(Original PDF) Australasian Business

Statistics, 4th Edition

Go to download the full and correct content document:
https://ebooksecure.com/product/original-pdf-australasian-business-statistics-4th-editi
on/
More products digital (pdf, epub, mobi) instant
download maybe you interests ...

(eBook PDF) Lifespan Development 4th Australasian

Edition

http://ebooksecure.com/product/ebook-pdf-lifespan-
development-4th-australasian-edition/

(eBook PDF) Business Statistics 4th Edition by Norean

D. Sharpe

http://ebooksecure.com/product/ebook-pdf-business-statistics-4th-
edition-by-norean-d-sharpe/

(eBook PDF) Modern Business Statistics, with Microsoft

Office Excel 4th Edition

http://ebooksecure.com/product/ebook-pdf-modern-business-
statistics-with-microsoft-office-excel-4th-edition/

(eBook PDF) The Practice of Statistics for Business and

Economics 4th

http://ebooksecure.com/product/ebook-pdf-the-practice-of-
statistics-for-business-and-economics-4th/
Business Statistics: Communicating with Numbers, 4e 4th
Edition Sanjiv Jaggia - eBook PDF

https://ebooksecure.com/download/business-statistics-
communicating-with-numbers-4e-ebook-pdf/

(eBook PDF) Management across Cultures - Australasian

Edition

http://ebooksecure.com/product/ebook-pdf-management-across-
cultures-australasian-edition/

(eBook PDF) Macroeconomics Australasian Edition by

Blanchard

http://ebooksecure.com/product/ebook-pdf-macroeconomics-
australasian-edition-by-blanchard/

(eBook PDF) Accounting Information Systems Australasian

edition

http://ebooksecure.com/product/ebook-pdf-accounting-information-
systems-australasian-edition/

(eBook PDF) Discovering Statistics Using IBM SPSS

Statistics 4th

http://ebooksecure.com/product/ebook-pdf-discovering-statistics-
using-ibm-spss-statistics-4th/
 AUSTRALASIAN
BUSINESS STATISTICS
4TH EDITION

BLACK | ASAFU-ADJAYE | BURKE | KHAN | KING

PERERA | PAPADIMOS | SHERWOOD | WASIMI
Fourth edition published 2016 by
John Wiley & Sons Australia, Ltd
42 McDougall Street, Milton Qld 4064
First edition published 2007
Second edition published 2010
Third edition published 2013
Typeset in Minion Pro 10/12
Australian editions © John Wiley & Sons Australia, Ltd 2007, 2010, 2013,
2016
Authorised adaptation of Business statistics for contemporary decision
making, 4th edition (ISBN 0-471-42983-X), published by John Wiley &
Sons, Inc., Hoboken, United States of America under exclusive licence
from Leyh Publishing, LLC. Copyright © 2004 in the USA by Leyh
Publishing, LLC. All rights reserved.
The moral rights of the authors have been asserted.
National Library of Australia
Cataloguing-in-Publication entry

Creator: Black, Ken (Kenneth Urban), author.

Title: Australasian business statistics / Ken Black, John Asafu-
Adjaye, Paul Burke, Nazim Khan, Gerard King, Nelson
Perera, Andrew Papadimos, Carl Sherwood, Saleh Wasimi.
Edition: 4th edition.
ISBN: 9780730312932 (paperback)
9780730324836 (e-text)
Notes: Includes index.
Subjects: Commercial statistics — Australasia — Textbooks.
Other Creators/
Contributors: Asafu-Adjaye, John, author.
Burke, Paul, author.
Khan, Nazim, author.
King, Gerard, author.
Perera, Nelson, author.
Papadimos, Andrew, author.
Sherwood, Carl, author.
Wasimi, Saleh A. (Saleh Ahmed), author.
Dewey Number: 519.5

Reproduction and Communication for educational purposes

The Australian Copyright Act 1968 (the Act) allows a maximum of 10% of
the pages of this work or — where this book is divided into chapters — one
chapter, whichever is the greater, to be reproduced and/or communicated
by any educational institution for its educational purposes provided that
the educational institution (or the body that administers it) has given a
remuneration notice to Copyright Agency Limited (CAL).
Reproduction and Communication for other purposes
Except as permitted under the Act (for example, a fair dealing for
the purposes of study, research, criticism or review), no part of this
book may be reproduced, stored in a retrieval system, communicated
or transmitted in any form or by any means without prior written
permission. All inquiries should be made to the publisher.
Cover and internal design images: © Daniel Fung / Shutterstock.com (top);
Hypervision Creative / Shutterstock (bottom)
Typeset in India by Aptara
Printed in China by
Printplus Ltd
10 9 8 7 6 5 4 3 2 1
 CHAPTER 1 Introduction to statistics 1

CHAPTER 2 Charts and graphs 13

CHAPTER 3 Descriptive summary measures 47

CHAPTER 4 Probability 93
Brief contents

CHAPTER 5 Discrete distributions 135

CHAPTER 6 The normal distribution and other continuous distributions 169

CHAPTER 7 Sampling and sampling distributions 193

CHAPTER 8 Statistical inference: estimation for single populations 227

CHAPTER 9 Statistical inference: hypothesis testing for single populations 261

CHAPTER 10 Statistical inferences about two populations 311

CHAPTER 11 Analysis of variance and design of experiments 367

CHAPTER 12 Chi-square tests 409

CHAPTER 13 Simple regression analysis 435

CHAPTER 14 Multiple regression analysis 479

CHAPTER 15 Time-series forecasting and index numbers 513

Brief contents v
 About the authors xi Summary 42
Key features xiii Key terms 43
Real-world issues at a glance xiv Review problems 43
Acknowledgements xv
CHAPTER 3
CHAPTER 1
Descriptive summary measures
Introduction to statistics
Learning objectives 47
Learning objectives 1 Opening vignette: Are you being followed? 48
Opening vignette: The search for information 2 Introduction 48
Introduction 2 Chapter case: Location, location, location! 49
1.1 Basic statistical concepts 3
Contents

3.1 Measures of central tendency 51

1.2 Types of data 4 Mode 51
Categorical data 4 Median 51
Numerical data 5 Mean 53
Cross-sectional and time-series data 5 3.2 Measures of location 56
1.3 Obtaining data 6 Percentiles 57
Obtaining secondary data 6 Quartiles 58
Obtaining primary data 6 3.3 Measures of variability 61
1.4 Statistical analysis using Excel 7 Range 61
Getting started with Excel and KaddStat 7 Interquartile range 61
Excel’s Analysis ToolPak add-in 7 Variance and standard deviation 62
KaddStat 8 Variance 63
Using Excel with this book 9 Standard deviation 64
1.5 When things go wrong 9 Population versus sample variance and
Space shuttle Challenger 9 standard deviation 68
The Sally Clark case 9 Computational formulas for variance and
The 1936 US presidential election 10 standard deviation 69
Summary 10 z-scores 71
Key terms 11 Coefficient of variation 72
Review problems 11 3.4 Measures of shape 74
Skewness 74
CHAPTER 2 Skewness and the relationship of the mean,
median and mode 75
Charts and graphs Coefficient of skewness 75
Kurtosis 76
Learning objectives 13 Box and whisker plots 76
Opening vignette: Red tape 14 3.5 Measures of association 80
Introduction 14 Correlation 80
Chapter case: Electronic games 15 Misuse of statistics 85
2.1 Frequency distributions 16 Chapter case revisited: Location, location, location! 85
Class midpoint 17 Summary 86
Relative frequency 17 Key terms 87
Cumulative frequency 17 Key equations 88
2.2 Graphical display of data 22 Review problems 89
Histograms 22 Maths appendix 91
Frequency polygons 28
Ogives 30 CHAPTER 4
Pie charts 32
Stem and leaf plots 33 Probability
Pareto charts 35
2.3 Graphical display of two-variable Learning objectives 93
continuous data: scatter plots 39 Opening vignette: A conditional workout 94
Chapter case revisited: Electronic games 41 Introduction 95

