Giáo trình The basic practice of statistics 9e by moore

The Basic Practice of Statistics



The Basic Practice of Statistics
Ninth Edition
David S. Moore
Purdue University
William I. Notz
The Ohio State University


Senior Vice President, STEM: Daryl Fox
Program Director, Math, Statistics, Earth Sciences, and Environmental Science: Andrew Dunaway
Program Manager: Sarah Seymour
Executive Content Development Manager, STEM: Debbie Hardin
Development Editor: David Dietz
Executive Project Manager, Content, STEM: Katrina Mangold
Director of Content, Math and Statistics: Daniel Lauve
Executive Media Editor: Catriona Kaplan
Associate Editor: Andy Newton
Assistant Editor: Justin Jones
Marketing Manager: Leah Christians
Marketing Assistant: Morgan Psiuk
Director of Content Management Enhancement: Tracey Kuehn
Senior Managing Editor: Lisa Kinne
Senior Content Project Manager: Edward Dionne
Project Manager: Heidi Allgair, SPi Global
Senior Workflow Project Manager: Paul Rohloff
Production Supervisor: Robert Cherry

Director of Design, Content Management: Diana Blume


Design Services Manager: Natasha Wolfe
Cover Design: Laura de Grasse
Interior Design: Vicki Tomaselli
Art Manager: Matthew McAdams
Director of Digital Production: Keri deManigold
Media Project Manager: Hanna Squire
Executive Permissions Editor: Cecilia Varas
Rights and Billing Editor: Alexis Gargin
Composition: SPi Global
Printing and Binding: LSC Communications
ISBN 978-1-319-38369-5 (ePub)
© 2021, 2018, 2015, 2012 by W. H. Freeman and Company
All rights reserved.
Printed in the United States of America
1 2 3 4 5 6  25 24 23 22 21 20
Macmillan Learning
One New York Plaza
Suite 4600
New York, NY 10004-1562
www.macmillanlearning.com


BRIEF CONTENTS
Chapter 0 Getting Started
Part I Exploring Data
EXPLORING DATA: Variables and Distributions
Chapter 1 Picturing Distributions with Graphs

Chapter 2 Describing Distributions with Numbers
Chapter 3 The Normal Distributions
EXPLORING DATA: Relationships
Chapter 4 Scatterplots and Correlation
Chapter 5 Regression
Chapter 6 Two-Way Tables*
Chapter 7 Exploring Data: Part I Review
Part II Producing Data
PRODUCING DATA
Chapter 8 Producing Data: Sampling
Chapter 9 Producing Data: Experiments
Chapter 10 Data Ethics*
Chapter 11 Producing Data: Part II Review
Part III From Data Production to Inference
PROBABILITY AND SAMPLING DISTRIBUTIONS
Chapter 12 Introducing Probability
Chapter 13 General Rules of Probability*
Chapter 14 Binomial Distributions*
Chapter 15 Sampling Distributions
FOUNDATIONS OF INFERENCE
Chapter 16 Confidence Intervals: The Basics
Chapter 17 Tests of Significance: The Basics
Chapter 18 Inference in Practice
Chapter 19 From Data Production to Inference: Part III Review
Part IV Inference about Variables
QUANTITATIVE RESPONSE VARIABLE
Chapter 20 Inference about a Population Mean
Chapter 21 Comparing Two Means
CATEGORICAL RESPONSE VARIABLE
Chapter 22 Inference about a Population Proportion

Chapter 23 Comparing Two Proportions
Chapter 24 Inference about Variables: Part IV Review
Part V Inference about Relationships
INFERENCE ABOUT RELATIONSHIPS
Chapter 25 Two Categorical Variables: The Chi-Square Test
Chapter 26 Inference for Regression
Chapter 27 One-Way Analysis of Variance: Comparing Several Means


Part VI Optional Companion Chapters
(Available Online)
Chapter 28 Nonparametric Tests
Chapter 29 Multiple Regression*
Chapter 30 Two-Way Analysis of Variance
Chapter 31 Statistical Process Control
Chapter 32 Resampling: Permutation Tests and the Bootstrap
*Starred

material is optional and can be skipped without loss of continuity.


CONTENTS
1.
2.
3.
4.
5.

