Essentials of Business Analytics 1st Edition

(eBook PDF) install download

https://ebookluna.com/product/essentials-of-business-
analytics-1st-edition-ebook-pdf/

Download more ebook instantly today - Get yours now at ebookluna.com

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

(eBook PDF) Essentials of Business Analytics 1st Jeffrey D. Camm

https://ebookluna.com/product/ebook-pdf-essentials-of-business-
analytics-1st-jeffrey-d-camm/

(eBook PDF) Essentials of Business Analytics 2nd Edition

https://ebookluna.com/product/ebook-pdf-essentials-of-business-
analytics-2nd-edition/

(eBook PDF) Business Analytics 1st Edition By Sanjiv Jaggia

https://ebookluna.com/product/ebook-pdf-business-analytics-1st-edition-by-
sanjiv-jaggia/

Progress in Heterocyclic Chemistry Volume 29 1st Edition - eBook PDF

https://ebookluna.com/download/progress-in-heterocyclic-chemistry-ebook-
pdf/
(eBook PDF) Essentials of Business Statistics, 1st Canadian Edition by Ken
Black

https://ebookluna.com/product/ebook-pdf-essentials-of-business-
statistics-1st-canadian-edition-by-ken-black/

(eBook PDF) Business Analytics: A Management Approach

https://ebookluna.com/product/ebook-pdf-business-analytics-a-management-
approach/

(eBook PDF) Business Analytics: The Art of Modeling With Spreadsheets, 5th
Edition

https://ebookluna.com/product/ebook-pdf-business-analytics-the-art-of-
modeling-with-spreadsheets-5th-edition/

(eBook PDF) Business Intelligence and Analytics 10th Edition

https://ebookluna.com/product/ebook-pdf-business-intelligence-and-
analytics-10th-edition/

Essentials of Business Law 9th Edition (eBook PDF)

https://ebookluna.com/product/essentials-of-business-law-9th-edition-ebook-
pdf/
Contents vii

Bar Charts and Column Charts 90

A Note on Pie Charts and 3-D Charts 93
Bubble Charts 93
Heat Maps 95
Additional Charts for Multiple Variables 97
PivotCharts in Excel 101
3.4 Advanced Data Visualization 102
Advanced Charts 103
Geographic Information Systems Charts 104
3.5 Data Dashboards 105
Principles of Effective Data Dashboards 106
Applications of Data Dashboards 106
Summary 108
Glossary 109
Problems 110
Case Problem: All-Time Movie Box Office Data 118
Appendix: Creating a Scatter Chart Matrix and a Parallel Coordinates
Plot with XLMiner 119

Chapter 4 Linear Regression 123

Analytics in Action: Alliance Data Systems 124
4.1 The Simple Linear Regression Model 125
Regression Model and Regression Equation 125
Estimated Regression Equation 126
4.2 Least Squares Method 127
Least Squares Estimates of the Regression Parameters 129
Using Excel’s Chart Tools to Compute the Estimated Regression
Equation 132
4.3 Assessing the Fit of the Simple Linear Regression Model 133
The Sums of Squares 134
The Coefficient of Determination 136
Using Excel’s Chart Tools to Compute the Coefficient of
Determination 137
4.4 The Multiple Regression Model 138
Regression Model and Regression Equation 138
Estimated Multiple Regression Equation 138
Least Squares Method and Multiple Regression 139
Butler Trucking Company and Multiple Regression 140
Using Excel’s Regression Tool to Develop the Estimated Multiple
Regression Equation 140
4.5 Inference and Regression 143
Conditions Necessary for Valid Inference in the Least Squares
Regression Model 144
viii Contents

Testing Individual Regression Parameters 150

Addressing Nonsignificant Independent Variables 153
Multicollinearity 154
Inference and Very Large Samples 156
4.6 Categorical Independent Variables 161
Butler Trucking Company and Rush Hour 161
Interpreting the Parameters 162
More Complex Categorical Variables 164
4.7 Modeling Nonlinear Relationships 165
Quadratic Regression Models 167
Piecewise Linear Regression Models 170
Interaction Between Independent Variables 173
4.8 Model Fitting 177
Variable Selection Procedures 177
Overfitting 179
Summary 180
Glossary 180
Problems 182
Case Problem: Alumni Giving 197
Appendix: Using XLMiner for Regression 198

Chapter 5 Time Series Analysis and Forecasting 202

Analytics in Action: Forecasting Demand for a Broad Line
of Office Products 203
5.1 Time Series Patterns 205
Horizontal Pattern 205
Trend Pattern 207
Seasonal Pattern 209
Trend and Seasonal Pattern 209
Cyclical Pattern 211
Identifying Time Series Patterns 212
5.2 Forecast Accuracy 212
5.3 Moving Averages and Exponential Smoothing 217
Moving Averages 217
Forecast Accuracy 221
Exponential Smoothing 221
Forecast Accuracy 224
5.4 Using Regression Analysis for Forecasting 226
Linear Trend Projection 226
Seasonality 228
Seasonality Without Trend 228
Seasonality with Trend 230
Using Regression Analysis as a Causal Forecasting Method 231
Contents ix

Combining Causal Variables with Trend and Seasonality

Effects 235
Considerations in Using Regression in Forecasting 235
5.5 Determining the Best Forecasting Model to Use 236
Summary 237
Glossary 237
Problems 238
Case Problem: Forecasting Food and Beverage Sales 246
Appendix: Using XLMiner for Forecasting 247

Chapter 6 Data Mining 251

Analytics in Action: Online Retailers Using Predictive Analytics
to Cater to Customers 252
6.1 Data Sampling 253
6.2 Data Preparation 254
Treatment of Missing Data 254
Identification of Outliers and Erroneous Data 254
Variable Representation 254
6.3 Unsupervised Learning 255
Cluster Analysis 256
Association Rules 265
6.4 Supervised Learning 269
Partitioning Data 269
Classification Accuracy 273
Prediction Accuracy 277
k-Nearest Neighbors 277
Classification and Regression Trees 283
Logistic Regression 299
Summary 308
Glossary 309
Problems 311
Case Problem: Grey Code Corporation 319

Chapter 7 Spreadsheet Models 320

Analytics in Action: Procter and Gamble Sets Inventory Targets Using
Spreadsheet Models 321
7.1 Building Good Spreadsheet Models 322
Influence Diagrams 322
Building a Mathematical Model 322
Spreadsheet Design and Implementing the Model
in a Spreadsheet 324
x Contents

7.2 What-If Analysis 327

Data Tables 327
Goal Seek 331
7.3 Some Useful Excel Functions for Modeling 332
SUM and SUMPRODUCT 332
IF and COUNTIF 333
VLOOKUP 337
7.4 Auditing Spreadsheet Models 339
Trace Precedents and Dependents 339
Show Formulas 340
Evaluate Formulas 340
Error Checking 341
Watch Window 342
Summary 343
Glossary 343
Problems 344
Case Problem: Retirement Plan 350

Chapter 8 Linear Optimization Models 352

Analytics in Action: Timber Harvesting Model at MeadWestvaco
Corporation 353
8.1 A Simple Maximization Problem 354
Problem Formulation 355
Mathematical Model for the Par, Inc. Problem 357
8.2 Solving the Par, Inc. Problem 358
The Geometry of the Par, Inc. Problem 358
Solving Linear Programs with Excel Solver 360
8.3 A Simple Minimization Problem 364
Problem Formulation 364
Solution for the M&D Chemicals Problem 365
8.4 Special Cases of Linear Program Outcomes 367
Alternative Optimal Solutions 367
Infeasibility 368
Unbounded 370
8.5 Sensitivity Analysis 372
Interpreting Excel Solver Sensitivity Report 372
8.6 General Linear Programming Notation and More Examples 374
Investment Portfolio Selection 375
Transportation Planning 378
Advertising Campaign Planning 381
8.7 Generating an Alternative Optimal Solution for a Linear Program 386
Summary 388
Glossary 389
Contents xi

Problems 390
Case Problem: Investment Strategy 398
Appendix: Solving Linear Optimization Models Using Analytic Solver
Platform 399

Chapter 9 Integer Linear Optimization Models 405

Analytics in Action: Optimizing the Transport of Oil Rig Crews 406
9.1 Types of Integer Linear Optimization Models 406
9.2 Eastborne Realty, An Example of Integer Optimization 407
The Geometry of Linear All-Integer Optimization 408
9.3 Solving Integer Optimization Problems with Excel Solver 410
A Cautionary Note About Sensitivity Analysis 414
9.4 Applications Involving Binary Variables 415
Capital Budgeting 415
Fixed Cost 416
Bank Location 420
Product Design and Market Share Optimization 424
9.5 Modeling Flexibility Provided by Binary Variables 426
Multiple-Choice and Mutually Exclusive Constraints 427
k out of n Alternatives Constraint 427
Conditional and Corequisite Constraints 427
9.6 Generating Alternatives in Binary Optimization 428
Summary 430
Glossary 430
Problems 431
Case Problem: Applecore Children’s Clothing 441
Appendix: Solving Integer Linear Optimization Problems Using Analytic
Solver Platform 442

Chapter 10 Nonlinear Optimization Models 448

Analytics in Action: Intercontinental Hotels Optimizes Retail Pricing 449
10.1 A Production Application: Par, Inc. Revisited 449
An Unconstrained Problem 450
A Constrained Problem 450
Solving Nonlinear Optimization Models Using Excel Solver 453
Sensitivity Analysis and Shadow Prices in Nonlinear Models 454
10.2 Local and Global Optima 455
Overcoming Local Optima with Excel Solver 457
10.3 A Location Problem 459
10.4 Markowitz Portfolio Model 461
10.5 Forecasting Adoption of a New Product 465
xii Contents

Summary 469
Glossary 470
Problems 470
Case Problem: Portfolio Optimization with Transaction Costs 477
Appendix: Solving Nonlinear Optimization Problems with Analytic
Solver Platform 480

Chapter 11 Monte Carlo Simulation 485

Analytics in Action: Reducing Patient Infections in the ICU 486
11.1 What-If Analysis 487
The Sanotronics Problem 487
Base-Case Scenario 487
Worst-Case Scenario 488
Best-Case Scenario 488
11.2 Simulation Modeling with Native Excel Functions 488
Use of Probability Distributions to Represent
Random Variables 489
Generating Values for Random Variables with Excel 491
Executing Simulation Trials with Excel 495
Measuring and Analyzing Simulation Output 495
11.3 Simulation Modeling with Analytic Solver Platform 498
The Land Shark Problem 499
Spreadsheet Model for Land Shark 499
Generating Values for Land Shark’s Random Variables 500
Tracking Output Measures for Land Shark 503
Executing Simulation Trials and Analyzing Output for Land Shark 504
The Zappos Problem 506
Spreadsheet Model for Zappos 507
Modeling Random Variables for Zappos 510
Tracking Output Measures for Zappos 515
Executing Simulation Trials and Analyzing Output for Zappos 517
11.4 Simulation Optimization 518
11.5 Simulation Considerations 524
Verification and Validation 524
Advantages and Disadvantages of Using Simulation 524
Summary 525
Glossary 526
Problems 527
Case Problem: Four Corners 536
Appendix 11.1: Incorporating Dependence Between
Random Variables 537
Appendix 11.2: Probability Distributions for Random Variables 545
Contents xiii

Chapter 12 Decision Analysis 550

Analytics in Action: Phytopharm’s New Product Research and
Development 551
12.1 Problem Formulation 552
Payoff Tables 553
Decision Trees 553
12.2 Decision Analysis Without Probabilities 554
Optimistic Approach 554
Conservative Approach 555
Minimax Regret Approach 555
12.3 Decision Analysis with Probabilities 557
Expected Value Approach 557
Risk Analysis 559
Sensitivity Analysis 560
12.4 Decision Analysis with Sample Information 561
Expected Value of Sample Information 566
Expected Value of Perfect Information 567
12.5 Computing Branch Probabilities with Bayes’ Theorem 568
12.6 Utility Theory 571
Utility and Decision Analysis 573
Utility Functions 577
Exponential Utility Function 580
Summary 581
Glossary 582
Problems 584
Case Problem: Property Purchase Strategy 595
Appendix: Using Analytic Solver Platform to Create Decision Trees 596

Appendix A Basics of Excel 609

Appendix B Data Management and Microsoft Access 621

Appendix C Answers to Even-Numbered Exercises (online)

References 659
Index 661
About the Authors

Jeffrey D. Camm Jeffrey D. Camm is Professor of Quantitative Analysis, Head of the

Department of Operations, Business Analytics, and Information Systems and College of
Business Research Fellow in the Carl H. Lindner College of Business at the University of
Cincinnati. Born in Cincinnati, Ohio, he holds a B.S. from Xavier University and a Ph.D.
from Clemson University. He has been at the University of Cincinnati since 1984, and has
been a visiting scholar at Stanford University and a visiting professor of business adminis-
tration at the Tuck School of Business at Dartmouth College.
Dr. Camm has published over 30 papers in the general area of optimization applied
to problems in operations management. He has published his research in Science, Man-
agement Science, Operations Research, Interfaces and other professional journals. At the
University of Cincinnati, he was named the Dornoff Fellow of Teaching Excellence and
he was the 2006 recipient of the INFORMS Prize for the Teaching of Operations Research
Practice. A firm believer in practicing what he preaches, he has served as an operations
research consultant to numerous companies and government agencies. From 2005 to
2010 he served as editor-in-chief of Interfaces, and is currently on the editorial board of
INFORMS Transactions on Education.
James J. Cochran James J. Cochran is the Bank of Ruston Barnes, Thompson, & Thurmon
Endowed Research Professor of Quantitative Analysis at Louisiana Tech University. Born
in Dayton, Ohio, he holds a B.S., an M.S., and an M.B.A. from Wright State University
and a Ph.D. from the University of Cincinnati. He has been at Louisiana Tech University
since 2000, and has been a visiting scholar at Stanford University, Universidad de Talca,
and the University of South Africa.
Professor Cochran has published over two dozen papers in the development and ap-
plication of operations research and statistical methods. He has published his research in
Management Science, The American Statistician, Communications in Statistics—Theory
and Methods, European Journal of Operational Research, Journal of Combinatorial
Optimization, and other professional journals. He was the 2008 recipient of the INFORMS
Prize for the Teaching of Operations Research Practice and the 2010 recipient of the Mu
Sigma Rho Statistical Education Award. Professor Cochran was elected to the International
Statistics Institute in 2005 and named a Fellow of the American Statistical Association
in 2011. A strong advocate for effective operations research and statistics education as a
means of improving the quality of applications to real problems, Professor Cochran has
organized and chaired teaching effectiveness workshops in Montevideo, Uruguay; Cape
Town, South Africa; Cartagena, Colombia; Jaipur, India; Buenos Aires, Argentina; and
Nairobi, Kenya. He has served as an operations research consultant to numerous compa-
nies and not-for-profit organizations. He currently serves as editor-in-chief of INFORMS
Transactions on Education and is on the editorial board of Interfaces, the Journal of the
Chilean Institute of Operations Research, and ORiON.
Michael J. Fry Michael J. Fry is Associate Professor of Operations, Business Analyt-
ics, and Information Systems in the Carl H. Lindner College of Business at the University
of Cincinnati. Born in Killeen, Texas, he earned a B.S. from Texas A&M University, and
M.S.E. and Ph.D. degrees from the University of Michigan. He has been at the University of
Cincinnati since 2002, and he has been a visiting professor at The Johnson School at Cornell
University and the Sauder School of Business at the University of British Columbia.
About the Authors xv

Professor Fry has published over a dozen research papers in journals such as Op-
erations Research, M&SOM, Transportation Science, Naval Research Logistics, and In-
terfaces. His research interests are in applying quantitative management methods to the
areas of supply chain analytics, sports analytics, and public-policy operations. He has
worked with many different organizations for his research, including Dell, Inc., Copeland
Corporation, Starbucks Coffee Company, the Cincinnati Fire Department, the State of Ohio
Election Commission, the Cincinnati Bengals, and the Cincinnati Zoo. In 2008, he was
named a finalist for the Daniel H. Wagner Prize for Excellence in Operations Research
Practice, and he has been recognized for both his research and teaching excellence at the
University of Cincinnati.

