Professional Documents
Culture Documents
Essential
STATISTICS
exploring the world through data
vii
xi
Approach
Our text is concept-based, as opposed to method-based. We teach useful statistical
methods, but we emphasize that applying the method is secondary to understanding the
concept.
In the real world, computers do most of the heavy lifting for statisticians. We
therefore adopt an approach that frees the instructor from having to teach tedious
procedures and leaves more time for teaching deeper understanding of concepts.
Accordingly, we present formulas as an aid to understanding the concepts, rather than
as the focus of study.
We believe students need to learn how to
• Determine which statistical procedures are appropriate.
• Instruct the software to carry out the procedures.
• Interpret the output.
We understand that students will probably see only one type of statistical software in
class. But we believe it is useful for students to compare output from several different
sources, so in some examples we ask them to read output from two or more software
packages.
One of the authors (Rob Gould) served on a panel of co-authors for the first
edition of the collegiate version of the American Statistical Association–endorsed
Guidelines for Assessment and Instruction in Statistics Education (GAISE). We firmly
believe in its main goals and have adopted them in the preparation of this book.
• We emphasize understanding over rote performance of procedures.
• We use real data whenever possible.
• We encourage the use of technology both to develop conceptual understanding and
to analyze data.
• We believe strongly that students learn by doing. For this reason, the homework
problems offer students both practice in basic procedures and challenges to build
conceptual understanding.
Coverage
The first few chapters of this book are concept-driven and cover exploratory data anal-
ysis and inferential statistics—fundamental concepts that every introductory statistics
student should learn. The last part of the book builds on that strong conceptual foun-
dation and is more methods-based. It presents several popular statistical methods and
more fully explores methods presented earlier.
Our ordering of topics is guided by the process through which students should
analyze data. First, they explore and describe data, possibly deciding that graphics and
numerical summaries provide sufficient insight. Then they make generalizations (infer-
ences) about the larger world.
Chapters 1–4: Exploratory Data Analysis. The first four chapters cover data collection
and summary. Chapter 1 introduces the important topic of data collection and com-
pares and contrasts observational studies with controlled experiments. This chapter also
teaches students how to handle raw data so that the data can be uploaded to their statis-
tical software. Chapters 2 and 3 discuss graphical and numerical summaries of single
variables based on samples. We emphasize that the purpose is not just to produce a
graph or a number but, instead, to explain what those graphs and numbers say about
the world. Chapter 4 introduces simple linear regression and presents it as a technique
for providing graphical and numerical summaries of relationships between two numeri-
cal variables.
We feel strongly that introducing regression early in the text is beneficial in build-
ing student understanding of the applicability of statistics to real-world scenarios.
After completing the chapters covering data collection and summary, students have
acquired the skills and sophistication they need to describe two-variable associations
and to generate informal hypotheses. Two-variable associations provide a rich context
for class discussion and allow the course to move from fabricated problems (because
one-variable analyses are relatively rare in the real world) to real problems that appear
frequently in everyday life.
Chapters 5–8: Inference. These chapters teach the fundamental concepts of statisti-
cal inference. The main idea is that our data mirror the real world, but imperfectly;
although our estimates are uncertain, under the right conditions we can quantify our
uncertainty. Verifying that these conditions exist and understanding what happens if
they are not satisfied are important themes of these chapters.
Chapters 9–10: Methods. Here we return to the themes covered earlier in the text and
present them in a new context by introducing additional statistical methods, such as
estimating population means and analyzing categorical variables. We also provide (in
Section 10.3) guidance for reading scientific literature, to offer students the experience
of critically examining real scientific papers.
Organization
Our preferred order of progressing through the text is reflected in the Contents, but
there are some alternative pathways as well.
10-week Quarter. The first eight chapters provide a full, one-quarter course in intro-
ductory statistics. If time remains, cover Sections 9.1 and 9.2 as well, so that students
can solidify their understanding of confidence intervals and hypothesis tests by revisit-
ing the topic with a new parameter.
Proportions First. Ask two statisticians, and you will get three opinions on whether
it is best to teach means or proportions first. We have come down on the side of
proportions for a variety of reasons. Proportions are much easier to find in popular
news media (particularly around election time), so they can more readily be tied to
students’ everyday lives. Also, the mathematics and statistical theory are simpler;
because there’s no need to provide a separate estimate for the population standard
deviation, inference is based on the Normal distribution, and no further approxima-
tions (that is, the t-distribution) are required. Hence, we can quickly get to the heart
of the matter with fewer technical diversions.
The basic problem here is how to quantify the uncertainty involved in estimating a
parameter and how to quantify the probability of making incorrect decisions when pos-
ing hypotheses. We cover these ideas in detail in the context of proportions. Students
can then more easily learn how these same concepts are applied in the new context of
means (and any other parameter they may need to estimate).