vi Contents
Chapter case: Too many leaders 96 Using the binomial table 147
4.1 Methods of determining probabilities 97 Mean and standard deviation of a binomial distribution 150
Classical method 97 Graphing binomial distributions 152
Relative frequency of occurrence method 98 5.4 Poisson distribution 155
Subjective probability method 99 Solving Poisson problems by formula 156
4.2 Structure of probability 100 Mean and standard deviation of a Poisson distribution 160
Experiment 100 Graphing Poisson distributions 160
Event 100 Poisson approximation of the binomial distribution 161
Elementary events 100 Misuse of statistics 164
Sample space 101 Chapter case revisited: Mental health and young people 165
Set notation, unions and intersections 102 Summary 166
Mutually exclusive events 103 Key terms 166
Independent events 103 Key equations 166
Collectively exhaustive events 104 Review problems 167
Complementary events 104
4.3 Contingency tables and probability matrices 105
Marginal, union, joint and conditional probabilities 106 CHAPTER 6
Probability matrices 107
4.4 Addition laws 109 The normal distribution and other continuous
General law of addition 109 distributions
Exclusive or 112
Complement of a union 113 Learning objectives 169
Special law of addition 114 Opening vignette: Healthy body temperature 170
4.5 Multiplication laws 116 Introduction 170
General law of multiplication 116 Chapter case: Prawn farm continues to grow 171
Special law of multiplication 117 6.1 The normal distribution 172
4.6 Conditional probability 120 History and characteristics of the
Assessing independence 122 normal distribution 172
Tree diagrams 124 6.2 The standardised normal distribution 175
Revising probabilities and Bayes’ rule 126 6.3 Solving normal distribution problems 177
Misuse of statistics 129 Misuse of statistics 181
Chapter case revisited: Too many leaders 129 6.4 The normal distribution approximation to the
Summary 130 binomial distribution 181
Key terms 131 6.5 The uniform distribution 184
Key equations 131 6.6 The exponential distribution 186
Review problems 132 Probabilities for the exponential distribution 187
Chapter case revisited: Prawn farm continues to grow 189
CHAPTER 5 Summary 190
Key terms 190
Discrete distributions Key equations 190
Review problems 191
Learning objectives 135
Opening vignette: Binge drinking 136
Introduction 136 CHAPTER 7
Chapter case: Mental health and young people 137
5.1 Discrete versus continuous distributions 137 Sampling and sampling distributions
5.2 Describing a discrete distribution 138
Mean, variance and standard deviation of discrete Learning objectives 193
distributions 139 Opening vignette: Detecting accounting fraud 194
Mean or expected value 140 Introduction 194
Variance and standard deviation of a discrete Chapter case: Prawn farm success tied to strict quality control 195
distribution 140 7.1 Sampling 196
5.3 Binomial distribution 143 Reasons for sampling 196
Assumptions about the binomial distribution 143 Reasons for taking a census 197
Solving a binomial problem 144 Sampling frame 197

Contents vii
7.2 Random versus nonrandom sampling 198 Misuse of statistics 256
Random sampling techniques 198 Chapter case revisited: Prawn farm up for sale 256
Simple random sampling 198 Summary 257
Stratified random sampling 201 Key terms 258
Systematic sampling 202 Key equations 258
Cluster (or area) sampling 203 Review problems 259
Nonrandom sampling 204
Convenience sampling 204
Judgement sampling 204 CHAPTER 9
Quota sampling 205
Snowball sampling 205 Statistical inference: hypothesis testing for
7.3 Types of errors from collecting sample data 205 single populations
Sampling error 205
Nonsampling errors 206 Learning objectives 261
7.4 Sampling distribution of the sample mean, x 207
Opening vignette: Australian childcare — enough to
make you cry? 262
Central limit theorem 211
Introduction 262
Sampling from a finite population 215
Chapter case: Prawn farm expects a bright future 263
7.5 Sampling distribution of the sample
9.1 Hypothesis-testing fundamentals 263
proportion, p̂ p 218
Misuse of statistics 220 Rejection and nonrejection regions 266
Chapter case revisited: Prawn farm success tied to strict quality Type I and Type II errors 269
control 221 Type I error 269
Summary 222 Type II error 270
Key terms 223 How are alpha and beta related? 271
Key equations 223 9.2 The six-step approach to hypothesis testing 272
Review problems 224 step 1. Set up H0 and Ha 272

step 2. Decide on the type and direction of the test 273

step 3. Decide on the level of significance (α ), determine

CHAPTER 8 the critical value(s) and region(s), and draw a
diagram 273
Statistical inference: estimation for single step 4. Write down the decision rule 273

populations step 5. Select a random sample and do relevant

calculations 273
Learning objectives 227 step 6. Draw a conclusion 273

Opening vignette: Rural obesity in Queensland on the rise 228 Misuse of statistics 273
Introduction 228 9.3 Hypothesis tests for a population mean: large
Chapter case: Prawn farm up for sale 228 sample case (z statistic, σ known) 274
8.1 Estimating the population mean using the step 1. Set up H0 and Ha 274

z statistic (σ known) 229 step 2. Decide on the type and direction of the test 275

Finite population correction factor 235 step 3. Decide on the level of significance (α ), determine the

Estimating the population mean using the z statistic when critical value(s) and region(s), and draw a diagram 275
the sample size is small 236 step 4. Write down the decision rule 275

8.2 Estimating the population mean using the step 5. Select a random sample and do relevant
t statistic (σ unknown) 238 calculations 275
The t distribution 238 step 6. Draw a conclusion 275

Robustness 239 Testing the mean with a finite population 276

Characteristics of the t distribution 239
Reading the t distribution table 240
Confidence intervals to estimate the population mean using
the t statistic 241
8.3 Estimating the population proportion 245
8.4 Estimating the population variance 248
8.5 Estimating sample size 252
Sample size when estimating µ 252
Determining sample size when estimating p 254
The critical value method 276
The p-value method 278
9.4 Hypothesis tests about a population mean: small
sample case (t statistic, σ unknown) 282
9.5 Testing hypotheses about a proportion 288
9.6 Testing hypotheses about a variance 292
9.7 Solving for Type II errors 296
Some observations about Type II errors 301
Operating characteristic and power curves 301

viii Contents
 Effect of increasing sample size on the Chapter case: Cyberbullying amongst Australian
rejection limits 302 adolescents 369
Chapter case revisited: Prawn farm expects a bright 11.1 Introduction to design of experiments 370
future 304 11.2 The completely randomised design (one-way
Summary 306 ANOVA) 372
Key terms 307 Reading the F distribution table 376
Key equations 307 11.3 Multiple comparison tests 380
Review problems 308 Tukey’s honestly significant difference (HSD) test: the case
of equal sample sizes 380
Tukey–Kramer procedure: the case of unequal
CHAPTER 10
sample sizes 383
11.4 The randomised block design 385
Statistical inferences about two populations
11.5 A factorial design (two-way ANOVA) 390

Learning objectives 311 Advantages of the factorial design 391

Opening vignette: Saving for retirement 312 Factorial designs with two treatments 391
Introduction 313 Statistically testing a factorial design 392
Chapter case: Life insurance premiums 314 Interaction 392
10.1 Hypothesis testing and confidence intervals for Misuse of statistics 400
the difference between two means (z statistic, Chapter case revisited: Cyberbullying amongst Australian
population variances known) 315 adolescents 401
Hypothesis testing 316 Summary 401
Confidence intervals 322 Key terms 402
10.2 Hypothesis testing and confidence intervals for Key equations 402
the difference between two means (t statistic, Review problems 403
population variances unknown) 326 Maths appendix 406
Hypothesis testing 326
Confidence intervals 333
CHAPTER 12
10.3 Statistical inferences about two populations with
paired observations 337
Hypothesis testing 337
Chi-square tests
Confidence intervals 343
Learning objectives 409
10.4 Statistical inferences about two population
Opening vignette: Social media is now crucial for business 410
proportions 347
Introduction 410
Hypothesis testing 347
Chapter case: Job security at Combaro Ltd 411
Confidence intervals 351
12.1 Chi-square goodness-of-fit test 412
10.5 Statistical inferences about two population
12.2 Contingency analysis: chi-square test of
variances 353
independence 423
Hypothesis testing 354
Misuse of statistics 428
Confidence intervals 359
Chapter case revisited: Job security at Combaro Ltd 429
Misuse of statistics 361
Summary 430
Chapter case revisited: Life insurance 361
Key terms 431
Summary 362
Key equations 431
Key terms 362
Review problems 431
Key equations 362
Review problems 364
Maths appendix 366 CHAPTER 13

CHAPTER 11 Simple regression analysis

Analysis of variance and design of experiments Learning objectives 435
Opening vignette: Teenage smoking in pregnancy
Learning objectives 367 and birth weight 436
Opening vignette: Australian teens and luxury Introduction 436
brands 368 Chapter case: Predicting the selling price of houses in the
Introduction 368 city of Baycoast 437