Why Did You Do That?
Preface

Acknowledgments
About the Authors
1. Chapter 0 Getting Started
1.
2.
3.
4.

0.1 How the Data Were Obtained Matters
0.2 Always Look at the Data
0.3 Variation Is Everywhere
0.4 What Lies Ahead in This Book

6. Part I Exploring Data
1. Chapter 1 Picturing Distributions with Graphs
1.
2.
3.
4.
5.
6.

1.1 Individuals and Variables
1.2 Categorical Variables: Pie Charts and Bar Graphs
1.3 Quantitative Variables: Histograms
1.4 Interpreting Histograms
1.5 Quantitative Variables: Stemplots
1.6 Time Plots

2. Chapter 2 Describing Distributions with Numbers

1.
2.
3.
4.
5.
6.
7.
8.
9.
10.

2.1 Measuring Center: The Mean
2.2 Measuring Center: The Median
2.3 Comparing the Mean and the Median
2.4 Measuring Variability: The Quartiles
2.5 The Five-Number Summary and Boxplots
2.6 Spotting Suspected Outliers and Modified Boxplots*
2.7 Measuring Variability: The Standard Deviation
2.8 Choosing Measures of Center and Variability
2.9 Examples of Technology
2.10 Organizing a Statistical Problem

3. Chapter 3 The Normal Distributions
1.
2.
3.
4.

3.1 Density Curves
3.2 Describing Density Curves

3.3 Normal Distributions
3.4 The 68–95–99.7 Rule


5.
6.
7.
8.

3.5 The Standard Normal Distribution
3.6 Finding Normal Proportions
3.7 Using the Standard Normal Table
3.8 Finding a Value Given a Proportion

4. Chapter 4 Scatterplots and Correlation
1.
2.
3.
4.
5.
6.

4.1 Explanatory and Response Variables
4.2 Displaying Relationships: Scatterplots
4.3 Interpreting Scatterplots
4.4 Adding Categorical Variables to Scatterplots
4.5 Measuring Linear Association: Correlation
4.6 Facts about Correlation

5. Chapter 5 Regression

1.
2.
3.
4.
5.
6.
7.
8.
9.

5.1 Regression Lines
5.2 The Least-Squares Regression Line
5.3 Examples of Technology
5.4 Facts about Least-Squares Regression
5.5 Residuals
5.6 Influential Observations
5.7 Cautions about Correlation and Regression
5.8 Association Does Not Imply Causation
5.9 Correlation, Prediction, and Big Data*

6. Chapter 6 Two-Way Tables*
1. 6.1 Marginal Distributions
2. 6.2 Conditional Distributions
3. 6.3 Simpson’s Paradox
7. Chapter 7 Exploring Data: Part I Review
1.
2.
3.
4.

Part I Skills Review
Test Yourself
Supplementary Exercises
Online Data for Additional Analyses

7. Part II Producing Data
1. Chapter 8 Producing Data: Sampling
1. 8.1 Population versus Sample
2. 8.2 How to Sample Badly
3. 8.3 Simple Random Samples


4.
5.
6.
7.

8.4 Trustworthiness of Inference from Samples
8.5 Other Sampling Designs
8.6 Cautions about Sample Surveys
8.7 The Impact of Technology

2. Chapter 9 Producing Data: Experiments
1.
2.
3.
4.
5.
6.
7.

9.1 Observation Versus Experiment
9.2 Subjects, Factors, and Treatments
9.3 How to Experiment Badly
9.4 Randomized Comparative Experiments
9.5 The Logic of Randomized Comparative Experiments
9.6 Cautions About Experimentation
9.7 Matched Pairs and Other Block Designs

3. Chapter 10 Data Ethics*
1.
2.
3.
4.
5.

10.1 Institutional Review Boards
10.2 Informed Consent
10.3 Confidentiality
10.4 Clinical Trials
10.5 Behavioral and Social Science Experiments

4. Chapter 11 Producing Data: Part II Review
1. Part II Skills Review
2. Test Yourself
3. Supplementary Exercises
8. Part III From Data Production to Inference
1. Chapter 12 Introducing Probability
1.
2.

3.
4.
5.
6.
7.
8.