Jeffrey W. Ohlmann Jeffrey W. Ohlmann is Associate Professor of Management

Sciences in the Tippie College of Business at the University of Iowa. Born in Valentine,
Nebraska, he earned a B.S. from the University of Nebraska, and M.S. and Ph.D. degrees
from the University of Michigan. He has been at the University of Iowa since 2003.
Professor Ohlmann’s research on the modeling and solution of decision-making prob-
lems has produced over a dozen research papers in journals such as Mathematics of Opera-
tions Research, INFORMS Journal on Computing, Transportation Science, and Interfaces.
He has collaborated with companies such as Transfreight, LeanCor, Cargill, the Hamilton
County Board of Elections, and the Cincinnati Bengals. Due to the relevance of his work to
industry, he was bestowed the George B. Dantzig Dissertation Award and was recognized
as a finalist for the Daniel H. Wagner Prize for Excellence in Operations Research Practice.

David R. Anderson David R. Anderson is Professor Emeritus of Quantitative Analysis

in the Carl H. Lindner College of Business at the University of Cincinnati. Born in Grand
Forks, North Dakota, he earned his B.S., M.S., and Ph.D. degrees from Purdue University.
Professor Anderson has served as Head of the Department of Quantitative Analysis and
Operations Management and as Associate Dean of the College of Business Administration.
In addition, he was the coordinator of the College’s first Executive Program.
At the University of Cincinnati, Professor Anderson has taught introductory statistics
for business students as well as graduate-level courses in regression analysis, multivariate
analysis, and management science. He has also taught statistical courses at the Department
of Labor in Washington, D.C. He has been honored with nominations and awards for
excellence in teaching and excellence in service to student organizations.
Professor Anderson has coauthored 10 textbooks in the areas of statistics, management
science, linear programming, and production and operations management. He is an active
consultant in the field of sampling and statistical methods.

Dennis J. Sweeney Dennis J. Sweeney is Professor Emeritus of Quantitative Analysis

and Founder of the Center for Productivity Improvement at the University of Cincinnati.
Born in Des Moines, Iowa, he earned a B.S.B.A. degree from Drake University and his
M.B.A. and D.B.A. degrees from Indiana University, where he was an NDEA Fellow.
During 1978–1979, Professor Sweeney worked in the management science group at
Procter & Gamble; during 1981–1982, he was a visiting professor at Duke University.
Professor Sweeney served as Head of the Department of Quantitative Analysis and as
Associate Dean of the College of Business Administration at the University of Cincinnati.
Professor Sweeney has published more than 30 articles and monographs in the areas
of management science and statistics. The National Science Foundation, IBM, Procter &
Gamble, Federated Department Stores, Kroger, and Cincinnati Gas & Electric have funded
his research, which has been published in Management Science, Operations Research,
Mathematical Programming, Decision Sciences, and other journals.
Professor Sweeney has coauthored 10 textbooks in the areas of statistics, management
science, linear programming, and production and operations management.
xvi About the Authors

Thomas A. Williams Thomas A. Williams is Professor Emeritus of Management Science

in the College of Business at Rochester Institute of Technology. Born in Elmira, New York,
he earned his B.S. degree at Clarkson University. He did his graduate work at Rensselaer
Polytechnic Institute, where he received his M.S. and Ph.D. degrees.
Before joining the College of Business at RIT, Professor Williams served for seven
years as a faculty member in the College of Business Administration at the University of
Cincinnati, where he developed the undergraduate program in Information Systems and
then served as its coordinator. At RIT he was the first chairman of the Decision Sciences
Department. He teaches courses in management science and statistics, as well as graduate
courses in regression and decision analysis.
Professor Williams is the coauthor of 11 textbooks in the areas of management sci-
ence, statistics, production and operations management, and mathematics. He has been a
consultant for numerous Fortune 500 companies and has worked on projects ranging from
the use of data analysis to the development of large-scale regression models.
Preface

Essentials of Business Analytics is designed to introduce the concept of business analytics

to undergraduate and graduate students. This textbook contains one of the first collections
of materials that are essential to the growing field of business analytics. In Chapter 1 we
present an overview of business analytics and our approach to the material in this text-
book. In simple terms, business analytics helps business professionals make better deci-
sions based on data. We discuss models for summarizing, visualizing, and understanding
useful information from historical data in Chapters 2 through 6. Chapter 7 covers the use of
spreadsheets for examining data and building decision models. In Chapters 8 through 10 we
discuss optimization models to help decision makers choose the best decision based on the
available data. Chapter 10 presents material that some may consider more advanced forms
of optimization (nonlinear optimization models), although these models are extremely use-
ful and widely applicable to many business situations. In any case, some instructors may
choose to omit covering Chapter 10. In Chapter 11 we introduce the concept of simulation
models for understanding the effect of uncertainty on decisions. Chapter 12 is an overview
of decision analysis approaches for incorporating a decision maker’s views about risk into
decision making. In Appendix A we present optional material for students who need to
learn the basics of using Microsoft Excel. The use of databases and manipulating data in
Microsoft Access is discussed in Appendix B.
This textbook can be used by students who have previously taken a course on basic
statistical methods as well as students who have not had a prior course in statistics. This
textbook introduces basic statistical concepts in enough detail to support their use in busi-
ness analytics tools. For the student who has not had a prior statistics course, these concepts
are sufficient to prepare the student for more advanced business analytics methods. For
students who have had a previous statistics class, the material will provide a good review.
All statistical concepts contained in this textbook are presented from a business analytics
perspective using practical business examples. For those instructors who wish to skip the
introductory statistics material, Chapters 2 and 4 can be considered optional.

Features and Pedagogy

The style and format of this textbook is based on the other classic textbooks written by the
Anderson, Sweeney, and Williams (ASW) team. Some of the specific features that we use
in this textbook are listed below.
● Integration of Microsoft Excel: Excel has been thoroughly integrated throughout
this textbook. For many methodologies, we provide instructions for how to perform
calculations both by hand and with Excel. In other cases where realistic models
are practical only with the use of a spreadsheet, we focus on the use of Excel to
describe the methods to be used.
● Use of Excel 2013: The material presented for Excel in this textbook is fully com-
patible with Excel 2013. In most cases, Excel 2013 can be considered a relatively
minor update from previous Excel versions as it relates to business analytics.
However, the data visualization abilities of Excel have been greatly enhanced in
Excel 2013. It is much easier to create, modify and analyze charts in Excel 2013.
xviii Preface

Recognizing that many students and instructors may not have access to Excel 2013
at this time, we also provide instructions for using previous versions of Excel when-
ever possible.
● Use of Analytics Solver Platform and XLMiner: This textbook incorporates the
use of two very powerful Microsoft Excel Add-ins: Analytics Solver Platform and
XLMiner, both created by Frontline Systems. Analytics Solver Platform provides
additional optimization and simulation features for Excel. XLMiner incorporates
sophisticated data mining algorithms into Excel and allows for additional data vi-
sualization and data exploration. In most chapters we place the use of Analytics
Solver Platform and XLMiner in the chapter appendix so that the instructor can
choose whether or not to cover this material. However, because these tools are es-
sential to performing simulation and data mining methods, we integrate XLMiner
throughout Chapter 6 on data mining and we utilize Analytics Solver Platform in
Sections 11.3 and 11.4 for simulation.
● Notes and Comments: At the end of many sections, we provide Notes and Com-
ments to give the student additional insights about the methods presented in that
section. These insights include comments on the limitations of the presented meth-
ods, recommendations for applications, and other matters. Additionally, margin
notes are used throughout the textbook to provide additional insights and tips re-
lated to the specific material being discussed.
● Analytics in Action: Each chapter contains an Analytics in Action article. These
articles present interesting examples of the use of business analytics in practice.
The examples are drawn from many different organizations in a variety of areas
including healthcare, finance, manufacturing, marketing, and others.
● WEBfiles: All data sets used as examples and in student exercises are also provided
online as files available for download by the student. The names of the WEBfiles
are called out in margin notes throughout the textbook.
● Problems and Cases: With the exception of Chapter 1, each chapter contains more
than 20 problems to help the student master the material presented in that chapter.
The problems vary in difficulty and most relate to specific examples of the use of
business analytics in practice. Answers to even-numbered problems are provided
in an online supplement for student access. With the exception of Chapter 1, each
chapter also includes an in-depth case study that connects many of the different
methods introduced in the chapter. The case studies are designed to be more open-
ended than the chapter problems, but enough detail is provided to give the student
some direction in solving the cases.

Acknowledgements
We would like to acknowledge the work of our reviewers, who provided comments and
suggestions for improvement of this text. Thanks to:

Matthew D. Bailey Q B. Chung

Bucknell University Villanova University
Phillip Beaver Elizabeth A. Denny
Daniels College of Business University of Kentucky
University of Denver
Mike Taein Eom
M. Khurrum S. Bhutta University of Portland
Ohio University
Preface xix

Yvette Njan Essounga Marco Lam

Fayetteville State University York College of Pennsylvania
Lawrence V. Fulton Ram Pakath
Texas State University University of Kentucky
James F. Hoelscher Susan Palocsay
Lincoln Memorial University James Madison University
Eric Huggins Dothan Truong
Fort Lewis College Embry-Riddle Aeronautical University
Faizul Huq Kai Wang
Ohio University Wake Technical Community College

We are indebted to our product director Joe Sabatino and our product manager,
Aaron Arnsparger; our marketing director, Natalie King, our marketing manager, Heather
Mooney, and our associate marketing development manager, Roy Rosa; our content de-
veloper, Maggie Kubale; our senior content project manager, Cliff Kallemeyn; our media
developer, Chris Valentine; and others at Cengage Learning for their counsel and support
during the preparation of this text.
Jeffrey D. Camm
James J. Cochran
Michael J. Fry
Jeffrey W. Ohlmann
David R. Anderson
Dennis J. Sweeney
Thomas A. Williams
 CHAPTER 1
Introduction
CONTENTS 1.5 BUSINESS ANALYTICS
IN PRACTICE
1.1 DECISION MAKING Financial Analytics
1.2 BUSINESS ANALYTICS Human Resource (HR) Analytics
DEFINED Marketing Analytics
Health Care Analytics
1.3 A CATEGORIZATION OF
Supply Chain Analytics
ANALYTICAL METHODS
Analytics for Government and
AND MODELS
Nonprofits
Descriptive Analytics
Sports Analytics
Predictive Analytics
Web Analytics
Prescriptive Analytics
1.4 BIG DATA
2 Chapter 1 Introduction

You apply for a loan for the first time. How does the bank assess the riskiness of the loan
it might make to you? How does Amazon.com know which books and other products to
recommend to you when you log in to their Web site? How do airlines determine what price
to quote to you when you are shopping for a plane ticket? How can doctors better diagnose
and treat you when you are ill or injured?
Even though you are applying for a loan for the first time, millions of people around the
world have applied for loans. Many of these loan recipients have paid back their loans in
full and on time, but some of them have not. The bank wants to know whether you are more
like those who have paid back their loans or more like those who defaulted. By comparing
your credit history, financial situation, and other factors to the vast database of previous
loan recipients, the bank can effectively assess how likely you are to default on a loan.
Similarly, Amazon.com has access to millions of previous purchases made by custom-
ers on its Web site. Amazon.com examines your previous purchases, the products you have
viewed, and any product recommendations you have provided. Amazon.com then searches
through its huge database for customers who are similar to you in terms of product pur-
chases, recommendations, and interests. Once similar customers have been identified, their
purchases form the basis of the recommendations given to you.
Prices for airline tickets are frequently updated. The price quoted to you for a flight
between New York and San Francisco today could be very different from the price quoted
tomorrow. These changes happen because airlines use a pricing strategy known as revenue
management. Revenue management works by examining vast amounts of data on past air-
line customer purchases and using these data to forecast future purchases. These forecasts
are then fed into sophisticated optimization algorithms that determine the optimal price
to charge for a particular flight and when to change that price. Revenue management has
resulted in substantial increases in airline revenues.
Finally, consider the case of being evaluated by a doctor for a potentially serious
medical issue. Hundreds of medical papers may describe research studies done on patients
facing similar diagnoses and thousands of data points exist on their outcomes. However,
it is extremely unlikely that your doctor has read every one of these research papers or is
aware of all previous patient outcomes. Instead of relying only on her medical training and
knowledge gained from her limited set of previous patients, wouldn’t it be better for your
doctor to have access to the expertise and patient history of thousands of doctors around
the world?
In 2007, a group of IBM computer scientists initiated a project to develop a new deci-
sion technology to help in answering these types of questions. That technology is called
Watson, named after the founder of IBM, Thomas J. Watson. The team at IBM focused on
one aim: how the vast amounts of data now available on the Internet can be used to make
more data-driven, smarter decisions.
Watson became a household name in 2011, when it famously won the television game
show, Jeopardy! Since that proof of concept in 2011, IBM has reached agreements with
the health insurance provider WellPoint, the financial services company Citibank, and
Memorial Sloan-Kettering Cancer Center to apply Watson to the decision problems that
they face.
Watson is a system of computing hardware, high-speed data processing, and analytical
algorithms that are combined to make data-based recommendations. As more and more
data are collected, Watson has the capability to learn over time. In simple terms, accord-
ing to IBM, Watson gathers hundreds of thousands of possible solutions from a huge data
bank, evaluates them using analytical techniques, and proposes only the best solutions for
consideration. Watson provides not just a single solution, but a range of good solutions with
a confidence level for each.
For example, at WellPoint’s Virginia data center, to the delight of doctors and patients,
Watson is already being used to speed up the approval of medical procedures. Citibank is
 Chapter 1 Introduction 3

beginning to explore how to use Watson to better serve its customers, and Sloan-Kettering
is launching a pilot study to assess the effectiveness of Watson in assisting with the diag-
nosis and treatment of patients.1
This book is concerned with data-driven decision making and the use of analytical
approaches in the decision-making process. Three developments spurred recent explo-
sive growth in the use of analytical methods in business applications. First, technological
advances, such as improved point-of-sale scanner technology and the collection of data
through e-commerce, Internet social networks, and data generated from personal electronic
devices, produce incredible amounts of data for businesses. Naturally, businesses want to
use these data to improve the efficiency and profitability of their operations, better under-
stand their customers, price their products more effectively, and gain a competitive advan-
tage. Second, ongoing research has resulted in numerous methodological developments,
including advances in computational approaches to effectively handle and explore massive
amounts of data, faster algorithms for optimization and simulation, and more effective
approaches for visualizing data. Third, these methodological developments were paired
with an explosion in computing power and storage capability. Better computing hardware,
parallel computing, and, more recently, cloud computing (the remote use of hardware and
software over the Internet) have enabled businesses to solve big problems faster and more
accurately than ever before.
In summary, the availability of massive amounts of data, improvements in analytic
methodologies, and substantial increases in computing power have all come together to
result in a dramatic upsurge in the use of analytical methods in business and a reliance on
the discipline that is the focus of this text: business analytics. Figure 1.1, a graph generated
by Google Trends, displays the search volume for the word analytics from 2004 to 2013
(projected) on a percentage basis from the peak. The figure clearly illustrates the recent
increase in interest in analytics.
Business analytics is a crucial area of study for students looking to enhance their em-
ployment prospects. By 2018, it is predicted that there will be a shortage of more than
1.5 million business managers with adequate training in analytics in the United States

FIGURE 1.1 GOOGLE TRENDS GRAPH OF SEARCHES ON THE TERM AnAlytics

Interest over time

The number 100 represents the peak search volume

110

88

66

44

22

2005 2007 2009 2011 2013

1
“IBM’s Watson Is Learning Its Way to Saving Lives,” Fastcompany Web site, December 8, 2012.
4 Chapter 1 Introduction

alone.2 As stated in the Preface, the purpose of this text is to provide students with a sound
conceptual understanding of the role that business analytics plays in the decision-making
process. To reinforce the applications orientation of the text and to provide a better under-
standing of the variety of applications in which analytical methods have been used suc-
cessfully, Analytics in Action articles are presented throughout the book. Each Analytics
in Action article summarizes an application of analytical methods in practice. For example,
the first Analytics in Action, Procter & Gamble Uses Business Analytics to Redesign its
supply chain (later in this chapter) describes how analytics was used to drive efficiency in
Procter & Gamble’s North American supply chain.