Contents ix
13.1 Introduction to simple regression analysis 437 Summary 507
13.2 Determining the equation of the regression Key terms 507
line 440 Key equations 508
13.3 Residual analysis 449 Review problems 508
Using residuals to test the assumptions of the regression
model 452
CHAPTER 15
13.4 Standard error of the estimate 455
13.5 Coefficient of determination 459
Time-series forecasting and index numbers
Relationship between r and r  2 462
13.6 Hypothesis tests for the slope of the regression Learning objectives 513
model and testing the overall model 462
Opening vignette: The power of tourism 514
Testing the slope 462
Introduction 515
13.7 Estimation and prediction 466
Chapter case: Forecasting at Combaro Ltd 516
Confidence (prediction) intervals to estimate the conditional
15.1 Components of a time series 518
mean of y : µy/x 466
Trend component 518
Prediction intervals to estimate a single value of y 467 Seasonal component 518
13.8 Interpreting the output 472 Cyclical component 519
Misuse of statistics 472 Irregular (or random) component 519
Chapter case revisited: Predicting the selling price of houses 15.2 Time-series smoothing methods 520
in the city of Baycoast 472
The moving average method 520
Summary 473
The exponential smoothing method 523
Key terms 474
Seasonal indices 525
Key equations 475
Deseasonalising time series 528
Review problems 476
15.3 Least squares trend-based forecasting
models 532
CHAPTER 14 The linear trend model 532
The quadratic trend model 535
Multiple regression analysis The exponential trend model 537
15.4 Autoregressive trend-based forecasting
Learning objectives 479 models 539
Opening vignette: Video gaming and gambling in Testing for autocorrelation 540
Australian adolescents 480 Ways to overcome the autocorrelation
Introduction 480 problem 543
Chapter case: Predicting the prices of houses in Baycoast: Addition of independent variables 543
using additional variables 481 Transforming variables 543
14.1 The multiple regression model 481 15.5 Evaluating alternative forecasting models 547
Multiple regression model with two independent variables 15.6 Index numbers 550
(first-order) 482
Simple price index 550
Determining the multiple regression equation 483
Aggregate price indices 551
14.2 Significance tests of the regression model and its
Unweighted aggregate price index 551
coefficients 488
Weighted aggregate price index 552
Testing the overall model 488
Changing the base period 556
Significance tests of the regression coefficients 490
Applications of price indices 557
14.3 Residuals, standard error of the
estimate and R 2 493 Misuse of statistics 559
Residuals 493 Chapter case revisited: Forecasting at Combaro Ltd 559
SSE and standard error of the estimate 497 Summary 562
Coefficient of multiple determination (R2) 499 Key terms 563
Adjusted R2 500 Key equations 563
14.4 Interpreting multiple regression Review problems 564
computer output 501
A re-examination of the multiple regression output 501 Appendix: Tables 569
Misuse of statistics 504 Sources 605
Chapter case revisited: Predicting the selling price of houses in the Glossary 609
city of Baycoast: using additional variables 505 Index 615

x Contents
 Ken Black is Professor of Decision Sciences in the School of Business and Public Administration
at the University of Houston–Clear Lake. He earned a Bachelor of Arts in mathematics from
Graceland College; a Master of Arts in mathematics education from the University of Texas at El
Paso; a Doctor of Philosophy in business administration in management science; and a Doctor of
Philosophy in educational research from the University of North Texas.
About the authors
Ken has taught all levels of statistics courses: forecasting, management science, market research
and production/operations management. He has published 20 journal articles, over 20 professional
papers and two textbooks: Business statistics: an introductory course and Business statistics: for con-
temporary decision making. Ken has consulted for many different companies, including Aetna,
the City of Houston, NYLCare, AT&T, Johnson Space Centre, Southwest Information Resources,
Connect Corporation and Eagle Engineering.
John Asafu-Adjaye is an Associate Professor in the School of Economics at the University of
Queensland (UQ). He obtained a Bachelor of Science (Honours) in agricultural economics from
the University of Ghana and then earned a Master of Science in operations research from the Aston
Business School, UK. He completed a Doctor of Philosophy in natural resource economics at the
University of Alberta, Edmonton, Canada.
At UQ John teaches business and economic statistics at both the undergraduate and post-
graduate levels. His research activities include policy analysis of economic and environmental
issues in Africa and the Asia–Pacific region. John is the author or co-author of over 80 research-
based publications, including 7 books and monographs, 5 book chapters, 63 peer-reviewed journal
articles and 11 commissioned reports.
Paul Burke is a Research Fellow in the School of Marketing and Centre for the Study of Choice
(CenSoC) at the University of Technology Sydney (UTS). He obtained a Bachelor of Economics
(First Class Honours in Marketing) from the University of Sydney. He holds a Doctor of Phil­
osophy and Graduate Certificate in Higher Education Teaching & Learning from UTS. Paul has
won teaching awards for his work in business statistics and large class teaching from UTS as well as
national recognition with citations from the Carrick Institute and the Australian Learning Teaching
Council. He has published in many international journals including Research Policy, Educational
Researcher, International Journal of Research in Marketing, Journal of Operations Management and
Journal of Product Innovation Management. His research interests are in choice modelling, experi-
mental design and consumer behaviour applied in the fields of education, ethical consumerism
and innovation. He has been chief investigator on many large-scale grants including Discovery and
Linkage grants from the Australian Research Council (ARC), working with many international
companies and organisations.
Nazim Khan is a Lecturer and Consultant in the School of Mathematics and Statistics at the
University of Western Australia. He earned a Bachelor of Engineering in electrical engineering
from the University of Western Australia, a Technical Teachers Certificate from the Fiji Institute of
Teaching, and a Bachelor of Science (Honours) in mathematics and a Doctor of Philosophy from
the University of Western Australia.
Nazim has taught decision theory at the MBA level, financial mathematics, forecasting and stat-
istics. Nazim is an active researcher in statistics and applications. He has also presented several
papers and published several articles in mathematics and statistics education. Nazim has consulted
for various companies and research groups in his capacity as Consultant with the UWA Statistical
Consulting Group.
Andrew Papadimos is a Lecturer in international business, statistics and economics on the
Brisbane campus of Australian Catholic University. His main research interests are the Chinese
economy and International Business in the Asia–Pacific region. Apart from a PhD in Interna-
tional Relations and Economics, Andrew also has a Masters in Applied Law from the University

About the authors xi

 of Queensland, and a Graduate Certificate in Higher Education from ACU. Andrew has lived and
worked for many years in Taiwan and the People’s Republic of China, and is fluent in speaking and
reading Mandarin Chinese. He has also had a great deal of real-world experience with international
business, having acted as a consultant on the Chinese economic and legal climate for international
corporations conducting business with China.
Carl Sherwood is a Lecturer in the School of Economics at the University of Queensland. He
obtained a Bachelor of Engineering (Civil), Master of Business Administration (MBA) and a Grad-
uate Certificate in Higher Education from the University of Queensland. With twenty years of
professional experience as an engineer, Carl has crafted his teaching by capturing this wealth of
business experience to make courses relevant to students.
Carl has been teaching a variety of subjects at the University of Queensland for more than a
decade. He has primarily concentrated on teaching statistics, at both the undergraduate and post-
graduate level, as well as teaching business economics to managers studying at MBA level. As a
result of his teaching efforts, Carl has won the University of Queensland School of Economics
Teaching Excellence Award on four occasions, a University of Queensland Citation for Outstanding
Contributions to Student Learning and a National Teaching Citation for Outstanding Contribu-
tions to Student Learning. One of Carl’s areas of research centres on exploring how statistics can be
made more meaningful, practical and engaging for students.
Saleh A Wasimi is an Associate Professor at Central Queensland University, Melbourne,
Australia. He earned his Doctor of Philosophy degree from the University of Iowa, US, and his
Masters and Bachelor degrees in water resources engineering from Bangladesh University of
Engineering & Technology, Dhaka. He has worked in Bangladesh, the US and Australia as an aca-
demic and has conducted research and consultancy works in those countries as well as in Italy,
Denmark, Sweden and Ireland. Saleh’s current research interests include stochastic processes,
optimisation, water resources planning and development, disaster management, hydrology, and
hydraulics. He has authored in excess of 50 refereed articles and won awards for his publications.

xii About the authors

 Opening vignettes are concise case studies showing students the relevance of statistics and how
data are used in business and the world they live in.
Chapter cases are brief business-world issues that introduce students to scenarios that use the
techniques covered in the chapter to make a business decision. These are based on all-new data sets
with a greater focus on cross-sectional data. At the end of each chapter, the chapter case
revisited uses the techniques and concepts from the chapter to help make the business decision and
reinforce the information presented in the text.
Excel-based data analysis is integrated throughout each chapter. Most businesses have access
Key features

to Microsoft Excel and, accordingly, this text focuses on analysing data using Excel with the
techniques learned in each chapter.
Misuse of statistics helps students avoid the pitfalls of using statistics incorrectly in business
scenarios by highlighting their potential misuse in easy-to-understand terms.
Problems are included at the end of every section of the text. They usually follow demonstration
problems and reinforce the concept learned in that section.
Going further with KaddStat is an online guide with stepped instructions to perform
the textbook demonstration problems using enhanced KaddStat Excel functionality. Going further
with KaddStat can be downloaded for free from the student website, www.johnwiley.com.au/
highered/black4e/kaddstat.