Means First. Conversely, many people feel that there is time for only one parameter
and that this parameter should be the mean. For this alternative presentation, cover
Chapters 6, 7, and 9, in that order. On this path, students learn about survey sampling
and the terminology of inference (population vs. sample, parameter vs. statistic) and
then tackle inference for the mean, including hypothesis testing.
To minimize the coverage of proportions, you might choose to cover Chapter 6,
Section 7.1 (which treats the language and framework of statistical inference in detail),
and then Chapter 9. Chapters 7 and 8 develop the concepts of statistical inference more
slowly than Chapter 9, but essentially, Chapter 9 develops the same ideas in the context
of the mean.
If you present Chapter 9 before Chapters 7 and 8, we recommend that you devote
roughly twice as much time to Chapter 9 as you have devoted to previous chapters,
because many challenging ideas are explored in this chapter. If you have already cov-
ered Chapters 7 and 8 thoroughly, Chapter 9 can be covered more quickly.
Features
We’ve incorporated into this text a variety of features to aid student learning and to
facilitate its use in any classroom.
Integrating Technology
Modern statistics is inseparable from computers. We have worked to make this text acces-
sible for any classroom, regardless of the level of in-class exposure to technology, while
still remaining true to the demands of the analysis. We know that students sometimes do
not have access to technology when doing homework, so many exercises provide output
from software and ask students to interpret and critically evaluate that given output.
Using technology is important because it enables students to handle real data, and
real data sets are often large and messy. The following features are designed to guide
students.
• TechTips outline steps for performing calculations using TI-84® (including
TI-84 + C®) graphing calculators, Excel®, Minitab®, and StatCrunch®. We do not
want students to get stuck because they don’t know how to reproduce the results
we show in the text, so whenever a new method or procedure is introduced, an
icon, Tech , refers students to the TechTips section at the end of the chapter. Each
set of TechTips contains at least one mini-example, so that students are not only
learning to use the technology but also practicing data analysis and reinforcing
ideas discussed in the text. Most of the provided TI-84 steps apply to all TI-84
calculators, but some are unique to the TI-84 + C calculator.
• Check Your Tech examples help students understand that statistical calculations
done by technology do not happen in a vacuum and assure them that they can get
the same numerical values by hand. Although we place a higher value on inter-
preting results and verifying conditions required to apply statistical models, the
numerical values are important, too.
• All data sets used in the exposition and exercises are available on the companion
website at pearsonhighered.com/gould. These data are also available at http://www
.pearsonhighered.com/mathstatsresources/. A variety of statistical software options
are available to be bundled with this text. For a complete list of the software options,
please contact your Pearson Education sales representative.
Guiding Students
• Each chapter opens with a Theme. Beginners have difficulty seeing the forest for
the trees, so we use a theme to give an overview of the chapter content.
• Each chapter begins by posing a real-world Case Study. At the end of the chapter,
we show how techniques covered in the chapter helped solve the problem pre-
sented in the Case Study.
• Margin Notes draw attention to details that enhance student learning and reading
comprehension.
The data icon appears alongside examples or discussions to indicate that the
original data are available on the companion website.
Caution notes provide warnings about common mistakes or misconceptions.
• KEY
POINT Key Points highlight essential concepts to draw special attention to them.
Understanding these concepts is essential for progress.
• Snapshots break down key statistical concepts introduced in the chapter,
quickly summarizing each concept or procedure and indicating when and how
it should be used.
• An abundance of worked-out examples model solutions to real-world problems rel-
evant to students’ lives. Each example is tied to an end-of-chapter exercise so that
students can practice solving a similar problem and test their understanding. Within the
exercise sets, the icon TRY indicates which problems are tied to worked-out examples
in that chapter, and the numbers of those examples are indicated.
• The Chapter Review that concludes each chapter provides a list of important new
terms, student learning objectives, a summary of the concepts and methods dis-
cussed, and sources for data, articles, and graphics referred to in the chapter.
Active Learning
• For each chapter we’ve included an activity, Exploring Statistics, that students
are intended to do in class as a group. We have used these activities ourselves, and
we have found that they greatly increase student understanding and keep students
engaged in class.
• All exercises are located at the end of the chapter. Section Exercises are designed
to begin with a few basic problems that strengthen recall and assess basic knowl-
edge, followed by mid-level exercises that ask more complex, open-ended ques-
tions. Chapter Review Exercises provide a comprehensive review of material
covered throughout the chapter.
