STATS
MODELING THE WORLD
SIXTH EDITION
David E. Bock
Floyd Bullard
Paul F. Velleman
Richard D. De Veaux
,TABLE OF CONTENTS
1. Stats Starts Here
2. Displaying and Describing Categorical Data
3. Displaying and Summarizing Quantitative Data
4. Understanding and Comparing Distributions
5. The Standard Deviation as a Ruler and the Normal Model
6. Scatterplots, Association, and Correlation
7. Linear Regression
8. Regression Wisdom
9. Re-expressing Data: Get It Straight!
10. Understanding Randomness
11. Sample Surveys
12. Experiments and Observational Studies
13. From Randomness to Probability
14. Probability Rules!
15. Random Variables
16. Probability Models
17. Sampling Distribution Models
18. Confidence Intervals for Proportions
19. Testing Hypotheses About Proportions
20. More About Tests and Intervals
21. Comparing Two Proportions
22. Inferences About Means
23. Comparing Means
24. Paired Samples and Blocks
25. Comparing Counts
26. Inferences for Regression
Part I: Exploring and Understanding Data:
This Part of the book covers data displays and summaries. Many students will recognize some of
the material from middle and high school, so our emphasis is on statistical thinking. Of course, we
define terms and provide examples. But we also discuss why methods presented are used, and
what we hope to learn from them. These are concepts that appear throughout the course. Even
more important than what to look for in a histogram or how to summarize the spread of a
distribution is the underlying lesson that there are reasons for displaying and summarizing data.
These reasons inform and motivate the entire course.
, 1-1
Chapter 1
Stats Starts Here
What’s it about?
This chapter is about Statistics – what it is and why we care. It also describes the important
features of the text. We’ve given the chapter an unusual title and tried to grab students’ attention
with a humorous footnote. (Some have e-mailed us to assure us that they do read the footnotes.)
If we can get them to read three words and the footnote, maybe we can get them to read on.
We then introduce students to data. We talk about the importance of context (the W’s), about
variables, and make the distinction between categorical and quantitative data. We begin to
introduce the vocabulary of Statistics. And the TI Tips section shows students how to enter data
into the calculator’s lists.
Comments
Do expect your students to read the book. Give them specific reading assignments, starting with
this first chapter. We’ve tried to make the book engaging. You can assign a few pages of reading
along with some problems each night.
This is the students’ first look at the style of the book, and we do lay it on more heavily here than
we will when discussing, say, confidence intervals. We want to shake things up. We want them
to notice that this is not the same old math or science textbook they’ve seen before. And we’d
like to get them on our side. That’s the reason for the humor and self-deprecating remarks.
Every Statistics text starts with a definition of Statistics. We do too, but ours is different. And the
difference matters. We say that Statistics is a way of reasoning and that the goal is to help us
understand the world. We’ve found it helpful to reinforce this idea throughout the semester,
especially when we get into the methods sections of the course. This book is first and primarily
about statistical thinking. Methods, definitions, and skills are all here, but each is presented with
the purpose of understanding the world. That’s why every example follows the Think, Show, Tell
pattern, starting with careful reasoning and concluding with a sentence or two telling what we’ve
learned about the world.
It is easy to be drawn into a focus on definitions, on algorithms, and on getting the “right
answer.” Those are easier to teach and certainly easier to grade. Please resist the temptation. If
you can help your students to stay focused on statistical thinking and understanding, this course
can change the way they view the world.
, 1-2 Part I Exploring and Understanding Data
Get students involved with data from the start. We don’t take a “big picture” approach at this
time. There will be plenty of time to build models and draw inferences later. For now, let’s just
get our hands dirty playing with the data. When students have a good sense of what kinds of
things data can say to us, they learn to expect to listen to the data. Throughout the course, we
insist that no analysis of data is complete without telling what it means. This is where that
understanding starts.
Rather than head directly for the “real purpose” of the course in the inference chapters, we prefer
to emphasize the connection between our work with data and what they tell us about the world.
No analysis (and no AP* Part II answer) is complete without a connection back to the real-world
circumstances. Setting that stage is the underlying motivation for this chapter. We’ll spend the
next 10 chapters or so looking at and exploring data without making formal inferences.
Looking Ahead
Most of our own students actually do the reading. (Yes, we were surprised at first.) If you can
hook students on reading the text, there are big benefits later on. As they read they learn that the
book is a valuable resource to help them understand sticky concepts, to help lead them through
writing complete and clear solutions, and to help them avoid common mistakes. Many find that
they can easily catch up after absences by reading the relevant chapters on their own.
Technology plays an important role in this book. We expect students to use a calculator or
computer statistics package for finding the numerical “answers.” So we won’t spend much time
worrying about the calculation details, although we do expect them to understand what’s
happening. Instead, we focus on understanding and meaning. But the book is “technology
neutral.” The “computer output” in the book is designed to look like the results of many
statistical packages, but exactly match none of them. Students should feel comfortable using
output from almost any statistics program or graphing calculator.
You might have the students thumb through the book and read the opening of some chapters.
Each one starts with a story and data, and most have additional stories and more data inside.
Statistics is about the real world. Among other topics, we’ll be discussing how well we can
predict hurricane tracks, whether generic batteries perform as well as their brand name
competitors, the debate about the safety of a widely used drug, and whether or not people over
30 snore more. We need to get students thinking about the context of data and able to make the
distinction between categorical and quantitative data. These are fundamental skills for everything
that follows, and they’ll be used throughout the course.
We also want students to discover how helpful the TI Tips are. If you can get them to follow
these instructions in each chapter you won’t need to spend much class time helping with button-
pushing, and students will be up to speed for the tests. If you use computer software in addition
to calculators, you may want to give students a customized handout to get them started in your
school’s particular computing environment.
Class Do’s
One of our favorite definitions says “Statistics is the art of distilling meaning from data.” Data
have a story to tell. Our objective is to uncover that story. Collect some data in class, and ask
students to look for interesting facts hiding there.