Key features xiii

 Chapter Opening vignette Chapter case

1 Introduction to statistics The search for information

Real-world issues

2 Charts and graphs Red tape Electronic games

3 Descriptive summary measures Are you being followed? Location, location, location!

4 Probability A conditional workout Too many leaders

at a glance

5 Discrete distributions Binge drinking Mental health and young

people

6 The normal distribution and Healthy body temperature Prawn farm continues to
other continuous distributions grow

7 Sampling and sampling Detecting accounting fraud Prawn farm success tied to
distributions strict quality control

8 Statistical inference: Rural obesity in Prawn farm up for sale

estimation for single Queensland on the rise
populations

9 Statistical inference: Australian childcare — Prawn farm expects a bright

hypothesis testing for single enough to make you cry? future
populations

10 Statistical inferences about Saving for retirement Life insurance premiums

two populations

11 Analysis of variance and Australian teens and luxury Cyberbullying amongst

design of experiments brands Australian adolescents

12 Chi-square tests Social media is now crucial Job security at Combaro

for business Ltd

13 Simple regression analysis Teenage smoking in Predicting the selling price

pregnancy and birth weight of houses in the city of
Baycoast

14 Multiple regression analysis Video gaming and Predicting the prices of

gambling in Australian houses in Baycoast: using
adolescents additional variables

15 Time-series forecasting and The power of tourism Forecasting at Combaro Ltd

index numbers

xiv Real-world issues at a glance

 The authors and publisher would like to thank the following copyright holders, organisations and
individuals for their permission to reproduce copyright material in Australasian Business Statistics,
4th edition.
Acknowledgements Images
• Google: 2 © Google. • Shutterstock: 14 © filmfoto; 15 (top) © auremar; 48 © Twin Design; 49
© bikeriderlondon; 94, 436 © Syda Productions; 96, 228 (top) © Monkey Business Images; 136
© Piotr Marcinski; 137 © luxorphoto; 170 © AVAVA; 194 © Andrey_Popov; 195 © Dream79;
262 (top) © Goran Bogicevic; 262 (bottom) © Mati Nitibhon; 312 © Jerry Sliwowski; 314
© Rawpixel; 368 © william casey; 369 © SpeedKingz; 410 © Ttatty; 411 © Kzenon; 437 © Ekaterina
Kamenetsky; 480 © Photosani; 481 © Yulia von Eisenstein; 514 © zhu difeng; 516 © gemphoto.
• Interactive Games & Entertainment Association: 15 (bottom), 42 © iGEA 2014. • Alamy: 171
© PhotoStock-Israel. • Picture Media: 228 (bottom) © REUTERS/Andrea Hopkins/Picture Media.

Text
• Oxford University Press: 601–4 © Durbin, J & Watson, GS 1951, ‘Testing for serial correlation in
least squares regression II’, Biometrika, vol. 38, pp. 159–78.

Every effort has been made to trace the ownership of copyright material. Information that will
enable the publisher to rectify any error or omission in subsequent editions will be welcome. In
such cases, please contact the Permissions Section of John Wiley & Sons Australia, Ltd.

John Wiley & Sons, Australia: Terry Burkitt (Publishing Manager), Kylie Challenor (Managing
Content Editor), Beth Klan (Project Editor), Tara Seeto (Senior Publishing Assistant), Delia Sala
(Graphic Designer), Jo Hawthorne (Senior Production Controller), Rebecca Cam (Digital Content
Editor).

Acknowledgements xv
 1
CHAPTER

Introduction to
statistics
LEARNING OBJECTIVES

After studying this chapter, you should be able to:

1 define some basic statistical concepts

2 classify data by type and explain why doing so is important

3 describe some common sources of data used in business statistics

4 outline the appropriate use of computers in statistical analysis

5 discuss some examples of the potential consequences of incorrect data analysis.

OPENING VIGNETTE
The search for information

Every day hundreds of millions of people use Google to search for information on the internet.
The number of searches per year has been growing exponentially since Google was founded
in 1998, and reached a total of 2.2 trillion searches in 2013, or almost 6 billion searches per
day. In 1999 it took Google a month to build an index of 50 million pages. Now this task takes
less than a minute. Currently Google has 68% of total web search volume. Its nearest rival is
Baidu with 19.1%. Google’s revenue has grown from $0.5 billion in the first quarter of 2008 to
almost $16 billion in the second quarter of 2014.
• What algorithms are used to provide fast searches and data retrieval?
• How are algorithms measured for search quality?
• How does Google optimise advertisement quality?
Answering all of these questions depends on statistical analysis of data. Such analysis is
essential for Google to maintain its market dominance and revenue.
It will come as no surprise to learn that Google employs many statisticians. Some are
specialists, but many have dual qualifications. Most of them work in the advertising division
(‘Ads’) or the search engine division (‘Search’). In the advertising division, quantitative analysts
design tools and processes to measure the effectiveness of Google’s advertising service and
in turn to improve those services. In the search division, statisticians analyse the quality of the
results returned by Google’s search engine. That information then feeds back to the software
engineers to improve the search engine.
With perhaps the biggest collection of data in the world, Google requires its statisticians to
work with multi-disciplinary teams to solve a wide range of business problems.

Introduction
Every minute of the working day, businesses around the world make decisions that determine
whether they will profit and grow or whether they will stagnate and die. Most of these decisions are
made with the assistance of information about the marketplace, economic and financial environ-
ments, workforce, competition and other factors. Such information usually comes in the form of
data. Business statistics provides the tools through which data are collected, analysed, summarised,
interpreted and presented to facilitate the decision-making process. Thus, business statistics plays
an important role in decision making within the dynamic world of business.
In this text, we first introduce basic statistical concepts. We then discuss how to organise and
present data so they are meaningful and useful to decision makers. We will learn techniques for

2 Australasian Business Statistics

 sampling (from a population) that allow studies of the business world to be conducted promptly
at lower cost. We will explore various ways to forecast future values and examine techniques for
determining trends. This text also includes many statistical tools for testing hypotheses and for
estimating population parameters. These and many other useful statistical techniques await us on
this journey through business statistics. Let us begin.

