalry regiment, if 600 mounted men were equipped
on the principles of the present detachment, they would take into
action, without ammunition horses or wheel carriages, 2,400 rounds
of ammunition, and 200 abouches a féu; and if 100 ammunition
horses were attached to this corps, it would further possess a
reserve of nearly 2,000 rounds more: the whole capable of every
movement and service practicable by any other regiment of heavy
cavalry; and the same proportionate power would be found to attach
to every other mode of equipment.
In addition to this view of the powers of the weapon, it is
important to state, that the detail of the service is most
extraordinarily simple; that there are but a few points to be attended
to in its application; and those such as may be most easily acquired;
the principal ones are, that care must be taken to fix the sticks very
firmly to the Rocket, and in the true direction of the axis of the
Rocket, to prevent aberration of flight.
That, at high angles, the frame must always be elevated for the
large Rockets from 5° to 10° more than the elevation at which the
Rocket is intended to be projected, and in the small Rockets from
2½° to 5°; for, as the Rocket leaves the frame before it has obtained
its full force, it drops a certain number of degrees in proportion to its
weight at going off. Thus the longest ranges of the 32-pounder
Carcass Rockets are obtained at about 55°, or rather more, if the
Rockets have been long made. An officer, however, being prepared
for this circumstance, will soon discover the maximum range of the
Rockets he may have to discharge.
Some allowance in elevation also must be made for the direction
of the wind: if it is powerful, and blows in a contrary direction to that
in which the Rocket is projected, the frame requires more elevation;
for the wind acting more on the stick than the body of the Rocket,
depresses the elevation in its rising. If, on the contrary, it blows in
the direction of the Rocket’s flight, less elevation is required; for, in
this case, the Rocket mounts by the wind’s action on the stick. So,
from the same cause, if the wind be strong, and across the range,
though no difference of elevation is necessary, still an allowance
must be made to leeward; for the Rocket, contrary to the course of
ordinary projectiles, has a tendency to draw to windward: a few
rounds, however, in all these cases, will immediately point out to the
observant officer what is the required allowance. These remarks
refer only to high angles; for no effect whatever is produced by the
wind in the ground-ranges: in these the only caution necessary to be
attended to is, to chuse the most smooth and level spot for the first
100 yards in front of the point from which it is intended to discharge
these Rockets, as they generally travel in contact with the surface for
this distance, not having acquired their full force, and are therefore
more liable to deflection; but having at this point acquired a velocity
not much less than the mean velocity of a cannon ball, they are not
to be more easily deflected: at this distance also they rise a few feet
from the ground, so as to clear any ordinary obstacles that may
occur; insomuch that, if it were desired to fire Rockets at low angles
into a besieged town, from the third parallel, these Rockets, having a
clear space to acquire their velocity, in front of the parallel, would
run up the glacis, clear the ditch, and skim over the parapet into the
town; and would no doubt be of great use in a variety of cases,
particularly in discomfiting and rendering the enemy unsteady, by
pouring in vollies of some hundreds or even thousands on this
principle, previous to an assault or escalade: indeed, knowing the
effect, I do not hesitate to affirm that this manœuvre, practised on
the great scale, would infallibly dislodge any enemy posted for the
protection of a breach.
Sufficient has, I conceive, now been stated, to give the officer
such a general view of the power and spirit of the weapon, as may
enable him to apply it in all possible cases to the best advantage;
and if he will but constantly bear in view that maxim which I have
laid down as the fundamental principle of this system, I will
confidently pledge myself that it will never disappoint him, either as
to the physical or moral effect which he may calculate on producing
upon his enemy; since, he must recollect, that for this latter effect, it
adds all the terrors of visibility to every species of that destructive
ammunition introduced by the use of gunpowder, but by every one
admitted hitherto to have been qualified, as to moral effect, by its
invisibility.
25th October, 1813.
W. CONGREVE.