1.1 Decision Making

It is the responsibility of managers to plan, coordinate, organize, and lead their organiza-
tions to better performance. Ultimately, managers’ responsibilities require that they make
strategic, tactical, or operational decisions. Strategic decisions involve higher-level issues
concerned with the overall direction of the organization; these decisions define the orga-
nization’s overall goals and aspirations for the future. Strategic decisions are usually the
domain of higher-level executives and have a time horizon of three to five years. Tactical
decisions concern how the organization should achieve the goals and objectives set by its
strategy, and they are usually the responsibility of midlevel management. Tactical decisions
usually span a year and thus are revisited annually or even every six months. Operational
decisions affect how the firm is run from day to day; they are the domain of operations
managers, who are the closest to the customer.
Consider the case of the Thoroughbred Running Company (TRC). Historically, TRC
had been a catalog-based retail seller of running shoes and apparel. TRC sales revenue
grew quickly as it changed its emphasis from catalog-based sales to Internet-based sales.
Recently, TRC decided that it should also establish retail stores in the malls and downtown
areas of major cities. This is a strategic decision that will take the firm in a new direc-
tion that it hopes will complement its Internet-based strategy. TRC middle managers will
therefore have to make a variety of tactical decisions in support of this strategic decision,
including how many new stores to open this year, where to open these new stores, how
many distribution centers will be needed to support the new stores, and where to locate
these distribution centers. Operations managers in the stores will need to make day-to-day
decisions regarding, for instance, how many pairs of each model and size of shoes to order
from the distribution centers and how to schedule their sales personnel.
Regardless of the level within the firm, decision making can be defined as the follow-
ing process:
1. Identify and define the problem
2. Determine the criteria that will be used to evaluate alternative solutions
3. Determine the set of alternative solutions
4. Evaluate the alternatives
if i were given one hour 5. Choose an alternative
to save the planet, i would
Step 1 of decision making, identifying and defining the problem, is the most critical. Only
spend 59 minutes defining
the problem and one minute if the problem is well-defined, with clear metrics of success or failure (step 2), can a proper
resolving it. approach for solving the problem (steps 3 and 4) be devised. Decision making concludes
—Albert Einstein with the choice of an alternative (step 5).

2
J. Manyika et al., “Big Data: The Next Frontier for Innovation, Competition and Productivity,” McKinsey Global Institute
Report, 2011.
 1.3 A Categorization of Analytical Methods and Models 5

There are a number of approaches to making decisions: tradition (“We’ve always

done it this way”), intuition (“gut feeling”), and rules of thumb (“As the restaurant owner,
I schedule twice the number of waiters and cooks on holidays”). The power of each of
these approaches should not be underestimated. Managerial experience and intuition are
valuable inputs to making decisions, but what if relevant data were available to help us
make more informed decisions? With the vast amounts of data now generated and stored
electronically, it is estimated that the amount of data stored by businesses more than
doubles every two years. How can managers convert these data into knowledge that they
can use to be more efficient and effective in managing their businesses?

1.2 Business Analytics Defined

What makes decision making difficult and challenging? Uncertainty is probably the number
one challenge. If we knew how much the demand will be for our product, we could do a
much better job of planning and scheduling production. If we knew exactly how long each
step in a project will take to be completed, we could better predict the project’s cost and
completion date. If we knew how stocks will perform, investing would be a lot easier.
Another factor that makes decision making difficult is that we often face such an enor-
mous number of alternatives that we cannot evaluate them all. What is the best combina-
tion of stocks to help me meet my financial objectives? What is the best product line for a
company that wants to maximize its market share? How should an airline price its tickets
so as to maximize revenue?
some firms and industries Business analytics is the scientific process of transforming data into insight for making
use the simpler term,
better decisions.3 Business analytics is used for data-driven or fact-based decision making,
analytics. Analytics is often
thought of as a broader which is often seen as more objective than other alternatives for decision making.
category than business As we shall see, the tools of business analytics can aid decision making by creating
analytics, encompassing insights from data, by improving our ability to more accurately forecast for planning, by
the use of analytical helping us quantify risk, and by yielding better alternatives through analysis and opti-
techniques in the sciences
mization. Indeed, a recent study based on a large sample of firms that was conducted by
and engineering as well.
in this text, we use business researchers at MIT’s Sloan School of Management and the University of Pennsylvania,
analytics and analytics concluded that firms guided by data-driven decision making have higher productivity and
synonymously. market value and increased output and profitability.4

1.3 A Categorization of Analytical Methods

and Models
Business analytics can involve anything from simple reports to the most advanced optimi-
zation techniques (methods for finding the best course of action). Analytics is generally
thought to comprise three broad categories of techniques: descriptive analytics, predictive
analytics, and prescriptive analytics.

Descriptive Analytics
Descriptive analytics encompasses the set of techniques that describes what has happened
in the past. Examples are data queries, reports, descriptive statistics, data visualization

3
We adopt the definition of analytics developed by the Institute for Operations Research and the Management Sciences
(INFORMS).
4
E. Brynjolfsson, L. M. Hitt, and H. H. Kim, “Strength in Numbers: How Does Data-Driven Decisionmaking Affect Firm Perfor-
mance?” (April 18, 2013). Available at SSRN http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1819486.
Another Random Scribd Document
with Unrelated Content
The text on this page is estimated to be only 13.66%
accurate

ai'dentifi'kei$(a)n, an(d) 'sou, (h)wen an oul(d) ' di'mcmidid

(h)iz 'haet an(d) iks'pleind Sat (h)i? (a)d1 'lo'st (h)iz 't$ek, 5(e)a waz
a 'greit2 ta'du: on 5a 'part av 5o njui 'meen. hat8 'ftaet s 'mai hset,
5a 'S*hi 'braun wan4,'' "sed 5i oul(d) 'dsentlman, "it s 'got m(a)i
i'nijlz in it— 'ef, 'eks, 'd3i:." 5a 'sAbstitjuit lukt in'said 5a "haet,
'a3nd5, 'Jua(r) 6 i'nAf, 5i i'nijlz w(s)a '5sa7. "(m)mm!" hi' 'sed
sas'pi$asli, "ju'8 'mait a(v) 'sim 5i:z i'nijlz "sAinhau." " bat3 5s a(r)9
'on m(a)i 'Sait, "tui," 'sed 5a "dsentlman, An'bAt(a)niij (h)iz
'we(i)skout. "'si:! 'ef, 'eks, •d5i!." "ju|M 'mait (h)av 'stoul(a)n 5a
'Jait," 'sed 5i a'tendant. '* 'gud 'hevnz ! " 'Jautid 5i oul(d)
'd^entlman, an(d) (h)i' 'to'a(r)10 'oupn (h)iz 'Jait an(d) 'Aiidavest.
"'mebi '5is 1 'ssetisfai ju' ! 'ei?" an(d) (h)if 'pointid ta 5a 'letaz 'ef,
'eks, d3ii 'tse'tuid11 on (h)iz 'brest in 'blu:. 5a 'sAbstitjuit 'stsad at 5a
'tse'tuiii] 12 'klousli. '5en at 'laist (h)i' 'hsendid 'ouva 5a 'hset. az13
(h)i' 'did (h)if 'sed ri'lAktantli : — ' 'wel, sins 'neitja rout 5ouz i'ni$lz
on j(u)a 'skin, ai s(a)'pouz 5ei 'niAst bif 'ju'az fa(r) a 'fsekt." lr had.
2greit. 8 b.vt. 4 'WAII. 5an(d). 6'$oa(r), 'Soia(r), 'Soi(r). T'wsa 5ea.
8ja. 9 5ei a(r). lo 'toi(r). uta'tu:d. 32ta'tu:irj. 18 'a?z.
The text on this page is estimated to be only 19.98%
accurate

18. i'konomi 'weistid. o 'tuorist woz 'stramdid in 'noiwei wiS

'ounli i'nAf 'mAiri in (h)iz 'pokit to pei (h)iz 'psssids back tu 'inglond.
'Oinkirj So 'msetod') 'ouvo, (h)i' di'saidid, Sot oz1 it woz 'ounli o 'tin
deiz 'dsoini, (h)i' kod 'iizili2 dis'pens wib8 'find, sou (h)i' 'went on 'bo:
(o)d So 'stiimo(r) on(d) 'boit o 'tikit. hi' 'klouzd (h)iz 'ioz to fto 'saund
ov So 'lAn(t)$ bel, on(d) (h)wen 'dino taim 'keim (h)i' ri'fjuizd Si
invi'teiSMn tu o'kAmp(o)ni o 'felo(u) 'traevlo to So so'lum on So
'graund Sot (h)i' 'did nt fill 'wel. So 'nekst 'momiij (h)i' skipt4
'brekfost bai pri'tendiij tu 'ouvo'sliip (h)im'self, on(d) ot 'Lvn(t)$ taim
(h)if o'ge(i)n 'msenid.^d to kiip 'aut ov So 'wei. ot 'dino taim,
hau'evo, So 'paeijz ov 'hAijgo(r) ouvo'keim So 'skruiplz ov
'kon$(o)ns, fo(r) i'5 woz 'sou 'hAijgri Sot (h)i? kod6 (h)ov 'i:tn 'leSo.
"ai m 'go(u)iij7 to 'fi:d," sed 'hi1, "'iivn if Sei '0rou mi' 'ouvobo:(o)d
'aiftowodz. ai 'mait oz wel 'draun oz 'sta:v." ot So 'dino 'teibl (h)i'
e(i)t 'r«v(o)nosli 'evriGiij put in 'frAnt ov (h)im. 'fild to ri'pli:J(o)n, hi'
felt 'breist 'AP fo So 'kAmiij 'ran. ''brirj mi' So 'bil," hi' 'sed to So
'stjuod. uSo 'bil, so'!" 'sed So 'laeto. " 'jes," 'ainsod So 'traevlo.
"S(s)o(r) 'iz nt 'eni 'bil," woz So ri'plai. "on 'Sis Sip 'mi:lz ofr)
in'kluidid8 in So 'pa3sids 'niAni." 1 '*z. 2 'iizoli. a wi9. 4 skipt = kept
o'wei from, fo hi', 'fo(r) i', 'fo' hi1, fr i'. 6kud. ?goirj. 8iij'kluidid. 14
The text on this page is estimated to be only 18.15%
accurate

19. 'eidz tu igza}mi'nei$(a)nz. [fta konva'sei$(a)nz in '5is

pi:s o(r) in 'veri fa'miljo 'stail.] 'misto 'baunso, laik 'meni 'A&OZ, 'aidl
az 'wel oz 'ignorant, in'tendid tu o'sist (h)im'self, (h)wen in 'skuilz1,
bai 'eni kon'traivons 5ot (h)iz indsi'njuiti kod2 so'dsest. ' (i)t s 'kwait
'feo," woz 5o 'litl 'dsentlmanz 'aigjumant, "to 'du: 5i ig'zaeminoz in
'eni wei jo3 kaen, oz 'loij oz ju1 'ounli gou in fo(r)4 o 'pa:s. o(v)
'koi(o)s, if jo3 w(e)o go(u)irj° in fo(r)4 o 'klais, of 'skolojip, o(r)6
'eniGiij o(v) '5set soit, it (w)od bi1 nou 'end 'mini on(d) 'doiti to
'krib7; on(d) 5o 'msen 5ot 'did it 'o:t to bi' 'kikt aut o(v) So so'saioti8
o(v) 'dsentlmon. bot (h)wen jir 'ounli gou in fo(r)4 o 'pais, (o)n(d)
aint 'duiiij 'eniwAn9 'eni 'haim b(a)i o 'litl bit o(v) 'kribirj, bot 'tjuiz to
rAn 5o 'risk to 'seiv j(u)o'self 5o 'bo5o(r) o(v) 'bii(i)rj 'plaud10 '(h)wai
5(e)n, 'ai 6iijk o 'felo11 z 'baund to 'dui (h)wot (h)i' 'keen fo(r)
im'self12, on(d) jo3 'sii, in 'mai keis, 'gigleemps13, 5(e)o z 5o
'niAm14 to bi' kon'sidod ; 'Sii d kAt 'Ap15 if ai 'didnt get 'Grin, sou ai
'niAst krib o 'bit if 'ounli fo 'ha: seik." 'bAt, o:l'5ou 5o 'litl 'd,5entlmon
'^AS meid 'filjol16 'tendanis 5i iks'kjuis fo(r) iz17 di'siit, on(d) 5a
'saiv fo(r) ^skuilz; So 'pleis ov igza3mi'neiS(o)n. '2 kud. 8ju'. 4 f r,
fo'(r). °goiij. 6o'(r>). ' krib = juiz Aii'feo 'miinz in ig'zaemi'nei$(o)n.
8so'saioti. 9'eniwon. ° 'plaud = AHsok'sesf(u)!. ! 'felo(u). 12fr im'self,
fo him'self, fo' him'self, fo'(r) im'self. 3 'gigkemps ; a 'nikneim 'givn tu
a 'wsora(r) av 'spektaklz. 4 'niAm = 'niA^a. 5 'kAt 'AP = bi' 'griivd. 6
'filial. I7fo' hiz, fo'(r) iz. 15
The text on this page is estimated to be only 16.86%
accurate