1.1 Basic statistical concepts

In this section some basic concepts will be discussed so that statistical problems can be put into
context. These concepts will be covered in detail in later chapters.
Two important concepts in statistics are population and sample. A population is a collection of
objects (often called units or subjects) of interest. Examples of populations include:
1. all small businesses
2. all workers currently employed by BHP Billiton
3. all dishwashers produced by Fisher & Paykel in Auckland in the past 12 months.
A population (and unit) can be very widely defined, such as ‘all cars’, or narrowly defined such as
‘all red Toyota Corolla hatchbacks produced in 2015’.
Collection of data on a whole population is called a census. A sample is a subset of the units in
a population. If selected using the principles of sampling, a sample can be expected to be represen-
tative of the whole population. Sampling has several advantages over a census. In particular, sam-
pling is simpler and cheaper. Further, some forms of data collection are destructive. For example,
crash test statistics for a particular model of car are obtained by destroying the car. This makes it
impossible to collect crash data on all cars, so sampling is the only option.
There are two steps in analysing data from a sample: exploratory data analysis and statistical
inference. These are related and both should be performed for any given data. Exploratory data
analysis, or EDA, is the first step, in which numerical, tabular and graphical summaries (such as
frequency tables, means, standard deviations and histograms) of data are produced to summarise
and highlight the key aspects or any special features of the data. Often, such analysis is sufficient
for the purpose of the study. However, more often this is a precursor to more formal and extensive
analysis of the data.
Statistical inference uses sample data to reach conclusions about the population from which the
sample was drawn. This is usually the main aim of any statistical exercise and involves more formal
data analysis techniques. An inference is a conclusion that patterns observed in the data (sample)
are present in the wider population from which the data were collected. A statistical inference is
an inference based on a probability model linking the data to the population. Clearly such conclu-
sions assume that the sample data are representative of the population; appropriate data collection
is vital for such assumptions to hold true.
As an example, in pharmaceutical research, tests must be limited to a small sample of patients
since new drugs are expensive to produce. Researchers design experiments with small, represen-
tative samples of patients and draw conclusions about the whole population using techniques of
statistical inference.
Note that no inference is required for census data, since a census collects data on the whole
population. In this case, EDA is all that is possible. Any inference will be based on simple com­
parisons of numerical and graphical summaries with a previous census.
A descriptive measure of the population is called a parameter. Parameters are usually denoted by
Greek letters. Examples of parameters are population mean ( µ ), population standard deviation (σ )
and population variance (σ 2). A descriptive measure of a sample is called a statistic. Statistics are
usually denoted by Roman letters. Examples of statistics are sample mean (x ), sample standard
deviation (s) and sample variance (s2).

Chapter 1 Introduction to statistics 3

 Distinction between the terms parameter and statistic is important. A business researcher often
wants to estimate the value of a parameter or draw inferences about the parameter. However, the
calculation of parameters is usually either impossible or infeasible because of the amount of time
and money required to conduct a census. In such cases, the business researcher can take a represen­
tative sample of the population and use the corresponding sample statistic to estimate the popu-
lation parameter. Thus, the sample mean, x, is used to estimate the population mean, µ . The basis
for inferential statistics, then, is the ability to make decisions about parameters without having to
complete a census of the population.
For example, Fisher & Paykel may want to determine the average number of loads that its 8 kg
LCD washing machines can wash before needing repairs. The population here is all the 8 kg LCD
washing machines, and the parameter is the population mean: that is, the average number of washes
per machine before repair. A company statistician takes a representative sample of these machines,
conducts trials on this sample, recording the number of washes before repair for each machine, and
then computes the sample average number of washes before repair. The (population) mean number
of washes for this type of washing machine is then estimated from this sample mean.
Inferences about parameters are made under uncertainty. Unless parameters are computed
directly from a census, the statistician never knows with certainty whether the estimates or infer-
ences made from samples are true. In an effort to estimate the level of confidence in the result of the
process, statisticians use probability statements. Therefore, part of this text is devoted to probability.

1.2 Types of data

Most available data are numerical. Before we analyse data we need to know what the numbers rep-
resent. For example, the data could be the dollar cost of items produced, the geographical location
of retail outlets, weights of shipments or rankings of sales staff. These data are of different types and
cannot be analysed the same way. Which exploratory techniques and which inferential methods we
use are largely determined by the type of data. Data can be broadly classified as qualitative (also
known as categorical) or quantitative (also known as numerical). Categorical data can be further
subclassified as nominal or ordinal, and numerical data can be subclassified as discrete or con-
tinuous. Figure 1.1 shows this pictorially.

Data

Qualitative/Categorical Quantitative/Numerical

FIGURE 1.1
Types of data Nominal Ordinal Discrete Continuous

Categorical data
A data type that is simply an identifier or label and has no numerical meaning is categorical data.
Indeed, such data are often not numbers. For example, the employment of a person (teacher, doctor,
lawyer, engineer, business executive, other) is a categorical data type. As another example, the grade

4 Australasian Business Statistics

 in a test (A, B, C, D, E, F) is again simply a label and is a categorical data type. Notice that the two
examples are slightly different, in that employment of a person cannot be ranked in any meaningful
way, but the test grades have a natural ordering. Thus, the first example is a nominal data type,
while the second is an ordinal data type.

Numerical data
Numerical data have a natural order and the numbers represent some quantity. Two examples are
the number of heads in ten tosses of a coin and the weights of rugby players. Note that in the first
example we know in advance exactly which values the data may take, namely 0, 1, .  .  .  , 10, whereas
in the second example all we can give is perhaps a range (say, 80–140 kg). The first example is that
of a discrete data type, where we can list the possible values. The second example is that of a con-
tinuous data type, where we can give only a range of possible values for the data. Discrete data often
arise from counting processes, while continuous data arise from measurements.
Some data that may be considered to be discrete are often taken as continuous for the purposes
of analysis. For example, a person’s salary is discrete (that is, in dollars and cents), but because the
range of the data is large and often the number of observations is also large, such data are con-
sidered to be continuous.

D E M O N S T R AT I O N P R O B L E M : Shoppers in a city are surveyed by the chamber of commerce. Some of the

P R O B L E M 1. 1 questions in the survey are listed below. What type of data will result from each of the
following questions?
1. What is your age (in years)? _____
2. Which mode of transport did you use to travel to the city today?
Public    Private
3. How far did you travel to the city today (in kilometres)? ______
4. How much did you spend in the city today? _____
5. What did you spend most of your money on today? (choose one)
Clothes   Shoes   Food   Electronic goods   Services   Other
6. How satisfied are you with your shopping experience in the city? (circle one)
Very satisfied   Satisfied   Neutral   Unsatisfied   Very unsatisfied
S O L U T I O N : Question 1 is age in years, so it is a discrete variable. However, for the purpose
of analysis age, like salary, is often regarded as continuous.
In question 2, the shopper is asked to categorise the type of transport they used. The
responses to this question cannot be ranked or ordered in any meaningful way. Therefore the
mode of transport data are categorical, nominal.
Questions 3 and 4 involve measurement and so provide continuous data.
Question 5 results in categorical, nominal data. The data cannot be ranked or ordered.
Question 6 provides categorical ordinal data, as the responses can be ranked or ordered in a
sensible and natural way.

Cross-sectional and time-series data

Data that are collected at a fixed point in time are called cross-sectional data. Such data give a
snapshot of the measured variables at that point in time. For example, Roy Morgan Research con-
ducts and publishes monthly surveys of consumer confidence. The monthly survey provides infor-
mation on consumer confidence for the given month.
Often data are collected over time. Such data are called time-series data. For example, data that
consist of consumer confidence over several months or years are time-series data. Note that, unlike
cross-sectional data, time-series data are time dependent. Such dependence needs to be appropri-
ately modelled and accounted for in the data analysis.

Chapter 1 Introduction to statistics 5

Another random document with
no related content on Scribd:
 CHAPTER XXIV.
MR. BIRON’S REPENTANCE.