12.1 The Idea of Probability
12.2 The Search for Randomness*
12.3 Probability Models
12.4 Probability Rules
12.5 Finite Probability Models
12.6 Continuous Probability Models
12.7 Random Variables
12.8 Personal Probability*

2. Chapter 13 General Rules of Probability*
1. 13.1 The General Addition Rule
2. 13.2 Independence and the Multiplication Rule


3.
4.
5.
6.
7.

13.3 Conditional Probability
13.4 The General Multiplication Rule
13.5 Showing That Events Are Independent

13.6 Tree Diagrams
13.7 Bayes’ Rule*

3. Chapter 14 Binomial Distributions*
1.
2.
3.
4.
5.
6.

14.1 The Binomial Setting and Binomial Distributions
14.2 Binomial Distributions in Statistical Sampling
14.3 Binomial Probabilities
14.4 Examples of Technology
14.5 Binomial Mean and Standard Deviation
14.6 The Normal Approximation to Binomial Distributions

4. Chapter 15 Sampling Distributions
1.
2.
3.
4.
5.
6.

15.1 Parameters and Statistics
15.2 Statistical Estimation and the Law of Large Numbers
15.3 Sampling Distributions
15.4 The Sampling Distribution of x¯

15.5 The Central Limit Theorem
15.6 Sampling Distributions and Statistical Significance*

5. Chapter 16 Confidence Intervals: The Basics
1.
2.
3.
4.

16.1 The Reasoning of Statistical Estimation
16.2 Margin of Error and Confidence Level
16.3 Confidence Intervals for a Population Mean
16.4 How Confidence Intervals Behave

6. Chapter 17 Tests of Significance: The Basics
1.
2.
3.
4.
5.

17.1 The Reasoning of Tests of Significance
17.2 Stating Hypotheses
17.3 P-Value and Statistical Significance
17.4 Tests for a Population Mean
17.5 Significance from a Table*

7. Chapter 18 Inference in Practice
1.
2.

3.
4.
5.

18.1 Conditions for Inference in Practice
18.2 Cautions about Confidence Intervals
18.3 Cautions about Significance Tests
18.4 Planning Studies: Sample Size for Confidence Intervals
18.5 Planning Studies: The Power of a Statistical Test of Significance*


8. Chapter 19 From Data Production to Inference: Part III Review
1. Part III Skills Review
2. Test Yourself
3. Supplementary Exercises
9. Part IV Inference about Variables
1. Chapter 20 Inference about a Population Mean
1.
2.
3.
4.
5.
6.
7.

20.1 Conditions for Inference about a Mean
20.2 The t Distributions
20.3 The One-Sample t Confidence Interval
20.4 The One-Sample t Test
20.5 Examples of Technology

20.6 Matched Pairs t Procedures
20.7 Robustness of t Procedures

2. Chapter 21 Comparing Two Means
1.
2.
3.
4.
5.
6.
7.
8.

21.1 Two-Sample Problems
21.2 Comparing Two Population Means
21.3 Two-Sample t Procedures
21.4 Examples of Technology
21.5 Robustness Again
21.6 Details of the t Approximation*
21.7 Avoid the Pooled Two-Sample t Procedures*
21.8 Avoid Inference about Standard Deviations*

3. Chapter 22 Inference about a Population Proportion
1.
2.
3.
4.
5.

22.1 The Sample Proportion p^

22.2 Large-Sample Confidence Intervals for a Proportion
22.3 Choosing the Sample Size
22.4 Significance Tests for a Proportion
22.5 Plus Four Confidence Intervals for a Proportion*

4. Chapter 23 Comparing Two Proportions
1.
2.
3.
4.
5.
6.

23.1 Two-Sample Problems: Proportions
23.2 The Sampling Distribution of a Difference between Proportions
23.3 Large-Sample Confidence Intervals for Comparing Proportions
23.4 Examples of Technology
23.5 Significance Tests for Comparing Proportions
23.6 Plus Four Confidence Intervals for Comparing Proportions*


5. Chapter 24 Inference about Variables: Part IV Review
1. Part IV Skills Review
2. Test Yourself
3. Supplementary Exercises
10. Part V Inference about Relationships
1. Chapter 25 Two Categorical Variables: The Chi-Square Test
1.
2.
3.