The exercises emphasize good statistical practice by requiring students to
verify conditions, make suitable use of graphics, find numerical values, and
interpret their findings in writing. All exercises are paired so that students can check
their work on the odd-numbered exercise and then tackle the corresponding even-
numbered exercise. The answers to all odd-numbered exercises appear in the back
of the student edition of the text.
Challenging exercises, identified with an asterisk (*), ask open-ended questions
and sometimes require students to perform a complete statistical analysis. For
exercises marked with a , accompanying data sets are available in MyStatLab and
on the companion website.
• Most chapters include select exercises marked with a within the exercise set,
to indicate that problem-solving help is available in the Guided Exercises
section. If students need support while doing homework, they can turn to the
Guided Exercises to see a step-by-step approach to solving the problem.
Acknowledgments
We are grateful for the attention and energy that a large number of people devoted to
making this a better book. We extend our gratitude to Elaine Newman (Sonoma State
University) and Ann Cannon (Cornell College), who checked the accuracy of this
text and its many exercises. Thanks also to David Chelton, our developmental editor,
to Carol Merrigan, who handled production, to Peggy McMahon, project manager,
and to Connie Day, our copyeditor. Many thanks to John Norbutas for his technical
advice and help with the TechTips. We thank Suzanna Bainbridge, our acquisitions
editor, Justin Billing, editorial assistant, and Deirdre Lynch, editor-in-chief, for signing
us up and sticking with us, and we are grateful to Dona Kenly and Erin Kelly for their
market development efforts.
We extend our sincere thanks for the suggestions and contributions made by the
following reviewers of this edition:
Lloyd Best, Pacific Union College Patrick Perry, Hawaii Pacific University Mahbobeh Vezvaei, Kent State
Mario Borha, Loyola University of Victor I. Piercey, Ferris State University University
Chicago Danielle Rivard, Post University Jerimi Ann Walker, Moraine Valley
David Bosworth, Hutchinson Community Alex Rolon, North Hampton Community Community College
College College Dottie Walton, Cuyahoga Community
Beth Burns, Bowling Green State University Ali Saadat, University of California – College
Jim Johnston, Concord University Riverside Judy H. Williams, Tidewater Community
Manuel Lopez, Cerritos College Carol Saltsgaver, University of Illinois – College
Ralph Padgett Jr., University of California – Springfield Jane Marie Wright, Suffolk County
Riverside Kelly Sakkinen, Lake Land College Community College
Ron Palcic, Johnson County Community Sharon l. Sullivan, Catawba College Cathleen Zucco-Teveloff, Rider
College Manuel Uy, College of Alameda University
We would also like to extend our sincere thanks for the suggestions and contributions
that the following reviewers, class testers, and focus group attendees made to the previ-
ous edition.
Arun Agarwal, Grambling State University Elizabeth Paulus Brown, Waukesha Karen Estes, St. Petersburg College
Anne Albert, University of Findlay County Technical College Mariah Evans, University of Nevada, Reno
Michael Allen, Glendale Community College Leslie Buck, Suffolk Community College Harshini Fernando, Purdue University
Eugene Allevato, Woodbury University R.B. Campbell, University of Northern Iowa North Central
Dr. Jerry Allison, Trident Technical College Stephanie Campbell, Mineral Area College Stephanie Fitchett, University of Northern
Polly Amstutz, University of Nebraska Ann Cannon, Cornell College Colorado
Patricia Anderson, Southern Adventist Rao Chaganty, Old Dominion University Elaine B. Fitt, Bucks County Community
University Carolyn Chapel, Western Technical College College
MaryAnne Anthony-Smith, Santa Ana Christine Cole, Moorpark College Michael Flesch, Metropolitan Community
College Linda Brant Collins, University of Chicago College
David C. Ashley, Florida State College James A. Condor, Manatee Community Melinda Fox, Ivy Tech Community
at Jacksonville College College, Fairbanks
Diana Asmus, Greenville Technical College Carolyn Cuff, Westminster College Joshua Francis, Defiance College
Kathy Autrey, Northwestern State Phyllis Curtiss, Grand Valley State Michael Frankel, Kennesaw State
University of Louisiana University University
Wayne Barber, Chemeketa Community Monica Dabos, University of California, Heather Gamber, Lone Star College
College Santa Barbara Debbie Garrison, Valencia Community
Roxane Barrows, Hocking College Greg Davis, University of Wisconsin, College, East Campus
Jennifer Beineke, Western New England Green Bay Kim Gilbert, University of Georgia
College Bob Denton, Orange Coast College Stephen Gold, Cypress College
Diane Benner, Harrisburg Area Julie DePree, University of New Nick Gomersall, Luther College
Community College Mexico–Valencia Mary Elizabeth Gore, Community College
Norma Biscula, University of Maine, Jill DeWitt, Baker Community College of Baltimore County–Essex
Augusta of Muskegon Ken Grace, Anoka Ramsey Community
K.B. Boomer, Bucknell University Paul Drelles, West Shore Community College College