iz1 'konj(a)ns, 'jet (h)i' kad 'naiSa pa'sweid 'mista 'va:d(a)nt

'grim ta 'folo(u) (h)iz ig'zaimpl, 'no: to bi' o 'konvo:t to hiz2
o'pinjonz, 'noi wad8 (h)i' bi' po'sweidid bai 'vo:d(o)rit to ri'linkwij
(h)iz di'zainz. ''(h)wai, Ink 'hio, 'giglsemps ! " 'misto 'baunso wod4
'sei; "hau 'kam ai ri'linkwi$5 (5)om, 'aifto 'hseviij 'heed6 'oil Sis 'tr-
Abl? ai 1 'put j(ir) 'AP tu o 'fju: o(v) m(a)i 'dodsiz — 'fri:, 'greitis, fo
'riA0in. in 5o 'foist pleis, 'giglsemps, jo7 si: 'hio z o 'smo:l 'so:kjnlo
bit o(v) 'peipo, 'kAvod wi58 |)elopo'ni:$(a)n9 on(d) 'pju:nik 'wo:z,
on(d) nou 'end o(v) 'deits — 'ritn 'smo:l an(d) 'Jo:t, jo7 'si:, bot
'kwait 'ledsibl — wi5 5o 'tji:f Ginz dAn in 'red 'ink. wel '5is 'dsentlmon
'gouz in 5o 'frAnt av m(a)i 'wotj 'Ando 5a 'gla:s ; 'tend, (h)wen ai get
'stAm(p)t fo(r) o 'deit, 'aut kAmz 5a 'wotj : — ai Ink ot 5o 'taim a(v)
'dei — ju? Ando'staend, on(d) 'daun gouz Sa 'deit. 'hia z a'nA^a
'dods!" 'aedid 5a litl 'dsentlman, az (h)i' pra'dju:st10 a 'Ja:t fram a
'droi(a). "ink 'hia, at 3a 'ris(t)ban(d)zn. 'hia(r) a(r) 'o:l 8a 'kirjz av
'izr(e)ial an(d) 'dsuzda, wi5 Ssa 'deits on(d) 'profits, 'ritn 'daun in
'indjan 'iijk, 'sou (a)z ta wo$ 'aut a'ge(i)n. ja7 'twitj 'AP 5a 'kAf a(v)
j(u)a 'kout, kwait seksi'dent(a)li, an(d) 5en ja7 'buk j(u)a 'kin. ja7
'si:, 'giglsemps, ai 'dount laik ta 'trAst, az 'SAHI 'felaz12 'du:, ta
'hsevirj (h)wat ja7 'wont 'ritn 'daun 'smo:l an(d) '$Avd 'intu a 'kwil,
an(d)'pa:st t(a) ja7 b(a)i 'SAHI mfen 'sitiij in Sa 'sku:lz ; '5aat s
'deind3(a)ras, 'dount l'a7 'si:1? an(d) ai 'dount laik ta hould 'ka:dz in
m(a)i 1 fo1 hiz, fo'(r) iz. 2 tu iz. 3 'no: "wild. 4 'baunsa(r) ad,
'baunsa wud. 5 k(a)n ai ri'ligkwij. 9'qiffca.(r) ayirj 'haad. 7]u?. 8wi9.
9 pelopo'niijfo/n, pelopo'niijjan. 10pro'dju:st. 11 'ris(t)bam(d)z.
12'felo(u)z. 16
The text on this page is estimated to be only 17.67%
accurate

'haend ; ai v im'pruzvd on '5#t, 9n(d) in'ventid 9 'fgistreit

'dods a(v) m(a)i 'oun, 5at ai in'tend t9 teik aut 9 'peitnt1 fo'. laik 'oil
'truili 'greit in'ven$(a)nz, it s nou 'end 'simpl. luk 'streit bi'foi(a) J92,
9n(d) J92 1 'si: 5is 'paek e(v) 'kaidz, — 'oil meid 9V 9 'saiz, 'nais t9
'hould in 89 'paim e(v) j(u)o 'haend: 5e9(r) o'baut 'oil 'soits o(v) 'rAin
'0inz, — 'evriGirj ai 'wont. (9)n(d) jo2 si:, 'hig z 9 'lonij 'strirj wi5 9
'litl bit 9(v) 'hukt 'waig(r) 9t 5i 'end, 'meid sou 5at ai k(g)n 'iizili
'haerj 89 'ka:d on it. 'wel, ai 'pais 69 'striij Ap m(a)i 'kout 'sliiv, 9n(d)
daun 'And9 m(a)i 'we(i)skot3; 9n(d) 'hi9, J92 'si:, ai v 'got 89
'wai9(r) 'end in 59 'pct:m g(v) m(a)i 'haend. 5en ai 'slip aut 59 'kcnd
ai 'wont, 9n(d) 'huk it 'ont9 5g 'waig, sou 5ot ai k(a)n 'heev it 'dsAst
bi'foi(a) mi' 9z ai 'rait. '5en, if 'eni g(v) 5i ig'zsemingz 'luk S9s'pi$9s,
g(r)4 if 'wAn 9(v) 59m5 kAmz 'raund t9 'spai, ai 'dsAst 'pul 59 bit
a(v) 'striij 5gt haenz 'And9 59 'botgm 9(v) m(axi 'we(i)sk9t3, 9n(d)
9'wei 'flaiz 5o 'ka:d 'AP m(a)i 'kout'sli:v ; 9n(d) (h)wen 5i ig'zseming
kAmz 'raund, (h)i' 'si:z 5ot m(a)i 'haend z 'nev9 'mu:vd, (9)n(d) 59t
5(s)g z 'nAGiq in it ! sou (h)i 'wo:ks 'o'f 'saatisfaid ; (9)11 (d) '5en ai
'Jeik 59 'litl 'begg(r) 'aut g(v) m(a)i 'sli:v 9'ge(i)n, (g)n(d) 59 'seim
'geim gouz 'on oz bi'fo:(o). 9n(d) (h)wen 5a 'strirj z 'tait, 'i:vn
'streit(9)nirj j(u)9 'bodi (i)z 'kwait S9'fi$(o)nt t9 'hoist 59 'ka:d 'int9
j(u)9 'sli:v wi'5aut 'mu:viq 'ai5g(r) 9(v) j(u)g 'haendz. ai v 'got on
igzsemi'neij(9)n kout 'meid on 'pgjpgs, wi5 9 'hi:p o(v) 'pokits, in
(h)witS ai k(o)n 'stou m(a)i 'kaidz in 'regjubCr) 'o:d9. '5i:z '6ri:
'pokits," sed 'misto 'baunsg, 9z (h)i' pr9'dju:st6 ^paetnt. 2ju'.
3'we(i)s(t)kout. 4 o:(r). 69v 9m. pro'dju:st. 17
The text on this page is estimated to be only 18.24%
accurate

5g 'kout, %(r) in'taioli fa 'juiklid. 'hig z 'i:t$ 'probbm1 'ritn

'rait aut on 9 'kaid ; 5s a2 'leid 'regjulali in 'oida, on(d) ai 'tain (5)am
'ouva(r) in m(a)i 'pokit, t(i)l ai get 'hould 0(v) 5a 'wAn ai 'wont,
(a)n(d) Sen ai teik it 'aut, (o)n(d) 'woik it. 'sou, jo8 'sii, 'giglsemps, ai
m 'seif to get '0rui ! it s im'posibl fo 5am4 ta 'plau mi', wi5 oil '5i:z
kan'traiv(a)nsiz." from " 5i ad'ventjaz av 'mista 'vad(a)nt grim." bai
kA0ba't biid. nout. — in 'spait av 'oil (h)iz 'dodsiz, Si in'dsimjas 'mista
'baunsa 'woz plaud. 20. 'nik(a)las5 'niklbi dis'kAsiz (h)iz 'draima wi5
'mesaz6 fo'lsa(r)7 an(d) 'lenvil. 'nik(a)las waz 'AP bi'taimz in 8a
'moiniq ; bAt (h)i' (ha)d8 'skeasli bi'gAn ta 'dres, 'notwiG'stsendin 9,
(h)wen (h)i' 'haid 'futsteps a'sendiq Sa 'steaz, an(d) waz 'prezntli
sa'l(j)uitid bai 5a 'voisiz av 'mista fo'lea, 5a 'psentamaimist, an(d)
'mista 'lenvil, 8a tra'dsiidjan10. ' 'haus, 'haus, 'haus ! " kraid 'mista
fo'lea. '(h)wot 'hou ! wi'5in '5sa ! " sed 'mista 'lenvil in 9 'diip 'vois.
'kon'faund11 5iiz 'felouz! 0oit 'nik(a)l9s ; 5ei v 'kAm t9 'brekf9st ai
s(9)'pouz. "ai 1 'oupn 5a doi(a) di'rek(t)li, if ju1 1 'weit an 'instant." 1
'problem. 2 5ei 9. 8 ju' 4 fo' 59m, f9(r) 9m, fo'(r) 9m, fr 9m. 5 mei
bif prg'naunst 'nikolas in 'evri 'instgns. 6 'mesJ9z, 'vAlggli 'mejgz. 7
mei bi1 prg'naunst fg'lsg, 'fols9, fo'leo in 'evri 'inst9ns. 6 hi' 9d. 9
notwiS'staendin. . n kgn'faund. 18
The text on this page is estimated to be only 15.16%
accurate

^9 'dsentlman in'triitid (h)im 'not to 'hAri (h)im'self ; 'send,

to bi'gail 5i 'int9v(9)l, 'heed1 9 'fensirj 'baut wi5 859 'woikinstiks on
5o 'veri smoil 'laendin-'pleis, ta 5i An'spiikobl diskom'pou59(r) av 'oil
Si 'A^9 'Iod39z 'daun 'steaz. * 'hi9, kAm 'in," sed 'nik (9)198, (h)wen
(h)i' d2 k9m'pliitid (h)iz 'toilit. " in 89 'neim 9v 'oil Sot s 'horibl8,
'dount meik 5aet 'noiz aut'said." " an An'komon 'snAg 'litl 'boks, '5is,"
sed 'mista 'lenvil, 'stepirj 'into 89 'frAnt ru'm, 9n(d) 'teikiq (h)iz hset
'o'f4 bi'foi(9)(r) i'5 k9d6 get 'in 9t 'oil. "p9''ni$9s rsnAg." "f9(r)7 9
'maen 9t 'oil p9'tikjub(r) in 'sAtS 'msetoz, it 'mait bi' 9 'traifl 'tui
snAg," sed 'nik(9)l9S ; "'foi, oil'Sou8 it 'iz, An'dautidli 9, 9 greit
k9n'vi:nJ9ns t9 bi? 'eibl to 'riitj 'eniGiq ju1 'wont from 5e 'siiliij 01 89
'flo:(9), o'(r) 'ai59 'said 9v 89 'ru'm, wi'Saut 'haevirj t9 'muiv frgm
j(u)9 'tSso, 'stil 5iiz10 gd'vamtidsiz kgn 'ounli bi' 'heed in gn
9'paitni9nt ov 5a moust 'limitid 'saiz." " (i)t 'iz nt11 9 'bit tui kgn'faind
fa(r) 9 'singl 'msen," ri'tgind 'mist9 'lenvil. "'5aet ri'maindz mi', —
'mai 'waif, 'misto 'd3ons(9)n12 — ai 'houp 'Jii 1 (h)9v13 SAm 'gud
'pait in 5is 'piis ov 'JU9Z1?" "ai 'glainst 9t 69 fren(t)$ 'kopi 'laist
'nait," sed 'nik(9)l9s. " it 'luks 'veri gud, ai 'Gink." ''(h)wot d(u) J9
'miin t9 'du; fg 'mi:, 'oul(d) 'feta1*1?" aiskt 'mist9 'lenvil, 'poukirj 5o
'strAglirj 'fai9 wi5 (h)iz15 1 (h)od. 2 i' (h)od. 3 'horobl. 4 'hset o'f. 6
bi'foi(9) hi'. €kud. 7fr, fo-(r). 8 'fo'r o:l'5ou, f(o)r oil'gou. * it s
An'dautidli. 10 stil '5i:z. n it s 'not. 12 niklbiziz 'pen neim. 13 Si- 1
'hgev. l4 'felo(u). 15 wiG hiz. 19
The text on this page is estimated to be only 14.70%
accurate

'woikinstik, on(d) 'aiftawadz 'waipirj it on 5g 'skgit 9v (h)iz

'kout. ' 'eni6irj in 59 'grAf an(d) 'grAmbl wei 1 " "juf 't9in j(u)o 'waif
on(d) 'tjaild aut ov 'do:(o)z," sed 'nik(o)10s ; " 9n(d) in 9 'fit ov
'reids on(d) 'dselosi, 'stseb j(u)o(r) 'eldist 'sAn in 89 'laibrari." u 'dui
ai 'Sou ! " iks'kleimd 'mista 'lenvil. '* '5aet s 'veri gud 'biznis." ' 'aifta
'(h)witS," sed 'nik(9)l9s, ju1 9 'trAbld wi5 ri'mo:s til 59 'laist 'sekt,
9n(d) '5en ju? 'meik Ap j(u)o 'maind t9 dis'troi j(u)9'self. 'bAt, 'dsAst
9z j(u') o 'reiziij 5o 'pistl t(g) j(u)g 'bed, 9 'klok 'straiks — 'ten." " ai
"sii1," sed 'mist9 'lenvil. ''veiri 'gud!" "ju1 'poiz," sed 'nik(9)l9s; uju*
rekg'lekt tu (h)9v 'hgid o 'klok straik 'ten in j (11)9(1-) 'infgnsi. 59
'pistl 'foilz from j(u)9 'hsend — ju1 g(r) ouvg'kAm — ju- 'b9ist 'into
'tigz, 911^) bi'kAm 9 'v9itju9s 9n(d) ig'zemplgri 'kserikt9(r)a 'ev9(r)
'a:ft9W9dz." * 'k^epitl ! " sed 'misto 'lenvil ; " 5set s 9 'Ju98 'kaid, 9
'S(0u(i)o kaid. 'get 59 'kgitn 'daun wi5 9 'tAt$ 9v 'neit^9 laik 'Sset,
9n(d) it 1 bi1 9 trai'Amfgnt sgk'ses." ' 'iz 5(s)9(r) 'eniGirj 'gud f9
'mi:1?" in'kwaigd4 'misto fo'l69 '»q(k)$osli. ''let mi1 'sii," sed
'nik(9)l9s. u'ju: plei 59 'fei9f(u)l 9n(d) 9't8et$t 's9iv(9)nt ; juf 9 't9ind
aut 9v 'do:(g)z wi5 59 'waif on(d) 'tjaild." ' 'oilw(e)iz 'kApld wi5 '5set
in'foml fi'nominon," sed 'misto fo'ls9 ; " 911 (d) wi* 'gou 'intg 'pu96
'lodsirjz, (h)we9(r) ai 'wount teik 'eni 'weid3iz, 9n(d) 'to:k 'sentimgnt,
ai s(9)'pouz1" 1 'ai 'si:. 2'kger9kt9(r). 8 '$09, '$09, 'Jo:. 4 in'kwaiod.
5 'p09, 'po9, 'poi.
The text on this page is estimated to be only 14.85%
accurate