4.
5.
6.
7.
8.
9.

25.1 Two-Way Tables
25.2 The Problem of Multiple Comparisons
25.3 Expected Counts in Two-Way Tables
25.4 The Chi-Square Statistic
25.5 Examples of Technology
25.6 The Chi-Square Distributions
25.7 Cell Counts Required for the Chi-Square Test
25.8 Uses of the Chi-Square Test: Independence and Homogeneity
25.9 The Chi-Square Test for Goodness of Fit*

2. Chapter 26 Inference for Regression
1.
2.
3.
4.
5.
6.
7.
8.

26.1 Conditions for Regression Inference
26.2 Estimating the Parameters
26.3 Examples of Technology

26.4 Testing the Hypothesis of No Linear Relationship
26.5 Testing Lack of Correlation
26.6 Confidence Intervals for the Regression Slope
26.7 Inference about Prediction
26.8 Checking the Conditions for Inference

3. Chapter 27 One-Way Analysis of Variance: Comparing Several Means
1. 27.1 Comparing Several Means
2. 27.2 The Analysis of Variance F Test
3. 27.3 Using Technology
4. 27.4 The Idea of Analysis of Variance
5. 27.5 Conditions for ANOVA
6. 27.6 F Distributions and Degrees of Freedom
7. 27.7 Follow-up Analysis: Tukey Pairwise Multiple Comparisons
8. 27.8 Some Details of ANOVA*
11. Notes and Data Sources
12. Tables
TABLE A Standard Normal Cumulative Proportions
TABLE B Random Digits
TABLE C t Distribution Critical Values
TABLE D Chi-Square Distribution Critical Values


TABLE E Critical Values of the Correlation r
13. Answers to Selected Exercises
14. Index
15. Part VI Optional Companion Chapters
(Available Online)
1. Chapter 28 Nonparametric Tests
1.

2.
3.
4.
5.
6.
7.
8.
9.
10.
11.

28.1 Comparing Two Samples: The Wilcoxon Rank Sum Test
28.2 The Normal Approximation for W
28.3 Examples of Technology
28.4 What Hypotheses Does Wilcoxon Test?
28.5 Dealing with Ties in Rank Tests
28.6 Matched Pairs: The Wilcoxon Signed Rank Test
28.7 The Normal Approximation for W+
28.8 Dealing with Ties in the Signed Rank Test
28.9 Comparing Several Samples: The Kruskal–Wallis Test
28.10 Hypotheses and Conditions for the Kruskal–Wallis Test
28.11 The Kruskal–Wallis Test Statistic

2. Chapter 29 Multiple Regression*
1.
2.
3.
4.
5.
6.

7.
8.
9.
10.
11.

29.1 Adding a Categorical Variable in Regression
29.2 Estimating Parameters
29.3 Examples of Technology
29.4 Inference for Multiple Regression
29.5 Interaction
29.6 A Model with Two Regression Lines
29.7 The General Multiple Linear Regression Model
29.8 Correlations between Explanatory Variables
29.9 A Case Study for Multiple Regression
29.10 Inference for Regression Parameters
29.11 Checking the Conditions for Inference

3. Chapter 30 Two-Way Analysis of Variance
1.
2.
3.
4.

30.1 Beyond One-Way ANOVA
30.2 Two-Way ANOVA: Conditions, Main Effects, and Interaction
30.3 Inference for Two-Way ANOVA
30.4 Some Details of Two-Way ANOVA*

4. Chapter 31 Statistical Process Control

1. 31.1 Processes


2.
3.
4.
5.
6.
7.
8.
9.
10.
11.

31.2 Describing Processes
31.3 The Idea of Statistical Process Control
31.4 x¯ Charts for Process Monitoring
31.5 s Charts for Process Monitoring
31.6 Using Control Charts
31.7 Setting Up Control Charts
31.8 Comments on Statistical Control
31.9 Don’t Confuse Control with Capability
31.10 Control Charts for Sample Proportions
31.11 Control Limits for p Charts

5. Chapter 32 Resampling: Permutation Tests and the Bootstrap
1.
2.
3.
4.

*Starred

32.1 Randomization in Experiments as a Basis for Inference
32.2 Permutation Tests for Two Treatments with Software
32.3 Generating Bootstrap Samples
32.4 Bootstrap Standard Errors and Confidence Intervals

material is optional and can be skipped without loss of continuity.