David Bosworth, Hutchinson Community Keith Driscoll, Clayton State University Larry Green, Lake Tahoe Community
College Rob Eby, Blinn College College
Diana Boyette, Seminole Community Nancy Eschen, Florida Community Jeffrey Grell, Baltimore City Community
College College at Jacksonville College
Albert Groccia, Valencia Community Walter H. Mackey, Owens Community Community College
College, Osceola Campus College Delray Schultz, Millersville University
David Gurney, Southeastern Louisiana Keith McCoy, Wilbur Wright College Jenny Shook, Pennsylvania State
University Elaine McDonald-Newman, Sonoma State University
Chris Hakenkamp, University of University Danya Smithers, Northeast State
Maryland, College Park William McGregor, Rockland Community Technical Community College
Melodie Hallet, San Diego State University College Larry Southard, Florida Gulf Coast
Donnie Hallstone, Green River Bill Meisel, Florida State College at University
Community College Jacksonville Dianna J. Spence, North Georgia College
Cecil Hallum, Sam Houston State University Bruno Mendes, University of California, & State University
Josephine Hamer, Western Connecticut Santa Cruz René Sporer, Diablo Valley College
State University Wendy Miao, El Camino College Jeganathan Sriskandarajah, Madison Area
Mark Harbison, Sacramento City College Robert Mignone, College of Charleston Technical College–Traux
Beverly J. Hartter, Oklahoma Wesleyan Ashod Minasian, El Camino College David Stewart, Community College of
University Megan Mocko, University of Florida Baltimore County–Cantonsville
Laura Heath, Palm Beach State College Sumona Mondal, Clarkson University Linda Strauss, Penn State University
Greg Henderson, Hillsborough Kathy Mowers, Owensboro Community John Stroyls, Georgia Southwestern
Community College and Technical College State University
Susan Herring, Sonoma State University Mary Moyinhan, Cape Cod Community Joseph Sukta, Moraine Valley
Carla Hill, Marist College College Community College
Michael Huber, Muhlenberg College Junalyn Navarra-Madsen, Texas Woman’s Lori Thomas, Midland College
Kelly Jackson, Camden County College University Malissa Trent, Northeast State Technical
Bridgette Jacob, Onondaga Community Azarnia Nazanin, Santa Fe College Community College
College Stacey O. Nicholls, Anne Arundel Ruth Trygstad, Salt Lake Community
Robert Jernigan, American University Community College College
Chun Jin, Central Connecticut State Helen Noble, San Diego State University Gail Tudor, Husson University
University Lyn Noble, Florida State College at Manuel T. Uy, College of Alameda
Maryann Justinger, Ed.D., Erie Jacksonville Lewis Van Brackle, Kennesaw State
Community College Keith Oberlander, Pasadena City College University
Joseph Karnowski, Norwalk Community Pamela Omer, Western New England Mahbobeh Vezvaei, Kent State University
College College Joseph Villalobos, El Camino College
Susitha Karunaratne, Purdue University Nabendu Pal, University of Louisiana at Barbara Wainwright, Sailsbury University
North Central Lafayette Henry Wakhungu, Indiana University
Mohammed Kazemi, University of North Irene Palacios, Grossmont College Dottie Walton, Cuyahoga Community
Carolina–Charlotte Adam Pennell, Greensboro College College
Robert Keller, Loras College Joseph Pick, Palm Beach State College Jen-ting Wang, SUNY, Oneonta
Omar Keshk, Ohio State University Philip Pickering, Genesee Community Jane West, Trident Technical College
Raja Khoury, Collin County Community College Michelle White, Terra Community College
College Robin Powell, Greenville Technical Bonnie-Lou Wicklund, Mount Wachusett
Brianna Killian, Daytona State College College Community College
Yoon G. Kim, Humboldt State University Nicholas Pritchard, Coastal Carolina Sandra Williams, Front Range
Greg Knofczynski, Armstrong Atlantic University Community College
University Linda Quinn, Cleveland State University Rebecca Wong, West Valley College
Jeffrey Kollath, Oregon State University William Radulovich, Florida State Alan Worley, South Plains College
Erica Kwiatkowski-Egizio, Joliet Junior College at Jacksonville Jane-Marie Wright, Suffolk Community
College Mumunur Rashid, Indiana University of College
Sister Jean A. Lanahan, OP, Molloy Pennsylvania Haishen Yao, CUNY, Queensborough
College Fred J. Rispoli, Dowling College Community College
Katie Larkin, Lake Tahoe Community Nancy Rivers, Wake Technical Lynda Zenati, Robert Morris Community
College Community College College
Michael LaValle, Rochester Community Corlis Robe, East Tennesee State University Yan Zheng-Araujo, Springfield
College Thomas Roe, South Dakota State University Community Technical College
Deann Leoni, Edmonds Community College Dan Rowe, Heartland Community College Cathleen Zucco-Teveloff, Rider
Lenore Lerer, Bergen Community College Carol Saltsgaver, University of University
Quan Li, Texas A&M University Illinois–Springfield Mark A. Zuiker, Minnesota State
Doug Mace, Kirtland Community College Radha Sankaran, Passaic County University,
Technology Tutorial
Videos and Study Cards
Technology Tutorials provide brief
video walkthroughs and step-by-
step instructional study cards on
common statistical procedures
for Minitab®, Excel®, and the
TI-83/84 graphing calculator.
