Business Statistics

Business Statistics, Second Edition, helps students learn the statistical tools and develop the understanding theyrs"ll need to go successfully from the classroom to the boardroom. The dynamic approach conquers the modern challenges of teaching business statistics by making it relevant, emphasizing analysis and understanding over simple computation, preparing students to make better business decisions through statistics, and effectively communicating results. This text features a wealth of real data applications, with coverage of current issues including ethics and data mining. It draws readers in using a conversational writing style and delivers content with a fresh, exciting approach that reflects the authorsrs" blend of teaching, consulting, and entrepreneurial experiences. Learning tools such as thePlan/Do/Reportguided examples prepare students to tackle any business problem they will encounter as a future business leader. This book follows the GAISE Guidelines, emphasizing real data and real-world interpretations of analyses.

Norean Sharpe (Ph.D. University of Virginia), as a researcher of statistical problems in business and a professor at a business school, understands the challenges and specific needs of the business student. She is currently teaching at the McDonough School of Business at Georgetown University, where she is also Associate Dean and Director of Undergraduate Programs. Prior to joining Georgetown, she taught business statistics and operations research courses to both undergraduates and MBAs for fourteen years at Babson College. She is the recipient of the 2008 Women Who Make a Difference Award for female faculty at Babson. Prior to joining Babson, she taught statistics and applied mathematics courses for several years at Bowdoin College. Norean is coauthor of the recent text, A Casebook for Business Statistics: Laboratories for Decision Making, and has authored more than 30 articles-primarily in the areas of statistics education and women in science. Norean currently serves as Associate Editor for CAUSE (Consortium for the Advancement of Undergraduate Statistics Education) and Associate Editor for the journal Cases in Business, Industry, and Government Statistics. Her research focuses on business forecasting and statistics education.

 

Richard D. De Veaux (Ph.D. Stanford University) is an internationally known educator, consultant, and lecturer. Dick has taught Statistics at a business school (The Wharton School of the University of Pennsylvania), an engineering school (Princeton University), and a liberal arts college (Williams College). He is an internationally known lecturer in data mining and is a consultant for many Fortune 500 companies in a wide variety of industries. While at Princeton, he won a Lifetime Award for Dedication and Excellence in Teaching. Since 1994, he has been a Professor of Statistics at Williams College. Dick holds degrees from Princeton University in Civil Engineering and Mathematics, and from Stanford University in Dance Education and Statistics, where he studied with Persi Diaconis. His research focuses on the analysis of large data sets and data mining in science and industry. Dick has won both the Wilcoxon and Shewell awards from the American Society for Quality and is a Fellow of the American Statistical Association. Dick is well known in industry, having consulted for such companies as American Express, Hewlett-Packard, Alcoa, DuPont, Pillsbury, General Electric, and Chemical Bank. He was named the “Statistician of the Year” for 2008 by the Boston Chapter of the American Statistical Association for his contributions to teaching, research, and consulting. In his spare time he is an avid cyclist and swimmer. He also is the founder and bass for the Doo-wop group, “Diminished Faculty,” and is a frequent soloist with various local choirs and orchestras. Dick is the father of four children.

 

Paul F. Velleman (Ph.D. Princeton University) has an international reputation for innovative statistics education. He designed the Data Desk® software package and is also the author and designer of the award-winning ActivStats® statistics package, for which he received the EDUCOM Medal for innovative uses of computers in teaching statistics and the ICTCM Award for Innovation in Using Technology in College Mathematics. He is the founder and CEO of Data Description, Inc. (www.datadesk.com), which supports both of these programs. He also developed the Internet site, Data and Story Library (DASL) (http://lib.stat.cmu.edu/DASL/), which provides data sets for teaching Statistics. Paul co-authored (with David Hoaglin) the book ABCs of Exploratory Data Analysis. Paul has taught Statistics at Cornell University on the faculty of the School of Industrial and Labor Relations since 1975. His research often focuses on statistical graphics and data analysis methods. Paul is a Fellow of the American Statistical Association and of the American Association for the Advancement of Science. Paul’s experience as a professor, entrepreneur, and business leader brings a unique perspective to the book.

 

Dick De Veaux and Paul Velleman have authored successful books in the introductory college and AP High School market with Dave Bock, including Intro Stats, Third Edition (Pearson, 2009), Stats: Modeling the World, Third Edition (Pearson, 2010), and Stats: Data and Models, Third Edition (Pearson, 2012).