WHY DID YOU DO THAT?
The Authors Answer Questions about The Basic Practice of Statistics
Welcome to the ninth edition of The Basic Practice of Statistics. As the title suggests, this text
provides an introduction to the practice of statistics that aims to equip students to carry out common
statistical procedures and to follow statistical reasoning in their fields of study and in their future
employment.
There is no single best way to organize our presentation of statistics to beginners. That said, our
choices reflect thinking about both content and pedagogy. Here are comments on several frequently
asked questions about the order and selection of material in The Basic Practice of Statistics.

Why Did You Write The Basic Practice of Statistics?
Several factors influenced the writing of The Basic Practice of Statistics. Easy-to-use statistical
software with graphical tools made it possible for students to explore and analyze data on their own.
Statistics educators recognized that actually doing statistics—exploring data, analyzing data, thinking
about what the data are telling us, and assessing the validity of the conclusions we make from data—
is an effective way to learn statistics. Teachers also recognized the importance of using real data
from actual studies to reinforce the fact that statistics is invaluable for answering real-world
questions. Finally, an introductory course in statistics should expose students to how statistics is
actually practiced by researchers. At the time of the writing of the first edition, few, if any, textbooks
for courses intended for students with only college algebra as the mathematics prerequisite

incorporated these ideas.
With this in mind, The Basic Practice of Statistics was designed to reflect the actual practice of
statistics, where data analysis and design of data production join with probability-based inference to
form a coherent science of data. The Basic Practice of Statistics was also designed to be accessible
to college and university students with limited quantitative background—just “algebra” in the sense of
being able to read and use simple equations.

Why Should I Use The Basic Practice of Statistics to Teach an
Introductory Statistics Course?
The Basic Practice of Statistics is based on three principles: balanced content, experience with data,
and the importance of ideas. These principles are widely accepted by statisticians concerned about
teaching and are directly connected to and reflected by the themes of the College Report of the
Guidelines in Assessment and Instruction for Statistics Education (GAISE) Project.


The GAISE guidelines include six recommendations for introductory statistics. The content, coverage,
and features of The Basic Practice of Statistics are closely aligned to these recommendations:
1. Teach statistical thinking.
Teach statistics as an investigative process of problem solving and decision making. In
The Basic Practice of Statistics, we present a four-step process for solving statistical
problems. This begins by stating the practical question to be answered in the context of a
real-world setting and ends with a practical conclusion, often a decision to be made, in the
setting of the real-world problem. The process is illustrated in the text by revisiting data
from a study in a series of examples or exercises. Different aspects of the data are
investigated in different examples and exercises, with the ultimate goal of making some
decision based on what has been learned.
Give students experience with multivariable thinking. The Basic Practice of Statistics
exposes students to multivariate thinking early in the book. Chapters 4, 5, and 6 introduce
students to methods for exploring bivariate data. In Chapter 7, we include online data with
many variables, inviting students to explore aspects of these data. In Chapter 9, we discuss

the importance of identifying the many variables that can affect a response and including
them in the design of an experiment and the interpretation of the results. In Part V, we
introduce students to formal methods of inference for bivariate data, and in the online
supplemental chapters, we discuss multiple regression, two-way ANOVA, and statistical
process control.
2. Focus on conceptual understanding. A first course in statistics introduces many skills, from
making a stemplot and calculating a correlation to choosing and carrying out a significance test.
In practice (even if not always in the course), calculations and graphs are automated. Moreover,
anyone who makes serious use of statistics will need some specific procedures not taught in
their college statistics course. The Basic Practice of Statistics, therefore, emphasizes
conceptual understanding by making clear the larger patterns and big ideas of statistics—not in
the abstract but in the context of learning specific skills and working with specific data. Many of
the big ideas are summarized in graphical outlines. Three of the most useful of these appear
opposite the title page. Formulas without guiding principles do students little good once the final
exam is past, so it is worth the time to slow down a bit and explain the ideas.
3. Integrate real data with a context and a purpose. The study of statistics is supposed to help
students work with data in their varied academic disciplines and in their unpredictable later
employment. Students learn to work with data by working with data. The Basic Practice of
Statistics is full of data from many fields of study and from everyday life. Data are more than
mere numbers: they are numbers with a context that should play a role in making sense of the
numbers and in stating conclusions. Examples and exercises in The Basic Practice of Statistics,
though intended for beginners, use real data and give enough background to allow students to
consider the meaning of their calculations.
4. Foster active learning. Fostering active learning is the business of the teacher, though an
emphasis on working with data helps. To this end, we have created interactive applets to our