www.mystatlab.com
www.mystatlab.com
xx
exercise, 34, 64, 197 stroke survival rate, 389 SOCIAL ISSUES
flu vaccines, 31 systolic blood pressures, 461–462 adoptions, 71
hand and foot length, 185–186 tight control of blood sugar, 512 age by year, 71
hand washing, 348, 399 transfusions for bleeding in the stomach, ages of brides and grooms, 464
handspans, 181 346 belief in UFOs, 245
head circumference, 126, 130, 134 treatment for CLL, 395, 400 body piercings, 50–51
healthcare plan, 399 triglycerides, 461, 462 cell phone calls, 455
heart attacks, 389 vaccinations for diarrhea, 514 country of origin, 507
heart rate before and after coffee, 465 vegan diets, 342 cremation rates, 292
heights, 131 video games and body mass index, 184 death row and head trauma, 34
heights and ages for children, 198 vitamin C and allergies, 31 divorce, 290
heights and weights, 152–153, 181, vitamin D and osteoporosis, 33 drunk walking, 291
193–194 weight loss, 31, 121, 180, 397, 507 education and marital status, 214,
heights of bedridden patients, 163–165 weights of soccer players and academic 215–216, 217, 221, 487–488
heights of children, 104–106 decathlon team members compared, education and widows, 225
heights of fathers and sons, 130, 193 122 gays and lesbians, 241, 345, 397
heights of females, 124, 133 weights of vegetarians, 459 gender and opinion on same-sex
heights of males, 133, 459, 464 marriage, 480–481
heights of students and parents, 467 LAW guns in homes, 398
HIV-1 and HIV-2, 33 chief justices’ ages at installation, 121 happiness, 123, 125, 196, 465
hormone replacement therapy, 73 gun control, 393, 397, 399 ideal family, 131
hospital rooms, 510–511 Oregon bar exam, 342, 349 Iraq casualties and hometown
human cloning, 344 three-strikes law, 397–398 populations, 191
hypothermia for babies, 395 life expectancy and TV, 191
ideal weight, 75 marital status, 32
iron and death rate, 511 POLITICS
marriage and children, 237
jet lag drug, 506–507 children of first ladies, 121
marriage and college degree, 237
life expectancy, 188, 191 dodging the question, 355–356, 385–386
marriage rates, 29
light at night and tumors, 510 party and right direction, 506
number of births and population, 30
light exposure in mice, 31–32 political party, 243–244
number of children, 458
low birth weights, 292 presidential election of 1960, 397
number of cigarettes smoked, 76
malnutrition, 345–346 presidents’ ages at inauguration, 121, 460
number of siblings, 28, 65, 180
Medicaid expansion, 33 primary elections of 2012, 348
obesity and marital status, 507, 515
men’s health, 370–372 socialism, 241
Occupy Wall Street, 509
multiple myeloma, 514 votes for independents, 398
population and number of millionaires, 189
nausea drug, 346 voting, 237, 343
population density, 29, 127, 132
nicotine gum, 395 population in 2007, 29
nicotine patch, 509–510 PSYCHOLOGY population increase, 132
nighttime physician staffing in ICU, 514 body image, 72 population prediction, 29
no-carb diets, 394 boys’ weight perception, 466–467 probation and gender, 32–33
number of AIDS cases, 29, 34–35 brain games, 20–21 proportion of people who are married,
obesity, 32, 344 confederates and compliance, 31, 397
obesity and marital status, 507 509–510 smiling and age, 396
overweight children, 342 depression treatment, 30 spring break fever, 301–302, 336
personal data collection, 8–9 dreaming, 348, 391
pneumonia vaccine for young children, extrasensory perception, 269, 274–276, SPORTS
30–31 340–341, 390, 396, 398–399 baseball strike, 126
position for breathing, 74 financial incentive effectiveness, 394 basketball free-throw shots, 243, 280
pregnancy, 124, 405–406, 451 gender and happiness of marriage, 508 basketball team heights, 468
preventable deaths, 69–70 happiness and traditional views, 239 marathon size, 46–47, 110, 131
prostate cancer, 32, 514 happiness and wealth, 242 NCAA soccer players, 50
pulse rates, 413, 460, 461, 463, 469 IQs, 124 Olympics, 122
removal of healthy appendixes, 510 obesity and marital status, 32 race finishing times, 165
scorpion antivenom, 33 opinion about nurses, 245 surfing, 121–122, 132, 464
SIDS, 205–206 overeating and brain function, 31 weights of backpacks, 464
sleep, 63, 64, 72, 180, 464, 466 poverty and IQ, 17–18 weights of baseball and soccer players