' '(h)waii — 'je(:)s," ri'plaid 'nik(a)las; * 'b'aet s 5a 'koi(a)s

av 5a 'piis." " ai 'mAst (h)av1 a 'dams av 'sAm kaind, ja2 'nou," sed
'mista fo'lsa. "ja2 1 'haev tu intra'djuis3 WAD fa Sa fi'nominan, 'sou
ja2 d 'beta meik a 'pai da dai4, an(d) seiv 'taim." 5(e)o z 'nA0irj 'iizia
5an '5aet," sed 'mista 'lenvil, ab'zaivirj Sa dis'taibd 'luks av 5a JAq
'draematist. e'pon m(a)i 'waid, ai dount 'sii5 'hau it s ta bi1 i'dsoind
'nik(a)las. ' '(h)wai, 'iz nt it 'obvias6 ? " 'ri:z(a)nd 'mista 'lenvil. '
'gaed'zuiks ! 'hu: k(a)n 'help 'sii(i)r) 5a 'wei ta 'dui it? ju* as'tonij mif
! ja2 'get 5a dis'trest 'leidi, an(d) 5a 'pua7 'litl 'tjaild, an(d) 5i a'tsetjt
'sa:v(a)nt 'inta 'pua7 'lodsirjz, 'dount ja2(? — 'wel, luk 'hia. 5a
dis'trest 'leidi 'sinks 'intu a 'tSsa(r) an(d) 'beriz (h)a- 'feis in (h)a-
'pokit'hsenkatSif — ' '(h)wot meiks ju1 'wiip, ma'mai 1 ' sez Sa
'tSaild. ' 'dount 'wiip, ma'mai, 'o; ju1 1 meik 'mi: wiip 'tui ! ' — '
an(d)8 'mil ! ' sez 5a 'fei6f(u)l 'saiv(a)nt, 'rAbirj (h)iz 'aiz wi5 iz 'aim. '
'(h)wot kan9 wi1 'dui ta 'reiz jua 'spirits, 'dia ma'mai1' sez 5a 'litl
'tjaild. 'ai, '(h)wot kan9 wi' 'duif sez Sa 'fei6f(u)l 'saiv(a)nt. ' 'ou
'pisa10!1 sez Sa dis'trest 'leidi ; ' 'wud 5at ai kad11 Jeik 'o?f 5iiz
'peinf(u)! 'Goits.'— *'trai, mam12, 'trai,' sez 5a 'fei9f(u)l 'saiv(a)nt ; '
'rauz j(u)a'self, mam; bi'13 a'mjuizd.' — 'ai 'wil,' sez 5a 'leidi; ' ai 1
'lam14 ta 'sAfa wiS 'foititjuid. 1 mast 'hsev. 2 juf. 3intro'djuis ; in
'kealis 'spiitj intra'dsuis (a pranAnsi'eiJ(a)n not reka'mendid). 4 'inglij
pranAnsi'eiJ(a)n av pa da 'd0. 6 'dount sii. 6 'obvjas. 7 'poa, 'poa,
'poi. 8 send. 9 (h)wot 'ksen. ° 'ingliS pranAnsi'ei$(a)n av 8a 'fren(t)S
neim 'pjsir. n kud. 12 maem, 'maedam. 3 'bii. 14 ai 'wil lain. 21
The text on this page is estimated to be only 16.83%
accurate

d(u) jir ri'membg Saet 'dams, mCa)!1 'onist 'frend, '(h)wit$,

in 'haepi 'deiz, ju- 'praektist wi5 ftis 'swiit 'eindsfc)!'? it 'nevg 'feild to
'kaim m(a)i1 'spirits '5en. ou ! 'let mi> 'si: it 'WARS g'ge(i)n bi'fo:(g)
(r) ai 'dai ! '— 'Sso(r) it 'iz— 'kju: fg2 5g 'baend, ' bi'fo:(g)(r) ai 'dai,'
— 9n(d) 'o'f 5ei 'gou. 'Saat s 5a 'regjub 0irj ; 'iz nt it, 'tomi1?" ' 'Saat
s 'it," ri'plaid 'misto fo'leo. " fo dis'trest 'leidi ouvo'pauod bai 'ould
rek9'lekj(9)nz3, 'feints at Si 'end QV 5o 'dams, 9n(d) jo4 'klouz wi8 9
'piktjo." from u'nik(o)los 'niklbi," bai 'tjailz 'dikinz. 21. 'misto 'bamz
raits to hiz5 'gaidjgn f9 'niAni. ['mist9 'bamz, 9 'Undgn 'medikl
'stjuid(9)nt, 'eid 9v o 'felo(u) 'stju:d(o)nt, i'volvz o 'ploizibl 'leto,
(h)witj, to'geSo wi5 89 dis'kA$n 9'kAmp(9)niir) its k9n'kok$(a)n, iz
'givn bi'lou.] 5o 'dif(o)rons bi'twin 5i i'pist(9)l9ri 9nd 89
konvo'seij(9)n(9)l 'stailz Jud bi' 'noutid. 'mist9 'bamz di't9imind tu
o'piil t9 hiz5 'gaidjgn. it 'wud nt 'dui tu a:sk (h)im 'point 'blasnk fof6
5o 'mAni; bot (h)if went 'ouv9 89 'kwestS(a)n in 'oil its 'beorinz wi8
'misto 'kAf, 911 (d) 'aift9(r) o 'greit 'meni 'kopiz, Sei pro'djuist 89
'folo(u)ir) i'pisl bi'twim Som : — mai 'dig 'gaidjgn, 'haeviq 9 'spsg
'haif-'aug from Si 'oilmoust An'siisirj — '(h)wot Jl wi 'sei 'aiftg(r)
'Ansiisirj'?" in'kwaigd7 'mistg 'bamz. 1 0i'aetrik(g)l trg'di$(8)n in'sists
on mi fg mai. 2fof. 8reko'lek$(a)nz. 4juf. 5 tu iz. 6fg. Tin'kwaigd.
The text on this page is estimated to be only 14.90%
accurate

z 5g 'w9id," 'ctmsgd 'kAf. " 5ei 'put it in 59 'kaidz a(v)

'lektjaz. 'kg'rikjubm 9V 'stAdi.' '5set 1 'nok im 'ouvo(r) ot 'WARS, if i1
z 'fiibl-'maindid." "bgt (h)wot 'iz1 9 ka'rikjalam ] " kgn'tinju-d 'bainz.
((/"i-* • r j9? luk it aut. 'mistg 'kAfs 'Isetin 'dikS(^)n9ri (h)gd 'nou
'kAV9z, gn(d) bi'gsen at 'es-'pi-'a:(rl2 in Si 'ingliS-'leetin 'pait, an(d)
'endid at 'ou-'a:(r)-'en3 in 59 'laetin-'ingliS. 'fo:tS(9)n9tli 89 'w9id
ri'kwaigd W9z in 89 'po:J(9)n ik'staent4. kg'rikjulgm,' ' Aams9d
'mistg 'kAf, 9 'pleis ta 'rAn in.' ' 'mistg 'bainz 6oit 'sAmGirj g'baut 9
'krikit 'graund. ' ' 9 'kait,' " kgn'tinju'd 'mist9 'kAf, " '9 'kAst9m(9)ri
'eksgsaiz.' ' " '5set 1 'dui," sed 'mist9 'bainz. ' 'hevn fa'giv mi' ! '
ka'rikjulgm ' z (59 wa:d." an(d) (h)if went 'on5 'raitin. ' 9v mai
ko'rikjulgm 9v 'stAdiz, ai 'ksenot, ai 'Gink, im'ploi it 'bet9 San in 'letirj
ju1 'nou 'hau ai (9)m 'getiq 'on, az it s 9 'lorj taim sins ai 'rout 'laist.
ai (ojm in 'kAmfgtabl 'lodsiijz — "ai d 'sei 'at 'prezant,' " sg'dsestid
'mistg 'kAf, huf (h)9d6 SAm 'veig 'fi9(r) 9v 'mistg 'bainz 'kAmirj t9 'liv
in'taigli. " ou ! 9v 'koi(9)s, Sset s Andg'stud. 'on wi 'gou 9'gen. -'wi5
'ounli 'WAU 'droibeek. SAHI 'disipeitid JAFJ 'men liv in 59 'haus, huiz
'noiz 9t 'taimz kgn'fjuiziz mi'. 5ei 'nev9 siim t9 'teik 'eni 'tii, no: 'hsev
5ei 59 'slaitist ai'dig 9v prg'feS (0)^(9)! 7 konv9'seij(8)n, 'bAt ai
(h)9v 1 '(h)wot s. 2 =SPR. 8 =ORN. 4'ekst9nt. 5 'went on, 6 'heed.
7pro'fe$(a)n(9)l. 23
The text on this page is estimated to be only 20.86%
accurate

'foimli, Sou 'mail(d)li, ri'fjuizd Sso(r) o'proutjiz tu 'intimosi.' "

"i* 'wount Gink it s 'mi:, Sou, jo 'mini — 'wil i1 1 " 'aiskt 'misto 'kAf.
'''oil 'rait," ri'plaid (h)iz 'frend. ''hau 1 i1 'nou '(h)weo(r) it 'iz 1 ai m
'not 'go(u)ir)1 to 'put Si o'dres." " S(e)n 'hau 1 jo 'get So 'mAiri 1 " "
ai (J)l haev it 'sent to So 'hospitl, 'Ando 'kAvo, to So 'sekrit(o)ri2.
'dount jo 'sii hau ris'pektobl it 'luks! 'a:, 'Saet puts mi' in 'maind —
'hau (o)m ai tu 'disk fr it?" '' 'sei jo 'wont it fo di'sek$(o)nz." ''nou
'gou, 'fred," sed 'misto 'bainz, 'Jeikiq (h)iz 'hed. if ai d di'sektid 'oil So
bilz o(v) moi'taeliti, ai 'kud nt (h)ov 'got '0rui So 'nAmbo(r) ov
'sAbdsikts ai v 'peid fo1 — o'koidirj to Si o'kaunt sent to So
'gAv(o)no. (h)wot 'dods 'wil 'du:3?" ''sei S(o)(r) o 'frej 'lektjoz tu
o'tend." " (i)t 'woun(t) 'dui. (h)i- kom'paundid fo Som4 'oil in o 'hiip
(h)wen ai 'keim Ap5 to 'taun." ' 'kaint jo 'giv o do'mestik 'tAt$T'
"'Sset s 'beto— 'le(t) mi 'sii— ' ai (h)ov boit 'leitli 'sev(o)rol 'vseljuobl
'buks ov o mis'gaidid 'stjuid(ojnt 'hui6- 'stop! 'spouz i1 'wonts to 'si;
(S)om 1 " * 'ou, (h)i' 'wount — bi'saidz, if i' 'dAz — 'get o lot o(v)
'leetin 'voljomz7 from 'oil 'Si:z ot 'sikspons ' ot o 'bukstoil, on 'sei Ss
o 'veri 'rso. kAt 'on." -' ov o mis'gaidid 'stjuid(o)nt hu? 'wilf (o)li '0rui
o'wei So 'tSainsiz (h)witj auo 'noubl insti'tjuiS(9)n 1 goirj. 2
j3okrot(o)ri. 3 '(h)wot dods 1 'dui? (h)wot 'dods 1 'dui 1 ~* f{o)r
om. 5 keim 'Ap. 6 hu1. 7 'volju'mz. 24
The text on this page is estimated to be only 15.06%
accurate

a'foidid. ai (h)av 'oilso(u) 'hsed mai 'leis-'Ap 'buits

'nju:'futid; 0n(d) mai 'blaek 'kout 'fre$ 'bAtnd 9n(d) 'k.vft wi5x 'piisiz
fram in'said 69 'skaits ; 9z ai '0o:t if ai (h)gd 'juizd 'juui klo'9 5g
'kontraist wud2 (h)9v bi'n 'tui 'vaiolont3. wi5 '5is ai $(9)! bi1 'eibl t9
gou 'on 9 'litl 'longo ; 'bAt, ai mis'trAst4 mai 't$ek 'trauzgz. ai (h)9v
'oilso(u) 'drArjk 9 greit 'dill5 9v 'kofi 'leitli, (h)witS 'klips mi1 9'weik 9t
'nait t9 'stAdi; 9n(d) Sg 'prais 9V 'koulz iz 'raiziij 'kru'ili6, 9z 'wel 9z
pro'vi5(9)nz7. ai (h)gv '5s9fo:(9) 'stopt 69 bred 9n 't$iiz — "ai d 'sei
''biskit 9n 'tjiiz,' if 'ai W9 'ju:," sg'dsestid 'mist9 'kAf ; it saundz
'11191(9) laik 9 'lAk$9ii8." — Co "biskit 9n 'tjiiz,' " 'mist9 "bamz went
'on, (h)witj ai 'haed fo- 'lAn(t)S, en(d) 'haev 9 'roul on(d) 9 'glais 9v
'eks(e)ldnt 'wo:t9 from 5o 'hospitl 'filto. juf wil pg'haeps9 'smail at
'5is, bAt ai 'du: it on 'prinsipl.' " "'nau, if 'ai W9 'jui, ai d 'ou 9 'msen
S9in 'niAni," sed 'mistg 'kAf. ' 'hu: k(g)n juf 'ou?" ai 'dount 'ou
'enibgdi 'niAtS, '68en(k) 'gudnis," ri'plaid 'mist9 'bainz. >('5en wi1
mgst in'vent 'sAmbgdi," 9b'z9ivd 'mistg 'kAf. u(h)wot d J9 'Gink 9V 9
'paigs JATJ 'skotSmon1?" bat '5ei 'nev9 lend 'mAni tu 'enibgdi." a:,
'Sis 1 bi' 911 ik'sepS(9)n. gou 'on frgm 'mai dik'teitin. 'ai (9)111
'slaitli in 'det wi5 9 JAIJ 'ed(i)nbr9 'stju:d(9)nt, hu1 'livz at 5a 'top av
o~9 'haus, an(d) (h)az 'promist t9 'Sou mi1 'hau t9 'wo$ 9n(d) 'staitj
mai 'oun '$9it-'kol9z — ' " 1 wi6. 2 wgd. 3 'vaiglant. 4 'mis'trAst. 5
'greit diil. 'kru'ali. 7 pra'vis(a)nz. 8 'Uksjuri, 'kkSuri. 9 'pra3ps. 25
The text on this page is estimated to be only 14.30%
accurate