Then Bram went upstairs also, and knocked at Mr. Biron’s door.
“I’m going for the doctor now, Mr. Biron,” he called out without
entering. “I’ve come up to ask if there’s anything I can get for you
before I go.”
“Come in, Elshaw, come in!” cried Theodore, in a voice full of
tremulous eagerness. “I want to speak to you.”
Bram obeyed the summons, and found himself for the first time in
Mr. Biron’s bedroom, which was the most luxurious room in the
house. A bright fire burned in the grate, this being a luxury Theodore
always indulged in during the winter; the bed and the windows were
hung with handsome tapestry, and there were book-shelves, tables,
arm-chairs, everything that a profound study of the art of making
oneself comfortable could suggest to the fastidious Theodore.
He himself was sitting, wrapped in a cozy dressing-gown, with his
feet on a hassock by the fire. But he looked even more wretched
than he had done in his drenched clothes downstairs. There was an
unhealthy flush in his face, a feverish glitter in his eyes.
Bram saw something in his face which he had never seen there
before, something which suggested that the man had discovered a
conscience, and that it was giving him uneasiness.
“Sit down,” said he, pointing to a seat on the other side of the
fireplace. Bram wanted to go for the doctor, but the little man was so
peremptory that he thought it best to obey. “Elshaw, I think I’m going
to die.”
He uttered the words, as was natural in such a man, as if the whole
world must be struck into awe by the news. Bram inclined his head in
respectful attention, clasping his hands and looking at the fire. He
could not make light of this presentiment, which, indeed, he saw
reason to think was a well-founded one. Mr. Biron’s never robust
frame had been shaken sorely by his own excesses in the first place,
by erysipelas and consequent complications, and it was evident that
the experiences of this night had tried him very severely. He was still
shivering in a sort of ague: his eyes were glassy, his skin was dry. He
stood as much in need of a doctor’s aid as did his daughter.
But still Bram waited, struck by the man’s manner, and feeling that at
such a moment there was something portentous in his wish to
speak. Mr. Biron had something on his mind, on his conscience, of
which he wanted to unburden himself.
“Elshaw,” he went on after a long pause, “I’ve been to blame over
this—this matter of Claire and—and her cousin Chris.” He stared into
Bram’s face as if the young man had been his confessor, and rubbed
his little white hands quickly the one over the other while he spoke. “I
did it for the best, as I’m sure you will believe; I thought he was an
honorable man, who would marry her and make her happy. You
believe that, don’t you?”
Up to this moment Bram had believed this of Theodore; now for the
first time it flashed through his mind that it was not true. However, he
made a vague motion of the head which Theodore took for assent,
and the latter went on. He seemed to have become suddenly
possessed by a spirit of self-abasement, to feel the need of opening
his heart.
“There was no harm in my sending her to meet him—until—last
night,” pursued the conscience-stricken man. “I know I did wrong in
letting her go then!”
Bram sat up in his chair with horror in his eyes.
“You sent her? Begging, of course, as usual?”
The words were harsh enough, brutal, perhaps, in the
circumstances. But Bram’s feeling was too strong for him to be able
to choose the expression of it. That this father, knowing what he did
know, suspecting what he did suspect, should have sent his
daughter to ask Christian for money was so shocking to his feelings
that he was perforce frank to the utmost.
“What could I do? How could I help it? One has got to live, Claire as
well as I!” muttered Theodore, avoiding Bram’s eyes, and looking at
the fire. “Besides, we don’t know anything. We may be doing her
wrong in suspecting—what—what we did suspect,” said he
earnestly, persuasively. “She never told me that she went away with
him, never! I believe it’s a libel to say she did, the mere malicious
invention of evilly-disposed persons to harm my child.”
Bram was silent. These words chimed in so well with the hopes he
would fain have cherished that, even from the lips of Mr. Biron, they
pleased him in spite of his own judgment. Encouraged by the attitude
which he was acute enough to perceive in his companion, Theodore
went on—
“No, you may blame me as much as you like. You have more to
blame me for than you know. I’m going to tell you all about it—yes,
all about it.” And he began to play nervously with his handkerchief,
and to dart at Bram a succession of quick, restless glances. “But I
will hear nothing against my child. It’s not her fault that she’s the
daughter of her father, is it? But she’s not a chip of the old block, as
you know, Elshaw.”
Bram, who was getting anxious about leaving Claire so long without
medical attention, got up from his chair. He did not feel inclined to
encourage the evident desire of Mr. Biron for the luxury of
confession, of self-abasement. Like most vain persons, Theodore
was almost as willing to excite attention by the record of his
misdeeds as by any other way. And in the same way, when he felt
inclined to write himself down a sinner, nothing would content him
but to be the greatest sinner of them all. So he put up an imploring
hand to detain Bram.
“Wait,” he said petulantly. “Didn’t I say I had something to tell you?
It’s something that concerns Claire, too.”
At the mention of this name Bram, who had moved towards the door,
stopped, although he was inclined to think that all this was a mere
excuse on the part of Theodore to detain him, and put off the
moment when he should be left by himself.
“You remember that a box was sent to you—a chest, by the man at
East Grindley who left you his money?”
Bram nodded. His attention was altogether arrested now. Even
before Mr. Biron uttered his next words it was clear that he had a real
confession to make this time, that he was not merely filling up the
time with idle self-accusations.
“I went to your lodging the day it came, just to see that it was safe.
Your landlady had sent to ask me if I could take care of it for you, as
it was something of value. But I preferred to leave the responsibility
with her. In—in fact, Claire thought it best too.”
Bram read between the lines here, knowing what strong reasons
poor Claire would have for taking this view. Mr. Biron went on—
“There was a key sent with it.”
Bram looked up. He had found no key, and had been obliged to force
the padlock.
“The key was in a piece of paper. I found it on the mantelpiece. I—I
—well, of course, I had no right to do it; but I thought it would be
better for me to look over the contents of the chest to make sure they
were not tampered with in your absence.”
Bram was attentive enough now.
“So I unlocked the box, and I just glanced through the things it
contained. You know what I found; with the exception of this, that
there was some loose cash——”
Bram’s face grew red with sudden perception. But he made no
remark.
“I forget exactly what it was, something between two and three
hundred pounds. Now, I know that in strict propriety,” went on Mr.
Biron, in whom the instinct of confession became suddenly tempered
with a desire to prove himself to have acted well in the matter, “I
ought to have left the money alone. But it was strongly borne in upon
me at the moment that my dear daughter was worried because of
unpaid bills; and—and that, in short, it would be just what you would
wish me to do if you had been here, for me to borrow the loose
sovereigns, and apply them to our pressing necessities. I argued
with myself that you would even prefer, in your delicacy, that I should
not have to ask for them. And—in short, I may have been wrong, but
I—borrowed them.”
A strange light had broken on Bram’s face.
“Did Miss Claire know?” he asked suddenly in a ringing voice.
“Well—er—yes, in point of fact she did. She came to look for me,
and she, well, she saw me take them. She—in fact—wished me to
put them back; and I could not convince her that I was doing what
you would have wished.”
Bram’s brain was bursting. His heart was beating fast. He came
quickly towards Mr. Biron, and seized him by the wrist. There was no
anger in his eyes, nothing but a fierce, hungry hope. For he could not
despise Theodore more than he had done before, while the fact of
Claire’s shame on meeting himself might now bear a less awful
significance then it had seemed to do.
“She knew you had taken it? And you forced her to say nothing?”
cried he in passionate eagerness.
Mr. Biron was disconcerted.
“Well, er—I thought that—that perhaps, until I could see my way to
paying it back, it would be better——”
But Bram did not wait for more explanations. Indeed, he needed no
more. He saw in a flash what the shame was which he had seen in