specifications that are available online. These are designed primarily to help in learning
statistics rather than in doing statistics. We suggest using selected applets for classroom
demonstrations even if you do not ask students to work with them. The Correlation and

Regression, Confidence Intervals, and P-Value of a Test of Significance applets, for example,
convey core ideas more clearly than any amount of chalk and talk.
For each chapter (except the review chapters), web exercises are provided online. Our intent is
to take advantage of the fact that most undergraduates are web savvy. These exercises require
students to search the web for either data or statistical examples and then evaluate what they
find. Teachers can use these as classroom activities or assign them as homework projects.
5. Use technology to explore concepts and analyze data. Automating calculations increases
students’ ability to complete problems, reduces their frustration, and helps them concentrate on
ideas and problem recognition rather than mechanics. At a minimum, students should have a
“two-variable statistics” calculator with functions for correlation and the least-squares
regression line as well as for the mean and standard deviation.
Many instructors will take advantage of more elaborate technology, as ASA/MAA and GAISE
recommend. And many students who don’t use technology in their college statistics course will
find themselves using (for example) Excel on the job. The Basic Practice of Statistics does not
assume or require use of software except in Part V, where the work is otherwise too tedious. It
does accommodate software use and provides students with knowledge that will enable them to
read and use output from almost any source. There are regular “Examples of Technology”
sections throughout the text. Each of these sections displays and comments on output from the
same three technologies, representing graphing calculators (the Texas Instruments TI-83 or TI84), spreadsheets (Microsoft Excel), and statistical software (JMP, Minitab, R, and CrunchIt!).
The output always concerns one of the main teaching examples so that students can compare text
and output.
6. Use assessments to improve and evaluate student learning. Within chapters, a few “Apply
Your Knowledge” exercises follow each new idea or skill for a quick check of basic mastery—
and also to mark off digestible bites of material. Each of the first four parts of the book ends
with a review chapter that includes a point-by-point outline of skills learned, problems students
can use to test themselves, and several supplementary exercises. (Instructors can choose to cover
any or none of the chapters in Part V, so each of these chapters includes a skills outline.) The
review chapters present supplemental exercises without the “I just studied that” context, thus
asking for another level of learning. We think it is helpful to assign some supplemental
exercises. Many instructors will find that the review chapters appear at the right points for preexam review. Students can use the “Test Yourself” questions to review, self-assess, and prepare

for exams. In addition, assessment materials in the form of a test bank and quizzes are available
online.

Why Did You Choose to Order Topics as Listed in the Book?


There are good pedagogical reasons for beginning with data analysis (Chapters 1 through 7), then
moving to data production (Chapters 8 through 11), and then to probability and inference (Chapters
12 through 27). In studying data analysis, students learn useful skills immediately and get over some
of their fear of statistics. Data analytics is much in the media these days, and by discussing data
analysis, instructors can link the course material to the current interest in data analytics. Data analysis
is a necessary preliminary to inference in practice because inference requires clean data. Designed
data production is the surest foundation for inference, and the deliberate use of chance in random
sampling and randomized comparative experiments motivates the study of probability in a course that
emphasizes data-oriented statistics. The Basic Practice of Statistics gives a full presentation of basic
probability and inference (16 of the 27 chapters in the printed text) but places it in the context of
statistics as a whole.


