WILLIAM CRAINE III - Chapter 2 Displaying and Describing Data 7 Cha...

SOLUTIONS

MANUAL

WILLIAM CRAINE III

INTRO STATS

F

IFTH EDITION

Richard De Veaux Paul Velleman David Bock 1 / 4

Contents

Chapter 1 Stats Starts Here 1 Chapter 2 Displaying and Describing Data 7 Chapter 3 Relationships Between Categorical Variables -Contingency Tables 17 Chapter 4 Understanding and Comparing Distributions 35 Chapter 5 The Standard Deviation as Ruler and the Normal Model 53 Review of Part I Exploring and Understanding Data 78

Chapter 6 Scatterplots, Association, and Correlation 97 Chapter 7 Linear Regression 112 Chapter 8 Regression Wisdom 145 Chapter 9 Multiple Regression 182 Review of Part II Exploring Relationships Between Variables 190

Chapter 10 Sample Surveys 216 Chapter 11 Experiments and Observational Studies 227 Review of Part III Gathering Data 245

Chapter 12 From Randomness to Probability 257 Chapter 13 Sampling Distribution Models and Confidence Intervals for Proportions 283 Chapter 14 Inferences About Means 301 Chapter 15 Testing Hypotheses 327 Chapter 16 More About Tests and Intervals 359 Review of Part IV From the Data at Hand to the World at Large 375

Chapter 17 Comparing Groups 403 Chapter 18 Paired Samples and Blocks 451 Chapter 19 Comparing Counts 472 Chapter 20 Inferences for Regression 497 Review of Part V Inference for Relationships 524

Parts I – V

Cumulative Review Exercises 566

• / 4

Chapter 1 Stats Starts Here 1 Copyright © 2018 Pearson Education, Inc.Chapter 1 – Stats Starts Here Section 1.1

• Grocery shopping. Discount cards at grocery stores allow the stores to collect information

about the products that the customer purchases, what other products are purchased at the same time, whether or not the customer uses coupons, and the date and time that the products are purchased. This information can be linked to demographic information about the customer that was volunteered when applying for the card, such as the customer’s name, address, sex, age, income level, and other variables. The grocery store chain will use that information to better market their products. This includes everything from printing out coupons at the checkout that are targeted to specific customers to deciding what television, print, or Internet advertisements to use.

• Online shopping. Amazon hopes to gain all sorts of information about customer behavior,

such as how long they spend looking at a page, whether or not they read reviews by other customers, what items they ultimately buy, and what items are bought together. They can then use this information to determine which other products to suggest to customers who buy similar items, to determine which advertisements to run in the margins, and to determine which items are the most popular so these items come up first in a search.

• Parking lots. The owners of the parking garage can advertise about the availability of parking.

They can also communicate with businesses about hours when more spots are available and when they should encourage more business.

• Satellites and global climate change. This rise and fall of temperature and water levels can

help in planning for future problems and guide public policy to protect our safety.Section 1.2

• Super Bowl. When collecting data about the Super Bowl, the games themselves are the Who.
• Nobel laureates. Each year is a case, holding all of the information about that specific year.

Therefore, the year is the Who.

• Health records. The sample is about 5,000 people, and the population is all residents of the

United States of America. The Who is the selected subjects and the What includes medical, dental, and physiological measurements and laboratory test results.

• Facebook. The Who is the 350 million photos. The What might be information about the photos,

for example: file format, file size, time and date when uploaded, people and places tagged, and GPS information. 3 / 4

• Part I Exploring and Understanding Data

Copyright © 2018 Pearson Education, Inc.Section 1.3

• Grade level.

a) If we are, for example, comparing the percentage of first-graders who can tie their own

shoes to the percentage of second-graders who can tie their own shoes, grade-level is treated as categorical. It is just a way to group the students. We would use the same methods if we were comparing boys to girls or brown-eyed kids to blue-eyed kids.

b) If we were studying the relationship between grade-level and height, we would be treating

grade level as quantitative.

• ZIP codes.

a) ZIP codes are categorical in the sense that they correspond to a location. The ZIP code

14850 is a standardized way of referring to Ithaca, NY.

b) ZIP codes generally increase as the location gets further from the east coast of the United

States. For example, one of the ZIP codes for the city of Boston, MA is 02101. Kansas City, MO has a ZIP code of 64101, and Seattle, WA has a ZIP code of 98101.

• Voters. The response is a categorical variable.
• Job hunting. The answer is a categorical variable.
• Medicine. The company is studying a quantitative variable.
• Stress. The researcher is studying a quantitative variable.

Section 1.4

• Voting and elections. Pollsters might consider whether a person voted previously or whether

he or she could name the candidates. Voting previously and knowing the candidates may indicate a greater interest in the election.

• Weather. Meteorologists can use the models to predict the average temperature ten days in

advance and compare their predictions to the actual temperatures.

• The News. Answers will vary.
• The Internet. Answers will vary.
• Gaydar. Who – 40 undergraduate women. What – Whether or not the women could identify

the sexual orientation of men based on a picture. Population of interest – All women.

• / 4