"'kaepitl!" i'dsaekjuleitid 'mista 'bamz; — "'an(d)'dam mai

'soks wi5 9 pous^'moitam1 'niidl' — ai d put 'Saet 'saitnli ; (i)t 'luks
so(u) 'iika'nomikl. — ' hi' (i)z en 'eks(a)l9nt ri'lidsas JAFJ 'maen,
an(d) 'givz mi- a greit 'dill2 av inf9'meiS(a)ft on 'Girjz in 'd3en(9)r9l,
'11101(9) (r) is'pe$(a)H 'sAtJ az o kg'nektid wiS aeng'tomikl 01
'medikl ''veiri 'gud," sed 'mista 'kAf, "bat 'nau ai 'Girjk 9 'litl
individju'seliti (w)9d3 'bii av 'juis. 'kaint wif meik an 'senikdout a'baut
im — tu is'taeblij im, ja 'nou, az a 'faekt — 'sAmGirj 'aut a Sa 'wei 1
'(h)wot 'wud nt a 'skotSman 'dui? " "'gou 'bsek ta 'skotland a'ge(i)n,"
sed 'bamz. '''nou, 'nons(a)ns4! Sset s 8i 'oul(d) 'biznis. 'ai v 'got it —
gou 'on. * 'SAHI av 5a 'greislis 'stjuid(a)nts 'pleid (h)im a 'saed trik5
laist 'wi:k. ju1 'nou, ai 'deasei6, (h)wot a 'steGaskoup 'iz — 'sAmGiq
laik a 'wudn 'ksendlstik wi'ftaut a 'staend, 'juizd ta 'test 5a 'steit av
$9 'Urjz.' " "'doun(t) put 'krjz,'" ab'zaivd 'mista 'bamz, "'put '
6a'ra3sik7 'visara ' — (i)t s 'graanda." ''rait 'ou! 'nau 5(e)n! ''WAU av
5i 'A^az 'boro(u)d (h)iz 'steGaskoup Si 'A^a 'dei, an(d) 'stopt it 'AP
wi58 'sAmGirj from 5i in'said av a 'tin 'trAmpit. (h)wen 8a 'skotSman
went 'raund Sa 'woidz wiS 8a fi'ziS(9)nz 'neks(t) 'dei, hif 'faund 8(s)a
waz 'sAmOirj in (h)iz 'steGaskoup; an(d) on 'trai(i)q ta 'blou Gru-9 it,
(h)witj i- had10 bi'n in 5a 'haabit av 'duiirj bi'foi(a) hi-11 'juizd 1
pous(t)'moitem. 2 'greit dill. 8 (wu)d. 4 'nonsens 1 6 saed 'trik. 6 in
'raapid 'spiitj, de'sei, da'sei. 7 Go'raesik. 8 wiG. 9 blou 'Gru:. 10 hi-
(o)d. " bi'foi(a) (r) i*. 26
The text on this page is estimated to be only 18.61%
accurate

it, hi1 'meid sot$ o 'streind3 noiz1 Sot (h)i' woz 'teikn 'AP
'sAm(h)wot 'Jaipli bai 'dokto 'bAlb. 'Sis woz o'hctitlis 'trik, on(d) wil
'giv ju? 'sAm ai'dio ov So 'set ai (9)111 so'raundid 'bai,' " ''wsl —
'Sset 'iz a 'sto:(o)ri ! " kraid 'misto 'bainz, 'geiziij wi5 8edmi'reiS(9)n
on 'mistg 'kAf. "'did ju'a in'vent it 1 " "'nou — 'tru:, 'oil trui — (o)'pon
mi 'ona. nau 'jui go(u) 'on, bi'ko'z 'jui nou 'best hau to 'get 5o
'mAni." "ou, '5set s 'sum dAn," sed 'misto 'bamz. 4'5is. JAq 'msen
'hsez, from 'taim to 'taim, 'lent mi1 'smoil 'sAmz ov 'mAni, (h)witj ai
'wij to ri'toin, oz (h)iz 'soikomstonsiz o 'not 'veri 'gud. 'sou, 'if ju? wil
'send mi* o 'faivpaund 'nout3, 'Ando 'kAvo, to 'misto 'linti, So'hospitl
'sekrit(o)ri4, juf wil o'blaids mi-.' " 'let mai 'frendz hsev 5is 'leto to
'riid, oz it 'mei o'mjuiz 5om. on(d) 'giv mai 'kaind '!AV tu 'aint 'spinor
on(d) 'tel (h)o-(r) ai Sfc)l bi- 'gleed to 'kAm on(d) teik 'ti: wi8 (h)o?0
'(h)wen ai ri'tom, on(d) in'devo tu ento'tein (h)o' wi5 on o'kaunt ov
mai 'Lmdon 'duiirjz ' — ai 'sei, 'fred, 'fsensi if ai wo to 'tel (h)o'(r) 'oil
! " on(d) bi'liiv mi* to ri'mein, 'veri o'fek$(o)notli 'juoz, 'robot 'bamz.'
" "if '5set 'dAznt 'dui it, 'ai m o 'dAtJman ! " hi* iks'kleimd oz (h)i'
kon'kluidid6. from 'kristofo 'taedpoul," bai 'selbot 'smi9. 1 'sAtJ o
streinds 'noiz. 2 'did jo, 'd: ju, 'di jo. 8 fo'miljoli : 'fai(v)pon'nout,
'fai(v)pAn'nout. 4 'sekrot(o)ri. wi9 hof. 6 kon'kluidid. 27
The text on this page is estimated to be only 15.00%
accurate

22. 5g 'fe59(r) in 5a 'haus 9v 'moi(9)nirj. [59 'fe5o(r) iz

sa'pouzd t9 'spiik.] ai wgz in 8 'haus 9V 'moi(9)nin. '5aet 'iz, 69
'$At9z w(s)g 'paitli 'klouzd ; 5g 'kgitnz w(s)9 'droin ; $9 'dresmeiko(r)
od1 teikn 'oidgz £9 'blsek; 9n(d) 'veri dig 'frendz w(e)9(r) in'vaitid tu
9 "fjmn(e)roL 'beki, 89 'meid, — ai 'ongd (h)g rez9'l(j)uiS(8)n2 —
strAgld 'haid t9 'luk Iu(:)'g(j)uibri9s8, 'not 9t 'oil 'kAmfgtid bai 59
'prospekt 9V 9 'njui 'gaun ; '(h)wailst 69 'foititjuid 9V ^9 bi'riivd4
'misiz 'kraemp W9Z 9n ig'zaimpl tu 'oil 'njuili di'livod 'wido(u)z. ai
prg'test5 ai 'lAvd 59 'wumgn f9 hg(r)6 'onisti. 5o 'bre9 'bi:(i)rj 'fegli
aut 9V (h)9f 'hAzbgnd, '5aet 'iz, (h)g' 'hAzbgnd bai 'kondsugfc)!7 'loi,
Si1 'nai5o 'wept, no: '(h)waind, 'nevo 'koit (hVself in 9
'straerjgjuleitirj 'sai ; bgt 'waipt 'oil di'failiq 'griif from (h)9f 'feis sz Ji1
(wu)d (h)9v 'waipt 'flai-spots from 59 'tjaing. Ji1 lukt 'moi(9) 5(o)n
ri'zaind. 6'9 'kraemp W9Z 'skruid 'daun, ai 'h9id (h)g' 'laif 'Ustili ;
oil'biiit 5o 'praektist 'beki 'begd (h)9- 'mistris "'not to gou 'on sou
''stirik(9)li8'; oz ''stiriks9' 'wud nt brirj (h)im 'bask; (g)n(d) (h)wai
'$ud 5ei — 'woz nt (h)i- in 'hevn?" 'misiz kraemp di'kleod Ji1 'kud nt
'help it ; 9n(d) frgm mai 'hart ai bi'liiv 59 'wumgn. "ai W9z 9 'gud
'waif t9 him10, 'beki," sed 59 'wido(u), 'smailirj in 59 'veri 'swiitnis 9V
'konj(9)ns. 1 'dresmeikg (h9)d. 2rezo'l(j)u:$(9)n. 8 19'g(j)uibri9s.
pro' test. 6 f9(r) 9'(r), fof(r) 9'(r), fr 9'(r). 8'stirik(9)li; An'edjukeitid
fof his'terikoli. 'stiriks"^= his'teriks. 10 tu im. griv. 5 28
The text on this page is estimated to be only 15.10%
accurate

' (h)wen (h)i1 waz a'laiv, m(am), ai 'oilw(e)iz 'sed ja waz1

'tu; 'gud fa(r) im2; bat 'nau (h)i- z 'dsAst 'go-n (i)t iz nt3 'rait ta 'sei
sou. 'stil (h)if waz 'ould, m(9m) ; s on (h)iz 'kofin, sou4 5(s)az 'nou
'haim in 'sei(i)i) 'nAGirj z 'wikida 5(a)n tu o'bjuiz 89 'die 'ded, m(om).
'stil (h)i' 'woz 'ould." "hi- 'woz," sed 5o 'wido(u), wi55 'slait 'emfasis.
'* 'nevo kod6 (h)av bi'n 'gud'lukirj ; 'b.vt, 'bles (h)im, 'dia 'soul ! 'hui
d 'bleim (h)im fa '5set 1 'stil, hi' 'neve kad6 (h)av bi'n 'h8en(d)sam,"
sed 'beki. "ai 'neva haid 'enibodi7 (h)u' 'sed az 'niAtJ. bat '(h)wot s
'bjuiti in a 'msen, 'beki? 'nA6irj. 'neva^a'les, (h)i' 'woz nt8
'h8en(d)sam, 'god 'nouz ! " kraid 5a 'wido(u). " an(d) '5en wi1 'oil
(h)av aua 'tempaz, m(am), ta bif 'Jua9. fa(r)10 'oil 5set, m(am),
'maista waz11 a 'litl12 'saua. 'sAmtaimz, az wan13 me(i)14 'sei, hi' d
'bail15 'ouva wi5 'viniga." "hi' 'ment 'nA6in, 'beki; 'nA0ir) at 'oil," sed
'misiz 'krsemp. (i)t waz 'ounli in aua 'hAnimum, ai ri'memba — 'hiai,
'beki ! "— 'hia 5a 'wido(u) 'slaitli '^dad— "ai J(e)l 'neva fa'get mai
'hAnimum ! " ''jes, m(am) — bat16 ja w(s)a 'goCu)!!]17 ta 'sei —
'(h)wot did 5a 'maista 'dui 'Sen, m(am) ] " "'swoi(a) laik 'eni 'truipa,
'beki. bat 'siknis did (h)im a 'dill av 'gud," sed 'rnisiz 'kraemp. 1
An'edjukeitid fa w(e)a. 2 fr im, fa him, fof him, for im. 8 (i)t s 'not. 4
sa. 5 wi9. 6 'neva 'kud. 7 'enibadi. 8 waz 'not. 9 'Soa, 'Joa, 'Joi. 10
fo-(r), fr. x 'woz. 12 'liitl. 18 wAn. u ma. 5 'bail ; 'vAlga fa 'boil. 16
bAt. L7'goirj. 29
The text on this page is estimated to be only 18.79%
accurate

"'kwait 'kjuod (h)im 9t 'laist, mfem). 9n(d) 'Sen — l?9t it s 9

'komon fo'lt — (h)i' 'did IAV 'niAni 9 'li(:)tl, m(9m) 1 " 9n(d) 'beki
'poizd. So 'wido(u) meid nou 'amso, bAt, 'glamsirj 9t
(h)9'meids9iv(9)nt, 'drui 9 'lorj 'sai. " 9n(d) '(h)wot woz So 'juis,
m(om)1? jo nou (h)i' 'kud nt teik it 'wiS (h)im1." 'hio(r) 9 'b9ist 9v
'lait 'senimeitid So 'wido(u)z 'feis, 9n(d) $i* 'kraid — S9 'monosilobl2
'bgeblirj from (h)o' 'hait u , , ,, — nou!" " ai 'wud nt 9'bjuiz Sg 'ded
fg Sg 'wg:ld, m(9m) ; b9t 'piipl 'koild (h)im 9n 'ould 'dsui," sed 'beki.
" hi1 'woz nt 'Sset, 'beki," 'amsod So 'wido(u), in So 'maildist, 'swiitist
toun ov ri'pruif. "bot (h)if 'did laik to 'draiv o 'baigin. hi1 'did IAV
'moi(o) S(o)n (h)iz 'pen90," kraid 'beki. "hi- wgz 9 'msen g(v) Sg
'wgild, 'beki," sed 'misiz 'krsemp. "mimim! mgm," sed 'beki, 'haidli
'nouiq Sg 'trui6 $i* 'Atgd ; "if so(u) 'meni8 fouks 'woz nt4 (h)wot Sei
'ko:l Som'selvz, ''men o(v) So 'woild,' So 'world, m(om), 'wud nt bi'
so(u)6 'bsed oz it 'iz." "ai 'deunt 'Gink So puo6 'msen 'left it 'wois
S(o)n (h)i' 'faund it," ob'zoivd So meenz 'wido(u). "on(d) 'Sen — if
(h)if 'woz nt 'ded, ai d 'sei it — (h)i' 'juizd 'ju: laik 'eni 'toik." " (i)t
woz (h)iz 'fon(d)nis, 'beki ; ot 'Hist, ai 'houp (i)t woz (h)iz 'fon(d)nis."
1 'wi9 him. 2 'monosilobl. s 'sou moni, so 'meni. 4 'woznt ;
An'edjukeitid fo 'w(s)o nt. 5 'bi: so. 6 poo, poo, po:. 30
The text on this page is estimated to be only 15.50%
accurate

, m(9m), ai v 'sed it o'ge(i)n (o)n(d) 9'ge(i)n. ju'1 W9z2 'tui

'gud fa(r) imV kraid 'beki. mai bi'liif ot 5o 'taim woz4 5ot 'misiz
'krsemp (h)od 'log bi'n ov $9 'meidz g'pinjgn5. hau'evg Si1 'amsod,
"'5aet s 'ouv9 'nau, 'beki." "it 'iz 'ouvg, 0n(d) o 'gud 6irj 'tui ; fo(r)6
'noubgdi7 Jgd8 spiik 'il o(v) 5g 'ded — ai 'mAs(t) sei9 it — 9
'w9iS910 maen 'nev9 'livd." '''beki, 'dount dis'tres mif; 'kAm 'hi9." wi5
'5is milk ri'pruif, 'misiz 'kraemp 9'proutjt (h)we9(r) 'ai W9z 'lai(i)rj,
'folo(u)d bai (h)g' 'meid. " (i)t 1 bi1 9 '6auz(9)nd "pitiz," sed 59
'wido(u), 'teikirj mi' 'd3entli in (h)g1 'hsend. ''kwait 9 'sin, mfgrn), t9
'dui it," sed 'beki. " 9n(d) 'jet ai 'niAst gou int9 'wiidz," sed 69
'wido(u). IC'oil 59 'bet9, m(9m) ; ju' 'dm luk so(u) 'nais11 in 'blaak,"
kraid 89 'meid. "it s Tdie(p),-" ai '0oit, "ai v bi'n 89 'sAbd^ikt 9v
'pri:vJ9S konv9'seij(9)n, 9n(d) 'mistris 9ii(d) 'meid 9 'nau dis'kAsirj
mai 'feit. '(h)wot (w)gd12 bi'kAm 9v mi' 1 " "9 '0auz(g)nd 'pitiz to
'dai it," sed 'misiz 'krsemp, stil 'geizirj 9t mi1. ai 'trembld 9t 89 'w;9id
0ruf 'evri 'filgmgnt. 'dai 'mil! '(h)wot! 'woz ai13 t9 foi'gou, 9n(d) 'sou
'sum, 89 'snou(w)i 'pjugriti14 9V mai 'aut'said1? in 59 'veri 'bjuiti 9v
mai '(h)waitnis — in mai ik'selirj15 'kaendg — to bi' 'daid ^'9, 'ju:.
2w9z; An'edjukeitid f9 w(s)9. 8fr im, £9 him, fof him, for im. 4 'woz.
6o'pinJ9n. 6fo:(r), fr. 7 'noubodi. 8 Sud. 9 ni9st(t) 'sei. ° 'w9is9 ;
'vAlgg fo 'wois. u 'sou (')nais, so 'nais. ]2 'wud. ]3 'woz 'ai, W9Z 'ai. 4
'pju9r9ti. 1S ek'selirj. 31
The text on this page is estimated to be only 16.00%
accurate