Why Does the Distinction between Population and Sample Not
Appear in Part I?
There is more to statistics than inference. In fact, statistical inference is appropriate only in rather
special circumstances. The chapters in Part I present tools and tactics for describing data—any data.
These tools and tactics do not depend on the idea of inference from sample to population. Many data
sets in these chapters (for example, the several sets of data about the 50 states) do not lend
themselves to inference because they represent an entire population. Likewise, many modern big data
sets are also viewed as information about an entire population, for which formal inference may not be
appropriate. John Tukey of Bell Labs and Princeton, the philosopher of modern data analysis, insisted
that the population–sample distinction be avoided when it is not relevant. He used the word batch for
data sets in general. We see no need for a special word, but we think Tukey was right.

Why Not Begin with Data Production?
We prefer to begin with data exploration (Part I), as most students will use statistics mainly in
settings other than planned research studies in their future employment. We place the design of data
production (Part II) after data analysis to emphasize that data-analytic techniques apply to any data.
However, it is equally reasonable to begin with data production; the natural flow of a planned study
is from design to data analysis to inference. Because instructors have strong and differing opinions on
this question, these two topics are now the first two parts of the book, with the text written so that it
may be started with either Part I or Part II while maintaining the continuity of the material.
Another reason for beginning with data exploration is to give students experience exploring data and
thinking about how to interpret what they discover. This experience provides a context for how data
production affects the reliability of conclusions one might draw from data.


Why Do Normal Distributions Appear in Part I?
Density curves such as the Normal curves are just another tool to describe the distribution of a
quantitative variable, along with stemplots, histograms, and boxplots. Professional statistical
software offers to make density curves from data just as it offers histograms. We prefer not to suggest
that this material is essentially tied to probability, as the traditional order does. And we find it helpful
to break up the indigestible lump of probability that troubles students so much. Meeting Normal
distributions early does this and strengthens the “probability distributions are like data distributions”
way of approaching probability when we get there.

Why Not Delay Correlation and Regression Until Late in the
Course, as Was Traditional?
The Basic Practice of Statistics begins by offering experience working with data and gives a
conceptual structure for this nonmathematical, but essential, part of statistics. Students profit from
more experience with data early and from seeing the conceptual structure worked out in relationships
among variables as well as in describing single-variable data. Correlation and least-squares
regression are very important descriptive tools and are often used in settings where there is no

population–sample distinction, such as studies of all of a firm’s employees. Perhaps most
importantly, The Basic Practice of Statistics asks students to think about what kind of relationship
lies behind the data (confounding, lurking variables, association not implying causation, and so on)
without overwhelming them with the demands of formal inference methods. Inference in the
correlation and regression setting is a bit complex, demands software, and often comes right at the
end of the course. We find that delaying all mention of correlation and regression to that point often
means that students don’t master the basic uses and properties of these methods. We consider
Chapters 4 and 5 (correlation and regression) essential and Chapter 26 (regression inference)
optional.

Why Use the z Procedures for a Population Mean to Introduce the
Reasoning of Inference?
This is a pedagogical issue, not a question of statistics in practice. The two most popular choices for
introducing inference are z for a mean and z for a proportion. (Another option is resampling and
permutation tests. We have included material on these topics but have not used them to introduce
inference.)
We find z for means quite accessible to students. Positively, we can say up front that we are going to
explore the reasoning of inference in the overly simple setting described in the box on page 367 titled
“Simple Conditions for Inference about a Mean.” As this box suggests, assuming an exactly Normal
population and a true simple random sample are as unrealistic as known s. All the issues of practice
—robustness against lack of Normality and application when the data aren’t an SRS as well as the


need to estimate s—are put off until, with the reasoning in hand, we discuss the practically useful t
procedures. This separation of initial reasoning from messier practice works well.
Negatively, starting with inference for p introduces many side issues: no exact Normal sampling
distribution but a Normal approximation to a discrete distribution; use of p^ in both the numerator and
denominator of the test statistic to estimate both the parameter p and p^’s own standard deviation;
loss of the direct link between test and confidence interval; and the need to avoid small and moderate
sample sizes because the Normal approximation for the test is quite unreliable.

There are advantages to starting with inference for p. Starting with z for means takes a fair amount of
time, and the ideas need to be rehashed with the introduction of the t procedures. Many instructors
face pressure from client departments to cover a large amount of material in a single semester.
Eliminating coverage of the “unrealistic” z for means with known variance enables instructors to
cover additional, more realistic applications of inference. Also, many instructors believe that
proportions are simpler and more familiar to students than means.