sleep medicine for shift workers, 398 sleep walking, 392 compared, 67
smoking, 123, 187, 188, 347, 463 smiling, 395 weights of college athletes, 462
steroids and height, 511 smiling and age, 508 wins and strike-outs for baseball pitchers,
stroke, 33 TV violence, 482–483, 506, 507–508 189
SURVEYS AND OPINION stem cell research, 321, 332–334, driving accidents, 132–133
POLLS 381–382 DWI convictions, 291
astrology, 344 taxes, 393 gas mileage of cars, 196
capital punishment, 340 underwater mortgages, 328–329 gas prices, 86–87, 92–93, 101
confidence in military, 343 value of college education, 236–237, meter thieves, 143, 176
confidence in public schools, 343 238, 245 MPG for highway and city, 190
dreaming in color, 348 wording of polls, 397 pedestrian fatalities, 30
e-reader poll, 364–365 plane crashes, 393
economics in East Germany, 343 TECHNOLOGY red cars and stop signs, 505–506
gender and opinion on same-sex age and the Internet, 303 right of way, 382–384
marriage, 480–481 cell phone use, 72, 455 seat belt use, 11–13, 239, 245, 390,
ghosts, 327 e-music and the Internet, 73 391–392
human cloning, 344 e-readers, 441–443 speed driven, 75
immigration, 343 Internet access, 241, 291 speeding tickets, 64, 131
marriage as obsolete, 343, 391 Internet advertising, 358–359 stolen bicycles, 272–273, 290
most important problem, 507 teens and the Internet, 220 stolen car rates, 14
musician survey, 72 text messages, 69, 190, 192 SUVs, 390
news survey, 281 texting while driving, 291, 398 texting while driving, 291, 398
opinion about nurses, 245 time and distance of flights, 188, 198
opinions on global warming, 74–75, 393 TRANSPORTATION traffic cameras, 75
party and right direction, 506 air fares, 183–184 traffic lights, 243
political party affiliation, 70–71 commuting times, 64 turn signal use, 346
presidential elections, 320–321, 344 crash-test results, 7 used car age and mileage, 147–148,
seat belt use, 11–13, 140, 390, 391–392 driver’s exam, 238, 241, 291–292 168–169, 456
sexual harassment, 307–308 drivers aged 60–65, 291 used car values, 168–169
Social Security, 339 drivers’ deaths and ages, 188 waiting for the bus, 254–255
TABLE I—Continued
Means of
Chemical Belligerent Effect
Projection
Mixtures[4]
Bromoacetone (80%) and French Lachrymatory Artillery shell
Chloroacetone (20%) Lethal
Chlorine (50%) and British Lethal
Cylinders
Phosgene (50%) German
Chlorine (70%) and Lethal
British Cylinders
Chloropicrin (30%) Lachrymatory
Chloropicrin (65%) and Lethal
British Cylinders
Hydrogen sulfide (35%) Lachrymatory
Chloropicrin (80%) and British Lethal Artillery shell
Stannic chloride (20%) French Lachrymatory Trench mortar bombs
American Irritant Projectors
Chloropicrin (75%) and Lethal Artillery shell
Phosgene (25%) British Lachrymatory Trench mortar bombs,
projectors
Dichloroethyl sulfide (80%) German Vesicant
and Chlorobenzene (20%) French Lethal Artillery shell
British
American
Ethyl carbazol (50%) and Sternutatory
German Artillery shell
Diphenylcyanoarsine (50%) Lethal
Ethyldichloroarsine (80%) and Lethal
German Artillery shell
Dichloromethylether (20%) Lachrymatory
Ethyliodoacetate (75%) and Artillery shell,
Alcohol (25%) British Lachrymatory 4-in. Stokes’ mortars,
Means of
Chemical Belligerent Effect
Projection
hand grenades
Hydrocyanic acid (55%)
Chloroform (25%) and British Lethal Artillery shell
Arsenious chloride (20%)
Hydrocyanic acid (50%),
Arsenious chloride (30%), French Lethal Artillery shell
Stannic chloride (15%) and
Chloroform (5%)
Phosgene (50%) and
British Lethal Artillery shell
Arsenious chloride (50%)
Dichloroethyl sulfide (80%) German Vesicant
and Carbon tetrachloride (20%) French Lethal Artillery shell
British
American
Phosgene (60%) and British Lethal
Artillery shell
Stannic chloride (40%) French Irritant
Methyl sulfate (75%) and Lachrymatory
French Artillery shell
Chloromethyl sulfate (25%) Irritant
(2) To simulate the presence of a toxic gas. This may be done either by
using a substance whose odor in the field strongly suggests that of the gas
in question, or by so thoroughly associating a totally different odor with a
particular “gas” in normal use that, when used alone, it still seems to imply
the presence of that gas. This use of imitation gas would thus be of service
in economizing the use of actual “gas” or in the preparation of surprise
attacks.