'pitS-'blaek? fa1 'nou fo-lt av 'main, bat 'oil 5a '(h)wim, 5a

'tiranas ka'priis av a'nA^a, ta bif di'greidid ta fta 'niigro(u) 1 "an(d)
'jet it 1 'wsa(r) a 'log taim 'daid," mjuizd 'misiz 'krsemp. "'dAznt 'Sou
5a 'dait, ta bi '$ua2, m(am)," sed 'beki. "'stil it s8 a 'piti. 'jet ai 'mAst
bi- 'blsek fa(r)4 a 'twelvmAnO, 'beki," ab'zaivd 5a 'wido(u). ja 'mAst,
ta bi' 'di:s(a)nt, m(am)," 'ainsad 5a 'meid. 'sAdnli, hau'eva, Ji- 'Goit
av a 'probabl is'keip, an(d) 'aedid, " An'les5 ja6 'mseri bi'fo:(a),
m(am)." " bi'foi(a)(r) a 'twelvmAn9 ! '(h)wot 'du: ja6 'Giqk mi', 'beki?
— 'wel, 'beki, wi- Jl 'sii " sed 'misiz kraemp. from " 5a teil av a 'fe5a,"
bai 'dAglgs ' 23. 'vaelantain 'voks 'vizits 5a 'wain 'va'lts at 5a 'daks.
['vselantain 'voks, a JAIJ 'maan 'giftid wi5 Sa 'spirit av 'mistSif an(d)
iks'tro:d(i)nari7 ventri'loukwial 'puaaz, a'kAmp(a)niz (h)iz 'frend
'broidsaidz, a 'lais(a)nst 'vitla, ta Sa 'Lvndan 'doks, (h)wea(r) i'8
a'mjuiziz (h)im'self bai 'Grouiij (h)iz 'vois 'inta 'vearias 'paits av Sa
'wain 'vo'lts.] 'nout. — in '5is 'ekstraakt 'meni di:vi'eij(a)nz from Sa
'no:m(a)l pranAnsi'eiS(a)n wil bif 'faund in 5a ka'loukwjal 'paits. '
'wel, 'kAm," sed 'broidsaidz, " 'nau ai m 'hia, 'let s 'sii hau m(a)i
'ekstra pa'tikjala 'gets 'on." 1 fo'. 2 'Joa, 'Joa, 'Soi. 8 it 'iz. 4 fr, fo'(r).
5 an'les. 6juf. 7ekstra'oidin(a)ri. 8 (h)wsa hi1. 32
The text on this page is estimated to be only 20.92%
accurate

'Sis 'hsepnd t9 bi' 'Ando Si 'opozit1 'aitS, on(d) (h)wail So

'kuipo woz 'in it wiS 'broidsaidz, 'vselontain, hu' woz 'lukirj 'veri
in'tentli ot som2 'kobwebz, po'si:vd o 'toil 'da:k 'figo maitS 'paist
(h)im in o 'maeno (h)witj 'strAk (h)im oz 'bii(i)r) iks'triimli mis'tiorios.
' 'hu: z 'Sset 'to:l 'po:sn (h)u' 'pa:st d3As(t) 'nau 1 " sed 'hi: to So
'ku:po. ' 'wAn o(v) So 'wotjmon. Sei 'woik 'in on 'aut in So 'daik to 'sii
Sot 'nou indi'vidj(u)ol 'peiz 'twais. jo 1 'si: im o'gen 'bai m 'bai3." '
'veri 'wel," 6o:t 'vselontain ; " if ai 'dui, ai 1 'staitl (h)im," on(d)
(h)wail So 'ku:po woz 'brout$irj Si 'ektro po'tikjolo/ hi1 'lukt 'raund
So 'vo'lt wiS on 'a3n(k)Sos 'ai. 'nau S(e)n," sed 'bro:dsaidz, 'haeridirj
(h)im o 'glais, "'d3As(t)4 'tel mi 'wot jo '6irjk o(v) 'Seet." 'vaeloritain
'teistid, on(d) 'faund it 'sou 'splendid Sgt (h)i' 'oilmoust5 An'konjosli
'finijt So 'glais. o'nASo 'glais woz 'dro:n, on(d) (h)wail 'broidsaidz woz
'smelirj it, on(d) 'Jeikirj it, on(d) 'meikirj it gou 'Grui6 'oil soits ov
mo'n(j)uivoz, So 'wotjmon 'paist o'ge(i)n. " Si ! " kraid 'vaelontain,
'Grouirj (h)iz 'vois o'niArj So 'kaisks (h)witj w(e)o 'nio him7. So
'wotSmon 'stud 'poifiktli 'stil. hi' (wo)d8 'skeosli o'lau (h)im'self to
'briiS. hi' woz on iks'triimli 'koijos maan, on(d) (h)iz 'neim woz 'dsoub
'skroginz. in'sted 9v 'rA$irj laik o 'fuil to So 'spot, 'hii, wiS 'aedmirobl9
'tsekt, 'held Ap (h)iz 'hsend tu in'dsoin 'sailons, on(d) 'traid wiS 'greit
'optikl 'enodsi to 'pios Si iks'triimli 1 'opozit. 2SAm. 8'haign'bai.
4d3os(t). 6in raepid spiitj, 'oilmost. 6 'gou Gru1. 7 ni9r im. s wud. 9
'sedmgrgbl. 33
The text on this page is estimated to be only 14.21%
accurate

A dctik 'gluim av Sa 'vo'lt. '5is (h)i' faund ta bi1

im'praektikabl. 'oil waz 'dctik, 'pitS 'daik, in 5a di'rekj(a)n from
'(h)witj Sa 'vois a'pia'd ta pra'siid1. 'nAGirj kad2 bi1 dis'tirjgwijt.
'twenti 'men mait3 (h)av bi'n 'drinkirj 'Ssa(r) Anpa'siivd. 'skroginz,
'Ssafoi(a), 'haevirj 'foimd (h)iz 'plaen av a'tsek, 'sed in a 'delikit4
'(h)wispa ta 8a 'kuipa : — "if 'jui stsend 'hia wif Jl 'naeb5 (5)am,"
an(d) 'krept 'veri 'stelGili 'raund 5i 'opazit6 'said av Si 'aitj. nau '5is
waz pri'saisli (h)wot 'vaelantain 'wontid. hi' 'wijt bAt7 tu ik'sait 5a
sas'pi$(9)n av 5a 'wotjman Sat 'pa:s(a)nz w(e)a 'haevirj a
klaen'dest(a)in 'triit, tu in'eibl (h)im ta 'kiip AP 5a 'geim. 'skroginz
(h)ad8, 'Ssafoi(a), nou 'suma got 'raund ban 'vaelantain 'sent a 'feint
'(h)wispa 'veri 'nia him9, 5a 'paipat ev '(h)witj waz10 5at 'hseri waz a
'full 'not ta 'get bi'haind fta 'kaisks. "ha'lou11!" 'Jautid 'skroginz, in a
'vois av '0Anda, on 'hiarirj 5a 'feint iks'prej(8)n av ftaet 'sentimant.
'''get bi'haind! 'get bi'haind !" kraid 'vaalantain, uwif Si bi- 'koit."
"ha'lou11!" a'ge(i)n 'Jautid 'skroginz wi5 'oil Si 'enadsi at (h)iz
ka'mamd. ''wot (a) ja12 a'baut '5sa 1 d ja 'hia 1 " US:!" sed
'v*lantain; " $• ! 'not a 'waid ! " '* 'ai 'hia ja, m(a)i 'rAm anz13! 'kAm
'aut a(v) '5a3t ! 'hia, 'dsounz." "ha'lou11!" 'Sautid 'd5ounz : "'wo(t) d
ja 'wont?" 1 pro'siid. 2 kud. 3 men 'mait. 4 'delikat. 'sleeq fo1 'kajtj.
6 'opozit. 7 bat. 8 'heed. 9 'nia(r) im. °'woz. l 'hA'lou, sAmtaimz
'holo(u), 'hselo(u). 12 a ju1. 8 ' anz = 'raisklz, 'd3oukaz. 34
The text on this page is estimated to be only 18.16%
accurate

* 'kAm '(h)io ! " kraid 'skroginz. ' 'hio, 'kwik ! — 'nAmbo

'nain ! — 'wii 1 'nseb jo, m(a)i 'Lvjintonz1 ! 'wi: 1 'faind jo 'aut ! " '
'nau 5(e)n," kraid 'dsounz, hir (h)od2 bi'n in'geidsd in 5o
foitifi'kei$(o)n'^ ov 'tu: 'paips ov 'port, " 'wot s 5o 'ran." ' '(h)io z a
'lot o 'feloz '(h)io," ri'plaid 'skroginz, '''swilin4 o'wei ot 5o 'wain laik
'dev(i)lz." r'wS9?" 'kraid 5o 'faiori'nouzd 'kuipo wi5 iks'tro:d(i)nori5
'fiosnis. ''hio!" 'Jautid skroginz. ''laits! 'laits ! " 'hio ! 'nain! 'laits!
'laits!" ri'itoreitid 'skroginz, hir o'piad to bi1 in o 'dredf(u)! 'steit ov
ik'saitmont 'd3Ast '5en. ' 'oil seif 'nau. 'lai 'stil," sed 'vaelantain,
'Grouirj (h)iz 'vois bi'haind o 'lot ov 'kwoita 'kaisks (h)witj 'stud on 5o
'left ov 'skroginz. "'a:! jo6 'seif i'nAf ! " iks'kleimd 'dsoub, in o 'toun
ov 'bito(r) 'aioroni. ' 'prei, 'dount o'laim jo 'blesid 'selvz ! jo6 'kwait
'seif to bi' 'nsebd in 'les 5(o)n 'nou 'taim. 'nau '5(e)n7, '5so, 'luk o'laiv
— 'nau, 'kwik!" (h)i' kon'tinju'd, oz 'tu: o'dij (o)n(o)l 'kuipoz o'proutSt
5o 'spot wiS 'laits. ' if jo 'get a'wei 'nau, m(a)i 'fain 'feloz, 'wai, 'mei
ai bi' 'bloud ! 'Sso, 'ju: 'gou bi'haind 'Sso, on 'ju: 'stsend 'hio, on 'jui
'kiip o 'Jaip luk- 'aut '5eo. 'nau '5(e)n, if 5ei is'keip, wi' 1 fo'giv
(5)om." 'hseviij 'steiS(9)nd 5o 'kuipoz wi5 'laemps in 5eo 'hsendz 1
'Ujintonz : fo'siijos fo1 'drinkoz. 2 hu1 d. 8 foitifi'keiS(o)n: ai5o
'stren9(o)nirj 5o 'kaisks, o'(r) 'sediij 'brsendi. 4 'swilin in 'staendod
pronAnsi'eiS(o)n. 5 ekstro'oid(i)nori. 6juf o. 7 5(e)n, on(d) 'similoli
6ruf'aut. 35
The text on this page is estimated to be only 19.82%
accurate

ot 'vsorios 'paits ov Si 'ait$, 'dsoub 'skroginz 'stoul 'dsentli

bi'twim tu: dis'tin(k)t rouz ov 'paips, on(d) 'vtelontain, 'wijirj to
'rendo(r) 'oil Si o'sist(o)ns in (h)iz 'pauo, prr'siidid (h)im. 'd5Ast,
hau'evo, oz (h)i' (h)(o)d 'riitjt So 'daikist 'pait ov Si 'a:t$, hi' 'kraid, in
on o'sjuimd 'vois, ov 'ko:(o)s, 'let s 'draun (h)im," on(d) '6ru: 5o
'glais ov 'wain (h)i' 'held in (h)iz 'hsend 'ouvo(r) iz1 'hed 'sou
'dekst(o)rosli, 5ot So 'houl ov it 'went 'into 5o 'feis ov 'misto
'skroginz, hir woz 'lukirj o'baut in o 'steit ov 8en(g)'zaioti 5o moust
in'tens. ' 'hio 8ei 'ai! 'hio(r) o 5o '6iivz ! " 'Jautid 'skroginz, 'waipirj
(h)iz 'wain-woSt 'feis wift 80 'sliiv ov (h)iz 'kout. "luk 'aut 5so ! — luk
'aut ! " on(d) (h)i- 'rA$t paist2 'vaelontain wi5 'greit indig'neiS(9)n
on(d) 'piod wiS kon'sid(o)robl 'fiosnis ov 'aespekt 'intu 'evri 'kseviti
'laids i'nAf tu o'dmit 5o 'teil ov o 'raet. " Si !" kraid 'vselontain,
'sendirj (h)iz 'vois 'rait o'hed: on(d) o'wei went 'skroginz to 5o 'spot
from '(h)witj 5o '(h)wispo(r) o'piod to pro'siid3, (h)wail 5o 'kuipoz
w(e)o 'lukiij o'baut wi5 'greit 'iigonis, iks'pektirj 'evri 'moumont to 'sii
5o 'Giivz 'raiz. ''kwaiot, 'hseri, 'kwaiot ! 5ei 1 'ksetj os4/' '(h)wispod
'vselontain. ' 'kaetj jo!" kraid 'skroginz, "to bi' '$uo5, wi1 'Jsel!" on(d)
(h)i' 'poukt (h)iz 'stik wi5 'infinit 'vaiolons6 bi'twim So 'kaisks, on(d)
'raetld it o'baut wi5 kon'sAmit despo'reiS(o)n, on(d) 'lukl! — oz So
'Isemp woz bi'niiG (h)iz 'wain-steind 'feis, it im'paitid sou 'ga:s(t)li o
'hju; to hiz7 'fiitjoz, Sot (h)i- 'rioli 'lukt laik8 o 'fimd. iz. 2rA$t'paist. 3
pro'siid. 4AS. '$00, 'Soi. 6 'vaiolons. 7 tu iz. 8 lukt 'laik. 36
The text on this page is estimated to be only 18.09%
accurate

''(h)a 'ha ha 'ha1 ! " kraid 'vselontain 'merili, 'sendirj (h)iz

'vois 'rait 'Ando Si 'ait$ o'dsoinin. o'wei went 'dsoub 'skroginz, 'bsekt
'AP bai So 'kuipoz, hu' 'strAk Sso 'Jinz 'klevoli o'ge(i)nst So 'komo
'kaisks, on(d) 'stAmbld 'ouvo So 'sksentlirj, 'WAR 'aifto Si 'ASo, wiS
'infinit 'prezons ov 'maind. " o'wei, o'wei ! " '$autid 'vselontain,
'6rouirj (h)iz 'vois to'woidz2 5o 'spot 5ei (h)(o)d 'dsAst 'left, on(d)
'dsoub 'skroginz 'rA^t bsek3 wi5 5o 'kuipoz ot (h)iz 'teil, ov 'huim 5o
'houl w(e)o(r) in'spaiod wi5 So 'spirit ov 'ven(d)3ons, :''stsend, 'Sso !
" 'Jautid 'skroginz; "Sei 'mAst pais4 'Sset 'wei ! " on(d) (h)if 'poukt
(h)iz '6ik 'stik bi'twim So 'kaisks o'gein 'desp(o)ritli, on(d) 'flAri$t it
o'baut wiS An'pseroleld5 'ziil. " it s 'oil 'AP wiS os6, 'hseri ; wi' o
'blokt 'rait in," '(h)wispod 'vselontain dis'peoriijli. " f o'giv os6 ! " hi'
'sedid, in o 'dif(o)ront 'vois, oz if 'hseri (h)(o)d 'rioli bi'kAm 'veri
'niAtS7 o'laimd — " f o'giv os6! wi' 1 'dui so(u) 'nou 'moi(o) ; 'hsev
'moisi!" "'moisi!" sed 'skroginz 'fo:v(o)ntli. "'moisi! jo 'dount (h)ov8 o
'skwiik9 ! 'kAm 'aut ! " hi' kon'tinjuid, "jo 'gAzliq 'vsegobounz10-—
'mo:si in'diid ! " " wi' v 'not drAnk11 o 'grei(t) diil12," sed 'vselontain
im'ploi(o)rinli. "wi' 'haev nt in'diid. ju' ^(Q)\ 'hsev it 'oil 'b*ek if ju'
'wil bot13 fo'giv os." 'skroginz 'smaild o sai'donik 'smail on(d) 'Jautid,
''nau 'S(e)n! 'ai14 jo 'kAmirj 'aut o' 'notl" 1 'ha 'ha 'ha 'ha, 'ho 'ho 'ho
'ho. 2 'toi(o)dz. 3rASt 'baek. 4 mos(t) 'pais. 5 An'pserolold. 6 AS. 7
mot$. 8 hsev. 9 'skwiik = bit. ° 'vsegobounz ; 'volgo fo'
'vsegobon(d)z^'vsegobon(d)z. " wi' 'haev nt 'drAnk. 12grei(t) 'dill,
'greit 'diil. 13 jo 'wil, ju- 1 'bAt, jo 1. 14 o. 37
The text on this page is estimated to be only 18.51%
accurate