Why Didn’t You Cover Topic X?
Introductory texts ought not to be encyclopedic. We chose topics on two grounds: they are the most
commonly used in practice, and they are suitable vehicles for learning broader statistical ideas.
Students who have completed the core of the book, Chapters 1 through 12 and 15 through 24, will
have little difficulty moving on to more elaborate methods. Chapters 25 through 27 offer a choice of
slightly more advanced topics, as do the optional supplemental chapters, available online.

Why Are Some Chapters and Sections Listed as Optional?
Many users have requested that we include the content listed as optional. However, as noted above,
many instructors face pressure from client departments to cover many topics in a single semester. We
have identified some material that can safely be omitted because it is not required for later parts of
the book. Instructors can cover this optional content if they wish, but they can also omit it in order to
cover topics that client departments have requested.
The content we designate as optional is not less important than other material in the book. For
example, many instructors will want to cover Chapters 6 and 25 because they consider relationships
between categorical variables an essential topic for their students.
We have enjoyed the opportunity to once again rethink how to help beginning students achieve a
practical grasp of basic statistics. What students actually learn is not identical to what we teachers
think we have “covered,” so the virtues of concentrating on the essentials are considerable. We hope
this new edition of The Basic Practice of Statistics offers a mix of concrete skills and clearly
explained concepts that will help many teachers guide their students toward useful knowledge.

PREFACE
 
Empowering Problem Solving and Real-World Decision Making
Now available with Macmillan’s new, ground-breaking online learning platform Achieve, the ninth
edition of The Basic Practice of Statistics teaches statistical thinking through an investigative
process of problem solving with pedagogy designed to help students of all levels. Examples and
exercises from a wide variety of topic areas use current, real data to provide students with insight
into how data is used to make decisions in the real world.
Achieve for The Basic Practice of Statistics connects the book’s trusted Four-Step problem-solving
approach and real-world examples to rich digital resources that foster understanding and facilitate the
practice of statistics. The tools in Achieve support learning before, during, and after class for students
and equip instructors with class performance analytics in an easy-to-use interface.

Overview of key features
Support for Learners on Every Page
Four-Step Problem-Solving examples guide students through the Four-Step process for working
through statistical problems: State, Plan, Solve, Conclude. Students are instructed to apply this
process in designated exercises.
Apply Your Knowledge exercises at the end of each section encourage students to read actively
and to cement new concepts by applying them as they learn.
Examples of Technology, located where most appropriate, display and comment on the output
from popular statistical software applications (notably Excel, Minitab, JMP, and R) and TI
83/84 graphing calculators in the context of worked examples. Students learn to interpret output
from any standard statistical package.
Definition and Theorem Boxes in the text alert students to key concepts, terms, and procedures.
Caution Boxes warn students of common mistakes or misconceptions.
Statistics in Your World margin notes further connect statistics topics to the real world,
highlighting interesting examples and applications from a variety of fields.
The main themes of the text are strongly aligned to the GAISE guidelines (from the Guidelines
in Assessment and Instruction in Statistics Education College Report).

New to the Ninth Edition
Examples and exercises clearly emphasize reaching conclusions and making decisions based
on data exploration and statistical inference.
Chapter Summaries are in concise list form, and Skills Reviews (in Review Chapters) refer to
relevant chapter sections to help students check their knowledge and review for exams.
Data in examples and exercises have been updated for relevance, and new examples and
exercises explore contemporary issues such as social media usage.
Displayed in boldface type, key terms are clearly defined in running text or in the margin, to
build understanding without focusing on vocabulary.

Highlight Four-Step Problem-Solving
Expanded in the Ninth Edition

Equips Students to Solve Complex Statistical Problems
Recognizing which approach to take and how to get started on a problem are often challenging for
statistics students. David Moore and William Notz reduce student stress and support learning by using
a problem-solving framework throughout The Basic Practice of Statistics.

The process is as follows. State: What is the practical question, in the context of the real-world
setting? Plan: What specific statistical operations does this problem call for? Solve: Make the graphs
and carry out the calculations needed for this problem. Conclude: Give your practical conclusion in
the setting of the real-world problem.