While there was some success with this kind of “gas,” very few such
attacks were really carried out, and these were in connection with projector
attacks.
Gases Used
Table I gives a list of all the gases used by the various armies, the
nation which used them, the effect produced and the means of projection
used.
Table II gives the properties of the more important war cases (compiled
by Major R. E. Wilson, C. W. S.).
The gases used by the Germans may also be classified by the names
of the shell in which they were used. Table III gives such a classification.
TABLE II
Physical Constants of Important War Gases
Liquid
Vapor
Density
Melting Boiling Pressure
Molecular at 20° C.
Name of Gas Formula point, point, at 20° C.
Weight under
°C. °C. (mm.
Own
Hg)
Pressure
Liquid
Vapor
Density
Melting Boiling Pressure
Molecular at 20° C.
Name of Gas Formula point, point, at 20° C.
Weight under
°C. °C. (mm.
Own
Hg)
Pressure
Bromoacetone C₃H₅BrO 136.98 1.7(?) - 54 126 9(?)
Carbon monoxide CO 28.00 (Gas) -207 -190 (Gas)
Cyanogen bromide BrCN 106.02 2.01 52 61.3 89
Cyanogen chloride ClCN 61.56 1.186 -6 15 1002
Chlorine Cl₂ 70.92 1.408 -101.5 33.6 5126
Chloropicrin Cl₃C(NO₂) 164.39 1.654 - 69.2 112 18.9
Dichloroethyl sulfide (CH₃CHCl₂)S 169.06 1.274 12.5 216 .06
Diphenylchloroarsine (C₆H₅)₂AsCl 264.56 1.422 44 333 .0025
Hydrocyanic acid HCN 27.11 .697 - 14 26.1 603
Phenyldichloroarsine C₆H₅AsCl₂ 210.96 1.640 ... 253 .022
Phosgene COCl₂ 98.92 1.38 ... 8.2 1215
Stannic chloride SnCl₄ 260.54 2.226 - 33 114 18.58
Superpalite CCl₃COOCl 197.85 1.65 ... 128 10.3
(
Xylyl bromide CH₃)C₆H₄CH₂Br 185.03 1.381 -2 214.5 ...
TABLE III
German Shell
Nature of
Name of Shell Shell Filling
Effect
B-shell [K₁ shell (White B or BM)] Bromoketone Lachrymator
(Bromomethylethyl ketone)
Blue Cross (a) Diphenylchloroarsine Sternutator
(b) Diphenylcyanoarsine Sternutator
(c) Diphenylchloroarsine,
Ethyl carbazol
C-shell (Green Cross) (White C) Superpalite Asphyxiant
D-shell (White D) Phosgene Lethal
(a) Superpalite
Green Cross Asphyxiant
(b) Phenylcarbylaminechloride
Superpalite 65%,
Green Cross 1 Asphyxiant
Chloropicrin 35%
Nature of
Name of Shell Shell Filling
Effect
Superpalite,
Green Cross 2 Phosgene, Asphyxiant
Diphenylchloroarsine
Green Cross 3 Ethyldichloroarsine,
(Yellow Cross 1) Methyldibromoarsine, Asphyxiant
Dichloromethyl ether
K-shell (Yellow) Chloromethylchloroformate Asphyxiant
(Palite)
Xylyl bromide,
T-shell (Black or green T) Lachrymator
Bromo ketone
Mustard gas,
Yellow Cross Vesicant
Diluent (CCl₄, C₆H₅Cl, C₆H₅NO₂)
Yellow Cross 1 See Green Cross 3
CHAPTER III
DEVELOPMENT OF THE CHEMICAL WARFARE
SERVICE
Administration Division
The Administration Division was the result of the development
which has been sketched in the preceding pages. It is not necessary
to review that, but the organization as of October 19, 1918 will be
given:
Director Major General Wm.