'vaelontain sent 'foi9 o 'laif ov di'faions, (hjwitj 'koizd So

'hizvirj 'buz(o)m ov 'skroginz to 'swel wiS 'ro'9. di'faions (h)i' 'kud nt1
'staend. hi1 'flu: to So 'spot from '(h)wit$ So 'laif (h)od o'pjocaiit]^
pro'siidid2, on(d) 'strAk So so'raundirj 'kaisks wi53 pi'kjuilio(r) indigr
-ff \ nei)(Q)n. "'wil jo4 kAm 'aut, of 'not," hi1 iks'klcimd, "bi'foi(o)(r)
ai 'dui jo4 o 'mistSiH" '''nou," 'Jautid 'vaelontain. Son 'teik So
'konsikwonsiz," kraid 'skroginz, hu* 'lukt ot 5aet 'moumont
ri'maikobli 'fios. "'nau '5(e)n," hi' kon'tinjuid, o'dresirj So 'kuipoz,
"wi1 (o)l giv (5)om 'nou 'kwoito ; wif (o)l ov 'nou mo:(o)5 'paili ; wi'
(o)l 'draeg (5)om 'aut 'nau, 'nek (o)n 'hiilz ! " 'priiviosli6, hau'evo, to
5i i'fektjuol o'kompliSmont ov Sis 'loidobl 'obdsikt, it woz 'obviosli7
'nesis(o)ri8 to 'faind Som — o ri'maikobl 'faekt, (h)witj 'strAk
'skroginz on(d) So 'kuipoz wiS9 'sAtS 'foi(o)s, Sot Sei 'set to 'woik ot
'wAns, wiS So 'vjui ov i'fektiij Sis 'haili im'po:t(o)nt pri'liminori, on(d)
dis'pleid on o'maunt ov 'ziil (h)wit$ 'rioli 'did Som 'greit 'kredit. "5s
o10 'sAmwso(r) o'baut 'hio, ai 'nou," ob'zoivd So 'kuipo. u'ou, wi'
S(o)l 'faind (S)om! wi' S(o)l 'haev (S)om!" kraid 'skroginz; "'aend,
wen wi' 'dui 'kaetS (S)om 'Sei 1 'nou it!" So 'haili sai'ksestik 'toun in
(h)witj Siiz 'woidz w(s)o(r) 'Atod woz 'klioli in'dikotiv11 ov 'sAmGiij
'veri 'desp(o)rit; on(d) oz So 'kuipoz, hu' w(s)o bi'ginir) to get 'veri
'not. 2 pro'siidid. 3 wi9. 4ju'. 5 'hsev no 'moi(o). 6 'priivjosli. 7
'obvjoslL 8 'nesos(o)ri. 9wi9. 10 Sei o. n 'indikeitiv. 38
The text on this page is estimated to be only 13.95%
accurate

t, w(s)o 'rAnirj 'raund 8i 'ctit$, 'vselontain, Anpg'siivd, '0ru:

89 'glais (h)i' 'hsed in (h)iz 'hsend g'pon 89 'gluimi "aitj 'opozit1,
on(d) i'miidjotli 'kraid : " '8e9 z 9 'fuil! 'nau wif 'kamt get 9'nA8g
'drop." ' 'hig 8e(i) 'a: ! " '$autid 'skroginz, on 'hiorirj 5o 'kra3$. ' 'nau
'5(e)n, 'boiz ! hu'rai ! wi' $(9)! 'neil2 (8)9111." 5is 'soul-'stoirir| 'spiitS
'put 89 'kuipgz on 8s9 'metl, 9n(d) 5ei ArA$t tg'woidz3 5i 'ait$ wi5
ri'njuid 'spirit ; bot 'dsAst bi'foKo) 5ei 'riitjt 89 'spot in '(h)witj 5o
'broukn 'glais W9z 'lai(i)ij, 'vselgntain 'kraid, !''nau, 'let s 'start; wi'
k(o)n 'get 'nou moi(9)4 r «55 wain. '* 'stop '5s9, jg 'vaeggbounz5 ! "
kraid 'skroginz 'vi:(h)9m9iitli6, 'Ginkiij t9 'fraitn 5gm 'aut 9v 5s9 'wits.
uwif 9 'kok'Ju97 t9 'ksetj jg, jg 'nou! J9 mg8 'dsAst 9z 'wel giv 'AP 9t
'wAns ! " hi' (h)gd 'nau 'riitjt 89 'spot in (h)witj 89 'glais lei 'smaejt
'intu 9 'nAmb9(r) 9V 'litl 'piisiz, 'krai(i)rj 'aut, "'hig z ws9 89
'vseggbounz5 'w£99." 'stuip 'daun," '(h)wisp9d 'vsebntain. ' 'kAm
'aut ! " kraid 'skroginz. " (i)t s 'nou 'juis, jo 'nou; wi'10 'sii J9 ! " 911
obz9'veiS(9)n '(h)witS, hau'evg 'loidobl so(u)'ev9(r) its 'obdsikt 'mait
(h)9v bi'n, in'volvd 9 'haili repri'hensibl11 'fo'ls(h)ud. '' 'nau '8(e)n !
— 'kroil 'dsentli," '(h)wisp9d 'vselgntain. " r-\ r )) kAm on. 'skroginz
'liipt12 'ouvo 89 'paips in 9n 'inst(g)nt, 9n(d) lukt 'raund 9n 'raund
wi8 9n iks'prej(9)n 9V sg'praiz. 1 'opozit. 2 'neil = si'kjug, 'ksetj. 3
'toidz. 4 no 'mo: (9). 6 'vseggbounz : 'vAlgg fo' 'vyeg9bon(d)z,
'v8eg9bon(d)z. 5 'vii(h)im9ntli. 1 'kok'Joo, -'Joa, -Joi. 8 me(i). 9'w9i.
} 'wi:. " repri'hensobl. 2 'lept. 39
The text on this page is estimated to be only 19.91%
accurate

"('hse)v jo 'got (Sjom1?" in'kwaiod1 So 'faiori-'nouzd 'kuipo.

"'got (S)om!" 'eko(u)d 'skroginz, "ai 'ounli 'dsAst 'wi$ ai 'haed — fo
'Seo 'seiks. ai d is'tseblij 9 'traifl o2 'tui in S(e)o 'mem(0)riz to 'soiv
(S)om fo 'laif. ai3 1 'woront Sei 'wudnt4 fo'get it o 'lorj wail."
'vselontain 'nau 'sent o 'slait 'laif sou 'veri 'nio So 'legz ov 'misto
'skroginz, Sot 'Saet 'dsentlmon 'spAn 'raund wiS So vi'lositi ov o
'koktjeifo, on(d) 'felt 'veri 'serjgri in'diid wiS (h)im'self5 (h)wen (h)i
ri'flektid Sot So ' 'USirjtonz ' 'stil w(s)o(r) ot 'laids. " weo 'keen6 Sei
ov 'krept 'tu1?" hi' 'kraid in o'meizmont. U5s o 'not7 o 'jaid 'from mif,
on(d) 'jet — 'wai, 'weo So — "S(s)o z 'nou 'ru'm fo 'tui men to 'haid
Seo 'bodiz 'hio," ob'zoivd So 'faiori-'nouzd 'kuipo. •" Sei 'mAs(t) bi'8
po'tikjololi 'sektiv," sed 'skroginz; on(d) 'vaBlontain 'sent o'nASo 'laif
'veri 'nio him9. 'dsoub 'skroginz 'lukt 'saevids — An'dautidli 'saevids.
hi1 'Juk (h)iz 'red 'hed wiS iks'triim despo'reiS(s)n on(d) 'graund (h)iz
'ti:9 wiS mo'naiok(o)! 'ziil. " wso 'kaan10 Sei bi' 'hid11?" hi1
iks'kleimd wiS 'greit 'emfosis. ' 'blisto(r) om12! wso 'ksen10 So
'skaundrolz 13 bi1 'got tu?" hi' 'fikst (h)iz 'aiz o'pon (h)iz
kom'psenjonz, on(d) (h)iz kom'paenjonz 'fikst 'Sso(r) aiz o'pon 'him,
(h)wail 'broidsaidz 'skraatjt (h)iz 'hed wiS (h)iz14 'rait 'hsend, on(d)
'rAbd (h)iz 'tjin 'veri mis'tioriosli wiS (h)iz14 'left. ot Sis 'moumont on
in'telidsont 'kuipo, huf (h)(o)d 1 in'kwaiod. 6 'weo k(o)n. 3 'weo
k(o)n. 13 'skaundrilz. 2o'.^ 3'ai. ^ 7 Sei 'aint. "hid; fo' 14wi6 hiz. ( 4
d 'not. !mos(t) 'bii. 'hidn. 5 wi6 him'self. 9 /- • / \ • movrj im. 2
'blisto Som. 40
The text on this page is estimated to be only 13.31%
accurate

iCa) 'saitjt wi'Saut rAt(0)riij 9 'silabl, 'ventjad tu 'afa(r) 9

'neS(9)n(a)l se'dsestKaJn, 5a 'paipat 9V (h)witS 'waz 5at 5ei 'saitnli
w(s)o 'sAm(h)wsa. 'sAmwsa ! " kraid 'skragim, 'veri 'sengrili ; " wif
'nou 5ei 'mAst bi' 'sAmwea ; bat1 'wea(r) 'iz 'sAmwsa? 'Sset s 89
'paint2." 5i in'telidsgnt 'kuipg, hu- 'ofgd 5is s9'dsestS(9)n, W9Z
'saibnt, fg hi'3 'soi Sat 'mistg 'skroginz 'lukt 'redi tu 'i:t (h)im. 'saibns
W9z4, '5s9fo:(9), 9 'spii^iz 9V 'wizdgm, (h)witj 89 'litl iiTtelidsgnt
'kuipg dis'pleid, 9n(d) 89 'soit$ waz ri'zjuimd wiS in'kriist5
paisi'vi9r9ns. bat 'vaelgntain (h)im'self 'nan bi'keim 'sAm(h)wot
'pAzld. hi1 'sksali, 'nju: 'hau t9 pra'siid6. hi1 W9z 'aer)(k)S9s t9 send
5i m'vizibl ''lA^igtanz' a'wei wiS 'eikla:7, bat 89 'kwest$(9)n 'waz,
'hau k9d (h)i1 'get 59m 9'wei? -* -"- * -"- 9t 'laist (h)i' '6o:t av
intra'djuisir)8 (h)iz 'vais 'inta 'WAII av 5a 'paips av 'wain in 'aida ta
'sii hau 'dsoub 'skraginz an(d) (h)iz kam'psenjanz (w)ad9 'sekt ;
'send, 'd3Ast az 5i ena'dsetik 'd5oub, 'aifta 'fiasli 'rAnirj 'raund an
'raund, (h)ad 'paizd ta ri'gein a 'litl 'bre9, an ta 'waip (5a
pa:spi'reij(a)n fram (h)iz 'feis wi5 5a 'kAf av (h)iz 'kout, hi1 'pitjt
(h)iz 'vais 'intu an iks'triimli 'ould 'kaisk, an(d) 'kraid, "'waz nt it 'Uki
wi1 'faund '5is WAn 'em(p)ti, 'eiT' 'd3oub 'skraginz 'stead ; an(d) 'sou
did 'mista 'braidsaidz, an(d) 'sou did 5a 'kuipa ; an(d) 5ei 'drui 'nia
Sa 'kaisk fram '(h)witj Sa 'saund (h)ad a'pearantli pra'siidid10, an(d)
'lisnd a'ge(i)n wi5 an iks'preS(9)n av 9'meizmant. 1 'bAt. 2 'paint ;
'vAlga fa' 'paint. 3 fa' hi1, fg(r) i. 4 waz. 5 iij'kriist. 6pro'siid.
7e'kla(:). s introdjuisiij. 9 wud. 10 pro'siidid. 41
The text on this page is estimated to be only 13.56%
accurate

' 'kiip 'in 5o 'hed," '(h)wispod 'vsetantain, 'veri 'oidibli1. " 5s

92 'hig ! " 'Jautid 'skroginz, 'snset$ir| on 'sedz from 89 'faiori-nouzd
'ku:p9. "luk 'aut! — 'nau 5s 92 'neild!" 9n(d) wi'5aut 9 'sirjgl
'moumgnts ri'flek$(9)n, wi'5aut k9n'sid(9)rir) '(h)we59 89 'kaisk
w(s)g 'ful o'(r) 'em(p)ti, wi'Saut 'iivn 'givirj 69 'slaitist 'noutis t9 '5ouz
(h)u' w(s)9 "wi5 (h)im3, hi' 'smse^t 'in 89 'hed 9V 89 'paip, 9n(d) 89
'wain, 9v 'koi(9)s, 'rA$t 'aut in 'torgnts. " 'jui 'fuil ! " 'kraid 89 'faigri-
nouzd 'kuipg, 9z 69 'striim 'dseSt 89 'lasmps from 5e9 'haendz, 9n(d)
iks'tingwijt 89 'laits. " 'help ! 'help ! " 'Sautid 'skroginz. "'sailans, ju*
'ses ! 'hould J9 'tArj ! " 'kraid Si in'reidsd 'kuip9. ' 'hoist 89 'kaisk 'AP
on 'end ! 'nau ! 'nau ! 'oil to'gefo ! hu'ra: ! " in 9n 'inst(g)nt 89 'Girj
W9z o'kompliSt, fo4 'vaelontain, hu? W9z 'rigli 'veri 'sori f94 '(h)wot
(h)od 'haepnd, put 'foiG wi5 89 'rest 'oil 5o 'strenG 9t (h)iz kg'mamd.
[89 'dsemids woz 'meid 'gud 9z 'fai(r) oz 'posibl, 9n(d) 'vaebntain
9n(d) (h)iz 'frend 'left 59 'vo'lts 'aifto 'tipirj 59 'kuipgz 'h8en(d)s9mli.]
9'dgepted wi5 'veri 'slait modifi'keiS(8)nz ond 9 'fjui 9'mi$(a)nz5
from "5o 'laif 9n(d) 9d'vent$9z 9V 'vaebntain 'voks," bai 'henri
'kokton. 1 'oidobli. 2 5e(i) 9. 3 'wi9 him. 4 fo-. 42
Welcome to our website – the ideal destination for book lovers and
knowledge seekers. With a mission to inspire endlessly, we offer a
vast collection of books, ranging from classic literary works to
specialized publications, self-development books, and children's
literature. Each book is a new journey of discovery, expanding
knowledge and enriching the soul of the reade

Our website is not just a platform for buying books, but a bridge
connecting readers to the timeless values of culture and wisdom. With
an elegant, user-friendly interface and an intelligent search system,
we are committed to providing a quick and convenient shopping
experience. Additionally, our special promotions and home delivery
services ensure that you save time and fully enjoy the joy of reading.

Let us accompany you on the journey of exploring knowledge and

personal growth!

ebookluna.com