Note.—All the cases of service referred to in the above instructions, will be found
particularly detailed in the following plates.
CONSTITUTION AND STRENGTH OF
A TROOP OF ROCKET HORSE
ARTILLERY.
A Troop is proposed to consist of three divisions.
Each division to be divided into two sub-divisions.
Each sub-division to consist of five sections of three men each,
and two drivers leading four ammunition horses, each mounted man
carrying into action four rounds of 12-pounder Rocket ammunition,
and each ammunition horse eighteen rounds; thus:
Each section carries 12 rounds of ammunition into action, and
one bouche a feù, and, consequently, each sub-division will have five
bouches a feù, and 140 rounds of ammunition: so that the whole
troop, consisting of six of those sub-divisions, will amount to 102
mounted men, and 24 ammunition horses, and will take into action,
without any wheel carriage, 30 bouches a feù, and 840 rounds of
ammunition.
It is, however, further proposed to attach to each division two
Rocket cars, one heavy and one light, the first carrying four men
with 40 rounds of 24-pounder Rockets, armed with cohorn shells,
the latter carrying two men, and 60 rounds of 12-pounder
ammunition. Each of these cars is capable of discharging two
Rockets in a volley.
It is proposed, also, to attach to each sub-division a curricle
ammunition cart, or tumbril, for two horses, to carry, in line of
march, three rounds out of four of each mounted man’s Rockets, to
ease the horse: and, in action, when every man carries his full
complement of ammunition on horseback, these cars may contain a
reserve of 60 rounds more for each sub-division, making the whole
amount of ammunition, for each sub-division, 200 rounds. With this
addition, therefore, the whole strength of the Rocket troop will stand
thus:

Officers 5
Non-commissioned Officers 15
Troopers 90
Drivers 60
Artificers 8
Cars, heavy 3
Cars, light 3
Curricle ammunition carts, or tumbrils 6
Bouches a feù 42
Ammunition, heavy shell 260
Ammunition, light shell, or case shot 1200
Making a total of
Ammunition of all sorts 1460 rounds.
Battery of bouches a
42 feù.
Cars, tumbrils, and forge cart 13
Officers, staff artificers, troopers, and
drivers 172
Troop, ammunition, and draft horses 164