L. Sibert
Staff:
Medical Officer Colonel W. J. Lyster
Ordnance Officer Lt. Col. C. B.
Thummel
British Military Mission Major J. H. Brightman
Colonel H. C.
Assistant Director
Newcomer
Office Administration Major W. W. Parker
Relations Section Colonel M. T. Bogert
Personnel Section Major F. E. Breithut
Contracts and Patents Captain W. K.
Section Jackson
Finance Section Major C. C. Coombs
Requirements and Progress Capt. S. M. Cadwell
Section
Confidential Information Major S. P. Mullikin
Section
Captain H. B.
Transportation Section
Sharkey
Training Section Lt. Col. G. N. Lewis
Procurement Section Lt. Col. W. J. Noonan
The administrative offices were located in the Medical
Department Building. The function of most of the sections is
indicated by their names.
The Industrial Relations Section was created to care for the
interests of the industrial plants which were considered as essential
war industries. Through its activity many vitally important industries
were enabled to retain, on deferred classification or on indefinite
furlough, those skilled chemists without which they could not have
maintained a maximum output of war munitions.
In the same way the University Relations Section cared for the
educational and research institutions. In this way our recruiting
stations for chemists were kept in as active operation as war
conditions permitted.
Another important achievement of the Administration Section was
to secure the order from The Adjutant General, dated May 28, 1918,
that read:
“Chemists in Camp
“As the result of the letter from The Adjutant
General of the Army, dated May 28, 1918, 1,749
chemists have been reported on. Of these the report
of action to August 1, 1918, shows that 281 were
ordered to remain with their military organization
because they were already performing chemical
duties, 34 were requested to remain with their
military organization because they were more useful
in the military work which they were doing, 12 were
furloughed back to industry, 165 were not chemists
in the true sense of the word and were, therefore,
ordered back to the line, and 1,294 now placed in
actual chemical work. There were being held for
further investigation of their qualifications on August
1, 1918, 432 men. The remaining 23 men were
unavailable for transfer, because they had already
received their overseas orders.
“The 1,294 men, who would otherwise be
serving in a purely military capacity and whose
chemical training is now being utilized in chemical
work, have, therefore, been saved from waste.
“Each case has been considered individually, the
man’s qualifications and experience have been
studied with care, the needs of the Government
plants and bureaus have been considered with
equal care, and each man has been assigned to the
position for which his training and qualifications
seem to fit him best.
“Undoubtedly, there have been some cases in
which square pegs have been fitted into round
holes, but, on the whole, it is felt that the
adjustments have been as well as could be
expected under the circumstances.”
Research Division
The American University Experiment Station, established by the
Bureau of Mines in April, 1917, became July 1, 1918 the Research
Division of the Chemical Warfare Service. For the first five months
work was carried out in various laboratories, scattered over the
country. In September, 1917, the buildings of the American
University became available; a little later portions of the new
chemical laboratory of the Catholic University, Washington, were
taken over. Branch laboratories were established in many of the
laboratories of the Universities and industrial plants, of which Johns
Hopkins, Princeton, Yale, Ohio State, Massachusetts Institute of
Technology, Harvard, Michigan, Columbia, Cornell, Wisconsin, Clark,
Bryn Mawr, Nela Park and the National Carbon Company were
active all through the war.
At the time of the signing of the armistice the organization of the
Research Division was as follows:
Col. G. A. Burrell Chief of Research Division
Dr. W. K. Lewis In Charge of Defense Problems
Dr. E. P. Kohler[5] In Charge of Offense Problems
Dr. Reid Hunt Advisor on Pharmacological Problems
In Charge of Editorial Work and Catalytic
Lt. Col. W. D. Bancroft
Research
Lt. Col. A. B. Lamb[6] In Charge of Defense Chemical Research
Dr. L. W. Jones[7] In Charge of Offense Chemical Research
Major A. C. Fieldner In Charge of Gas Mask Research
Major G. A. Richter In Charge of Pyrotechnic Research
Capt. E. K. Marshall[8] In Charge of Pharmacological Research
Dr. A. S. Loevenhart[9] In Charge of Toxicological Research
Major R. C. Tolman In Charge of Dispersoid Research
Major W. S. In Charge of Small Scale Manufacture
Rowland[10]
In Charge of Mechanical Research and
Major B. B. Fogler[11] Development
Captain G. A. Rankin In Charge of Explosive Research
Major Richmond In Charge of Administration Section
Levering