Claire’s eyes when she met him after his return. It was the
knowledge that her father was a thief, that he had robbed Bram
himself, and that she could neither make restitution nor confession
for him.
And with this knowledge there flashed upon him the question—Was
this the only shame she had to conceal? He was ready, passionately
anxious, to believe that it was.
Mr. Biron was quick to take advantage of this disposition in Bram.
His mood of self-abasement seemed to have passed away as rapidly
as it had come. Not attempting to draw his hand away from Bram’s
grasp, he said buoyantly—
“But I could not let the matter rest. I felt that you might suspect her,
my child, of what her father, from mistaken motives perhaps, had
done——”
Bram cut him short.
“Oh, no, I shouldn’t have done that, Mr. Biron,” he said rather dryly.
“But you were very welcome to the money. And I am glad to think
you enjoyed yourself while it lasted.”
This thrust, caused by a sudden remembrance of the hunter and the
new clothes in which Theodore had been so smart at his expense,
was all the vengeance Bram took. He tore himself away as speedily
as possible, and ran off for the doctor with a lighter heart than he had
borne for many a day. Might not miracles happen? Might they not?
Bram asked himself something like this as he ran through the rain
over the sodden ground.
When he returned to the farmhouse with the doctor, Bram received a
great shock. For, on entering the kitchen, he found Mr. Cornthwaite
himself pacing up and down the room, while Joan watched him with
anxious eyes from the scullery doorway.
Josiah stopped short in his walk when the two men entered. He
nodded to Bram, and wished the doctor good-evening as the latter
passed through, and went upstairs, followed by Joan.
“Will you come through, sir?” said Bram. “There’s a fire in the
drawing-room.”
Mr. Cornthwaite, over whom there had passed some great change,
followed him with only a curt assent. Bram supposed that even he
had been touched to learn that the woman of whom he had come in
search was so ill as to be past understanding that her persecution
had already begun. He stood in front of the fire, with his hat in one
hand and his umbrella in the other, with his back to Bram, in dead
silence for some minutes.
Then he turned abruptly, and asked in a stern, cold voice, without
looking up from the floor, on which he was following the pattern of
the carpet with the point of his umbrella—
“Did that scoundrel Biron get back home all right?”
“He’s got home, sir, but he’s very ill. He’s caught cold, I think.”
“He was not molested, attacked again, by the woman, the woman
Tyzack, who threw the vitriol over him before?”
“No, sir. She followed him, but he lost sight of her before he got
here.”
Mr. Cornthwaite nodded, and was again silent for some time. Bram
was much puzzled. Instead of the fierce resentment, the savage
anger which had possessed the bereaved father immediately after
the loss of his son there now hung over him a gloomy sadness
tempered by an uneasiness and irresolution, which were new
attributes in the business-like, strong-natured man.
The silence had lasted some minutes again, when he spoke as
sharply as before.
“I came to see the daughter, Claire Biron. But I’m told—the woman
tells me—that she is ill, and can’t see any one. Is that true?”
“Yes, sir. She is delirious.”
Mr. Cornthwaite turned away impatiently, and again there was a
pause. At last he said in the same sharp tone—
“You brought her back home, I suppose?”
“Yes. At least I followed her, and when she grew too tired to walk
alone I caught her up, and helped her along.”
Mr. Cornthwaite looked at him curiously. The little room was ill-
lighted, by two candles only and the red glow of the fire. He could
see Bram’s face pretty well, but the young man could not see his.
“Still infatuated, I see?” said Josiah in a hard, ironical voice.
Bram made no answer.
“You intend to marry her, I suppose?” went on Mr. Cornthwaite in a
harder tone than ever.
Bram stared. But he could see nothing of Mr. Cornthwaite’s features,
only the black outline of his figure against the dim candle-light.
“No, sir,” said he steadily. “I only hope to be able to save her life.”
“And how do you propose to do that?”
“Sir, you know best.”
His voice shook, and he stopped. There was silence between them
till they heard the footsteps of the doctor and Joan coming down the
stairs. Mr. Cornthwaite opened the door.
“Well, Doctor,” said he, “what of the patients?”
There was more impatience than solicitude in his tone.
“They’re both very ill,” answered the doctor. “They ought each to
have a nurse, really.”
“Very well. Can you engage them, Doctor? I’ll undertake to pay all
the expenses of their illness.”
The doctor was impressed by this generosity; so was Bram, but in a
different way. What was the reason of this sudden consideration, this
unexpected liberality to the poor relations whom he detested, and to
whom he imputed the death of his son?
“What’s the matter with them?” went on Mr. Cornthwaite in the same
hard, perfunctory, if not slightly suspicious tone.
“Pneumonia in Mr. Biron’s case, brought on by exposure to wet and
cold, no doubt. He has just had a severe shivering fit, and his pulse
is up to a hundred and four. We must do the best we can, but he’s a
bad subject for pneumonia, very.”
“And the daughter?”
“Acute congestion of the brain. She’s delirious.”
“Ah!”
Mr. Cornthwaite seemed satisfied now that he had the doctor’s
assurance that the illness was genuine. He made no more inquiries,
but he followed the medical man into the hall and to the front door.
The doctor perceived that it was locked and bolted at the top and
bottom.
“All right,” said he, “I’ll go through the other way.”
And he made his way to the kitchen, followed by Mr. Cornthwaite
and Bram.
As he opened the door which led into the kitchen, the wind blew
strongly in his face from the outer door, which was wide open. The
rain was sweeping in, and the tablecloth was blown off into his face
as he entered. At the same moment Joan, who had gone into the
back kitchen to prepare something the doctor had ordered, made her
appearance at the door between the two rooms.
“I shouldn’t leave this door open,” said the doctor as he crossed the
room to shut it. “The wind blows through the whole house.”
Joan stared.
“Ah didn’t leave it open, sir,” said she. “Ah’ve only just coom through
here, and it were shut then. Some one’s been and opened it.”
Bram gave a glance round the room, and then opened the door
through which he and the others had just come to examine the hall.
“What’s the matter?” asked Mr. Cornthwaite sharply. He had bidden
the doctor a hasty good-bye, afraid of the condolences which he saw
were on the tip of his tongue.
Bram, with a candle in his hand, was peering into the dark corners.
“I was just thinking, sir, that perhaps Meg Tyzack had got in while we
were talking in the drawing-room,” said he. “Mr. Biron made me bolt
the doors to keep her from getting in. He seemed to be afraid she
would follow him into the house.”
The words were hardly uttered, when from the floor above there
came a piercing scream, a woman’s scream.
“Claire!” shouted Bram, springing on the stairs.
But before he could mount half a dozen steps a wild figure came out
of Claire’s room, and rushed to the head of the staircase in answer
to his call. But it was not Claire. It was, as Bram had feared, Meg
Tyzack, recognizable only by her deep voice, by her loud, hoarse
laugh, for the figure itself looked scarcely human.
Standing at the top of the stairs, with her arms outstretched as if to
prevent any one’s passing her on the way up, the gaunt creature
seemed to be of gigantic height, and looked, with her loose,
disordered hair and the rags which hung down from her arms instead
of sleeves, like a witch in the throes of prophecy.
“Stand back! Stand back! Leave her alone!” she cried furiously, as
Bram rushed up the stairs, and struggled to get past her. She flung
her arms round him, laughing discordantly, and clinging so tightly
that without hurting her he would have found it impossible to
disengage himself.
“What has she done? What has she done?” asked Mr. Cornthwaite
in a loud, hard, angry voice as he came to Bram’s assistance.
At the first sound of Mr. Cornthwaite’s voice, Meg’s rage seemed
suddenly to disappear, to give place to a fit of strange gloom, quite
as wild, and still more terrible to see. Releasing Bram, who ran past
her, she leaned over the banisters, and looked straight into Mr.
Cornthwaite’s haggard face.
“What has she done? What have I done?” said she in a horrible
whisper. “Why, I’ve done the best night’s work that’s ever been done
on this earth, that’s what I’ve done. I’ve sent the man and the woman
I hated both to——. Ha! ha! ha!”
With a shrieking laugh she leapt past him to the bottom of the stairs.
 CHAPTER XXV.
MEG.