The number of sections in a sub-division may vary according to

the actual effective strength of the troop at any time; so that the
distribution may be accommodated to the numbers, without
departing from this principle of constitution. The number of men and
horses above stated is precisely the same as that of a troop of horse
artillery.
 The reserve of ammunition is supposed to proceed with the
park.
 THE EQUIPMENT OF ROCKET
CAVALRY.
Plate 1st represents the mode of equipment for carrying Rockets
on horseback, as it was arranged during the course of experiments,
which were carried on, under my direction, at Bagshot, in 1811; as it
was subsequently carried into actual service, under Captain Bogue,
with the Allied armies in Germany, in the ever memorable campaign
of 1813; and as it is at present proposed to equip the new corps of
Rocket Horse Artillery, established on the 1st of January, 1814, by
Earl Mulgrave, Master General of the Ordnance, and composed of two
troops, under the command of Lieutenant Colonel Fisher, of the
Royal Artillery.
The right hand figure represents a trooper completely armed
and equipped, in review order. The left hand figure is a delineation
of the same, with the shabracque removed, to shew the holsters in
which the Rockets are conveyed. These holsters each contain two
12-pounder Rockets, each Rocket armed with a 6-pounder shell, or
case shot; they are connected together at top, and are supported by
the pummel of the saddle, which is made in the hussar fashion,
though the saddle itself is, in fact, formed and stuffed the same as a
common English saddle. This projection in front keeps the holsters
clear of the horse’s withers and shoulders, which, from their size, it
might otherwise be difficult to do; for the latter of these purposes,
also, the flap of the saddle comes further forward than usual. The
holsters, thus connected, slip on and off from the pummel with great
facility, which is an object of importance, as a part of the service of
the Rocket trooper is, when from some impassable obstacle, he can
no longer advance on horseback, to dismount and pass over such
obstacle, with his ammunition holsters and chamber, on foot. The
sticks, which are seven feet in length, and four in number, answering
to the number of Rockets, are collected in a bundle by means of a
strap with four loops, contrived on purpose, and are carried on the
off-side, the thicker ends being supported in a bucket, suspended
from the flap of the saddle, the strap above mentioned, as confining
them together in the middle, leading across the man’s thigh to the
peak of the saddle; by this means they fall naturally under his right
arm, without at all incommoding him, either in mounting or
dismounting, or even in going through the sword exercise. By this
arrangement also, they are easily drawn from the bundle
downwards, for fixing to the Rocket, leaving any number that may
remain as securely fixed as when the whole are in the quiver.
It has already been stated, that the men are told off in sections
of threes. They are accordingly numbered 1, 2, and 3. Now numbers
1 and 3 have nothing to carry but their proportion of the
ammunition, viz. four Rockets and four sticks each, while No. 2 has
in addition to carry the chamber from which the Rockets of his
section are discharged. This chamber is a small iron plate trough,
about one foot six inches in length, capable of being fixed steadily in
the ground by four iron points at the bottom of it, so that the
Rockets may be discharged parallel to the surface and close to it.
The weight of this chamber, or bouche a feù, is about six lbs. and it
is carried in a small leather case, shewn in both these figures, just at
the back of the valise.
The men are armed with a sabre, which is in action suspended
to the saddle, that they may not be incumbered in mounting and
dismounting. Each man has besides a pistol in his cross belt, and a
spear head in his holster, which may be occasionally fixed at the end
of one of the Rocket sticks, so as to give the further aid of a very
formidable lance. Instead of carrying slow match, which would be
dangerous as well as inconvenient, the portfire is lighted in action by
a flash of powder obtained from a pistol lock and pan, mounted on a
small stock; and a light portfire stick for discharging the Rocket,
about three feet in length, is constructed of a thin iron tube, which
shuts up, and is carried in the holster. The sticks are fastened in the
loops on the Rocket case, either by the gripe of a pair of pincers
with points in them, or by the stroke of a small hammer with a point
in the head, or by some equally simple tool. Every part of this
equipment, except the sticks, is so completely concealed by the
shabracque, that the Rocket trooper has the appearance merely of a
lancer.
The weight of ammunition carried by the troop horse, with the
full complement going into action, is three stone six lbs.; to which
the horse is fully equal for any ordinary operation. But in long
marches, it would be not only useless but improvident to burthen
him to this extent; small tumbrils, therefore, are provided to convey
three rounds of each man’s Rockets, he still carrying one round on
the near side, and the four sticks on the off side to balance, which
leaves the horse, in travelling, only one stone four lbs. weight of
ammunition to carry; a burthen of two stone less on line of march,
than that of the heavy dragoon’s or artillery-man’s horse; allowing
for the difference of the weight of the men requisite for the
respective services. The Rocket trooper has no heavy weights to lift
—no guns to spunge, or to limber up and unlimber. He is required
merely to be light and active for mounting and dismounting, and for
moving nimbly on foot with a single Rocket, when in action: so that,
whereas an artillery man cannot average less than 13 stone, the
Rocket trooper need not exceed 10 stone, a difference amounting
within a few pounds to the whole weight of ammunition carried by
the men, even in action. It is needless to add that this difference in
the men must also give great facility in recruiting for a Rocket corps.

Plate 1
 OF THE EQUIPMENT OF THE
AMMUNITION HORSE.
Plate 2 represents the mode of equipping the Ammunition
Horses.
The left hand figure shews that the whole of the ammunition,
&c. may be completely covered and protected from the weather by a
painted canvass; and the other has this cover off, to shew the
particular distribution of the load, which consists of eighteen Rockets
and Rocket sticks, and a proportion of small stores, such as portfires,
slow match, &c.
This load is carried on a bat saddle, made as small and as light
as possible, with a pad at the back part of it, extending towards the
crupper. The saddle is furnished on the top with two iron forks to
receive a leather case, in which the sticks are carried in half lengths,
of three feet six inches each, a length from which no inconvenience
arises; being contrived so that the two parts may be united, to form
the stick complete in a moment, by means of a ferule fixed to one
end and receiving the other; in which situation they are firmly fixed
and connected, either by a pair of pointed pincers, by a hammer
with a point in the head, or by a wrench. When these sticks are
taken from the Ammunition Horse, to replenish the stock of the
mounted men, they are to be joined at that time by the simple,
secure, and momentary operation just mentioned.
The Rockets are carried in a sort of saddle bags, as they may be
termed, stitched into separate compartments for each Rocket,
covered by a flap at one end, and secured by a chain, staples, and
padlocks, the Rocket lying horizontally. By this arrangement the load