Bram Elshaw heard Meg’s wild words as he rushed along the

corridor towards the room out of which she had just come—Claire’s
room, as he guessed, with a sob of terror rising in his throat.
The door was open. On the floor, just inside, lay what Bram at first
thought to be Claire’s lifeless body. Meg had dragged her off the bed,
and flung her down in an ecstasy of mad rage.
But even as he raised her in his arms, before the frightened Joan
had run up to his aid, Bram was reassured. The girl was
unconscious, but she was still breathing. Joan wanted to send him
away.
“Leave her to me, sir, leave her to me. You can goa and fetch t’
doctor back,” cried she, as she tried jealously to take Claire out of his
arms.
But Bram did not seem to hear her. He was staring into the
unconscious face as if this was his last look on earth. He hung over
her with all the agony of his long, faithful, unhappy love softening his
own rugged face, and shining in his gray eyes.
“Oh, Claire, Claire, my little Claire, my darling, are you going away?
Are you going to die?”
The words broke from his lips, hoarse, low, forced up from his heart.
He did not know that he had uttered them; did not know that he was
not alone with the sick girl. Joan, whose tears were running down
her own face, suddenly broke into a loud sob, and shook him roughly
by the shoulder.
“Put her down; do ee put her down,” she said peremptorily. “Do ye
go for to think as your calling to her will do her any good? Goa ee for
t’ doctor. And God forgive me for speaking harsh to ye, sir.”
“Oh Claire, Claire, my little Claire, are you going to die?”—Page
200.
And the good woman, seeing the strange alteration which came over
Bram’s face as he raised his eyes from the girl’s face to hers as if he
had come back from another world, changed her rough touch to a
gentle pat of his shoulder, and turned away sobbing.
Bram lifted Claire from the floor with the easy strength of which his
spare, lean frame gave no promise, and placed her tenderly on the
bed. Then he held one of her hands for a moment, leaned over her,
and kissed her forehead with the lingering but calm tenderness of a
mother to her babe.
“A’ reght,” muttered he to Joan, falling once more into the broad
Yorkshire he had dropped for so long, “Ah’m going.”
At the foot of the stairs he was brought suddenly to full remembrance
of the hard, matter-of-fact world of every day. Mr. Cornthwaite was
standing, cold and grave, buttoning up his coat, ready to go.
“Where are you going?” asked he shortly.
“For the doctor again, sir. Meg has nearly done for her, for Miss
Claire.”
Mr. Cornthwaite uttered a short exclamation, which might have been
meant to express compassion, but which was more like indifference,
or even satisfaction. So Bram felt, in a sudden transport of anger.
“And the old man—Mr. Biron, what did she do to him?”
Bram was silent. He remembered Meg’s ferocious words, her
triumphant cry that she had killed both the woman and the man she
hated; and as the remembrance came back he turned quickly, and
went in the direction of Theodore’s room. But Mr. Biron was lying
quietly in bed, apparently unaware that anything extraordinary had
happened. For when he saw Bram he only asked if he were going to
stay with him. Bram excused himself, and left the room.
“Mr. Biron’s all right, sir,” he said to Mr. Cornthwaite, who had by this
time reached the door, impatient to get away.
The only answer he got was a nod as Mr. Cornthwaite went out of
the house.
Bram had not to go far before he found some one to run his errand
for him, so that he was able to return to the house. His mind was full
of a strange new thought, one so startling that it took time to
assimilate it. He sat for a long time by the kitchen fire, turning the
idea over in his mind, until the doctor returned, and went away again,
after reporting that Claire was not so much injured by the woman’s
violence as might have been feared.
It was very late when a nurse, the only one to be got on the spur of
the moment, arrived at the farmhouse. Bram was still sitting by the
kitchen fire. When she had been installed upstairs Joan came down
for a little while.
“What, you here still, Mr. Elshaw?” cried she.
“Well, you might have known I should be,” he answered with a faint
smile. “I’m here till I’m turned out, day and night now!”
“Why, sir, ye’d best goa whoam,” said Joan kindly. “Ye can do no
good, and Ah won’t leave her, ye may be sure. Ah’ve sent word
whoam as they mun do wi’out me till t’ mornin’.”
“Ah, but I’ve something to say to you, Joan. Look here; doesn’t it
seem very strange that Mr. Cornthwaite when he is half-mad with
grief at his son’s death, should come all the way out here to see his
niece? And that he should say nothing more about—about the death
of his son? And that he should give orders for a nurse to come, and
undertake to pay all the expenses of her illness? Doesn’t it look as if
——”
Joan interrupted him with a profound nod.
“Lawk-a-murcy, ay, sir. Ah’ve thowt o’ that too,” said she in an eager
whisper. “And don’t ye think, sir, as it’s a deal more likely that that
poor, wild body Meg killed Master Christian wi’ her strong arms and
her mad freaks than that our poor little lass oop yonder did it?”
Bram sprang up.
“Joan, that’s what I’ve been thinking myself ever since the woman
rushed out from here. She said she’d sent to h—— the woman and
the man she hated, didn’t she? Well, if Claire was the woman, surely
Mr. Christian must have been the man!”
They stared each into the face of the other, full of strong excitement,
each deriving fresh hope from the hope each saw in the wide eyes of
the other. At last Joan seized his hand, and wrung it in her own
strong fingers with a pressure which brought the water to his eyes.
“You’ve got it, Mr. Bram, you’ve got it, Ah believe!” cried she in a
tumult of feeling. “Oh, for sure that’s reght; and our poor little lass is
as innocent of it as t’ new-born babe!”
Full of this idea, Bram conceived the thought of making inquiries at
Meg’s own home, and he started at once with this object.
It was now very late, past eleven o’clock; but his uneasiness was too
great to allow him to leave the matter till the morning. So, at the risk
of reaching the farmhouse, where Meg’s parents lived, when
everybody was in bed, he took a short cut across the wet, muddy
fields, and arrived at his destination within an hour.
The rain had ceased by this time, and the moon peeped out from
time to time, and from behind a mass of straggling clouds. The little
farm lay in a nook between two hills, and as Bram drew near he saw
that a light was still burning within. In getting over a gate he made a
little noise, and the next moment he saw a woman’s figure come
quickly out of the farmhouse.
“Meg, is that you, Meg?” asked a woman’s voice anxiously.
“No,” said Bram, “it isn’t Meg, ma’am. It’s me, from Hessel, come to
ask if she’d got safe home.”
She came nearer, and peered into his face.
“And who be you?”
“My name’s Bram Elshaw. I’m a friend of the Birons at Duke’s Farm.”
“Ah!”
There was a world of sorrow, of significance, in the exclamation.
After a pause, she said, not angrily, but despondently—
“Then maybe you know all about it? Maybe you can tell me more
than I know myself? Have you seen anything of Meg—she’s my
daughter—this evening?”
Bram hesitated. The woman went on—
“Oh, don’t be afraid to speak out, sir, if it’s bad news. We’ve been
used to that of late; ever since our girl took up with t’ gentleman that
has treated her so bad. It’s no use for to try to hide it; t’ poor lass
herself has spread t’ news about. She’s gone right out of her mind, I
do believe, sir. She wanders about, so I often have to sit up half t’
night for her, and she never gives me a hand now with t’ farm work.
And as neat a hand in t’ dairy as she used to be! Well, sir, what is it?
Has she made away with herself?”
“She came to Duke’s Farm to-night, and attacked Miss Biron,” said
Bram.
“Well, she was jealous,” said Meg’s mother, who seemed to be less
afflicted with sentiment concerning her daughter than with vexation
at the loss of her services. “The lass found it hard she should lose
her character, and then t’ young gentleman care more for his cousin
all t’ time. Not but what Meg was to blame. She used to meet him
when she knew he was going to Duke’s Farm, up in t’ ruined
cottages on top of t’ hill at Hessel. So I’ve learnt since. Folks tell you
these things when it’s too late to stop them!”
Bram remembered the night on which he had heard the voices in the
dismantled cottages, and he remembered also with shame that he
had conceived the idea that Christian’s companion might be his
cousin.
“Did she tell you where she was going when she went out to-night?”
asked Bram.
“She hasn’t been home since this afternoon,” replied Meg’s mother.
“She went out before tea, muttering in her usual way threats against
him and her,—always him and her. She never says any different. I’ve
got used to her ravings; I don’t think she’d do any real harm unless
to herself, poor lass!”
“I’m afraid she has this time,” said Bram gravely. “I don’t know
anything more than I’ve told you; but I’m afraid you must be prepared
for worse news in the morning.”
Startled, the woman pressed for an explanation. Bram, having really
nothing but suspicion to go upon, could tell her nothing definite. But
his suspicion was so strong that he felt no diffidence about preparing
Meg’s mother for a dreadful shock. On the other hand, he was able
to assure her that, whatever she might have done, her manifestly
disordered state of mind would be considered in the view taken of
her actions.
Then he returned to Hessel, tried the door of Duke’s Farm, and
found it locked for the night. He went round to the front, looked up at
the dim light burning in Claire’s room with a fervent prayer on his
lips, and then climbed the hill to his own lodging.
On inquiry at the farm next morning on his way to his work Bram
learnt from the nurse, who was the only person he could see, that
while Mr. Biron had had a very bad night, Claire was as well as could
be expected. No decided improvement could be reported as yet, nor
could it indeed be expected. But she was quieter, and her
temperature had gone down, temporarily at least.
He went on his way feeling a little more hopeful, after impressing
upon the nurse to keep the doors locked for fear of any further
incursions from poor, crazy Meg Tyzack.
On arriving at the works, he saw, as was to be expected after the
tragedy of the preceding evening, an unusual stir among the
workmen, who were standing about the entrance, talking in eager
and excited tones. One of the workmen saluted Bram, and asked
him if he had “heard t’ fresh news.”
“What’s that?” asked Bram.
“Coom this weay, sir; Ah’ll show ye.”
Bram, with a sick terror at his heart, asking himself what new horror
he should be called upon to witness, followed the man through the
works. The rain had come on again, a drizzling, light rain, which was
already turning the morning’s dust into a thick, black paste. They
passed across the yards and through the sheds, until again they
reached the spot where the railway divided the works into two parts.
An exclamation broke from Bram’s lips.
“Not another—accident—here?”
For there was quite a large throng of workmen scattered over the
lines on the opposite side, and culminating in one dense group not
far from the spot where he had found Christian on the previous night.
“Ay, sir, it’s a woman this time.” And his voice suddenly fell to a
hoarse whisper. “T’ woman as killed Mr. Christian! T’ poor creature
was crazed, for sure! She got in here, nobody knows how, this
morning; an’ she must ha’ throwed herself down on t’ line pretty nigh
t’ place where she throwed him down last neght. She must ha’
waited for t’ mornin’ oop train. Anyway, we fahnd her lyin’ there this
mornin’, poor lass!”
Bram had reached the group. He forced his way through, and looked
down at the burden the men were carrying towards the very shed
under the roof of which Chris had died.
The mutilated body, which had been decapitated by the heavy
wheels of the train, was only recognizable by the torn and stained
clothing as that of Meg Tyzack.
Bram staggered away, with his hand over his eyes.