PART I. EXPLORING AND COLLECTING DATA

 

1. Statistics and Variation

1.1 So, What Is Statistics?

1.2 How Will This Book Help?

 

2. Data

Amazon.com

2.1 What Are Data?

2.2 Variable Types

2.3 Data Sources: Where, How, and When

Ethics in Action

Technology Help

Brief Cases: Credit Card Bank

 

3. Surveys and Sampling

Roper Polls

3.1 Three Ideas of Sampling

3.2 Populations and Parameters

3.3 Other Sample Designs

3.4 The Valid Survey

3.5 How to Sample Badly

Ethics in Action

Technology Help: Random Sampling

Brief Cases: Market Survey Research

The GfK Roper Reports Worldwide Survey

 

4. Displaying and Describing Categorical Data

Keen

4.1 Summarizing a Categorical Variable

4.2 Displaying a Categorical Variable

4.3 Exploring Two Categorical Variables: Contingency Tables

Ethics in Action

Technology Help: Displaying Categorical Data on the Computer

Brief Cases: KEEN

 

5. Displaying and Describing Quantitative Data

AIG

5.1 Displaying Quantitative Variables

5.2 Shape

5.3 Center

5.4 Spread of the Distribution

5.5 Shape, Center, and Spread-A Summary

5.6 Five-Number Summary and Boxplots

5.7 Comparing Groups

5.8 Identifying Outliers

5.9 Standardizing

*5.10 Time Series Plots

*5.11 Transforming Skewed Data

Ethics in Action

Technology Help: Displaying and Summarizing

Quantitative Variables

Brief Cases Hotel Occupancy Rates 122

Value and Growth Stock Returns 122

 

6. Correlation and Linear Regression

Lowe's

6.1 Looking at Scatterplots

6.2 Assigning Roles to Variables in Scatterplots

6.3 Understanding Correlation

6.4 Lurking Variables and Causation

6.5 The Linear Model

6.6 Correlation and the Line

6.7 Regression to the Mean

6.8 Checking the Model

6.9 Variation in the Model and R2

6.10 Reality Check: Is the Regression Reasonable?

6.11 Non-linear Relationships

Ethics in Action

Technology Help: Correlation and Regression

Brief Cases: Fuel Efficiency

The U.S. Economy and Home Depot Stock Prices

Cost of Living

Mutual Funds

 

Case Study: Paralyzed Veterans of America

 

PART II. MODELING WITH PROBABLITY

 

7. Randomness and Probability

Credit Reports and the Fair Isaacs Corporation

7.1 Random Phenomena and Probability

7.2 The Nonexistent Law of Averages

7.3 Different Types of Probability

7.4 Probability Rules

7.5 Joint Probability and Contingency Tables

7.6 Conditional Probability

7.7 Constructing Contingency Tables

Brief Case: Market Segmentation

 

8. Random Variables and Probability Models

Metropolitan Life Insurance Company

8.1 Expected Value of a Random Variable

8.2 Standard Deviation of a Random Variable

8.3 Properties of Expected Values and Variances

8.4 Discrete Probability Distributions

Ethics in Action

Brief Case: Investment Options

 

9. The Normal Distribution

The NYSE

9.1 The Standard Deviation as a Ruler

9.2 The Normal Distribution

9.3 Normal Probability Plots

9.4 The Distribution of Sums of Normals

9.5 The Normal Approximation for the Binomial

9.6 Other Continuous Random Variables

Ethics In Action

Brief Cases: The CAPE10

Technology Help: Making Normal Probability Plots

 

10. Sampling Distributions

Marketing Credit Cards: The MBNA Story

10.1 The Distribution of Sample Proportions

10.2 Sampling Distribution for Proportions

10.3 The Central Limit Theorem

10.4 The Sampling Distribution of the Mean

10.5 How Sampling Distribution Models Work

Ethics in Action

Brief Cases Real Estate Simulation

Part 1: Proportions

Means

 

Case Study: Investigating the Central Limit Theorem

 

PART III. INFERENCE FOR DECISION MAKING

 

11. Confidence Intervals for Proportions

The Gallup Organization

11.1 A Confidence Interval

11.2 Margin of Error: Certainty vs. Precision

11.3 Assumptions and Conditions

11.4 Choosing the Sample Size

*11.5 A Confidence Interval for Small Samples

Ethics in Action

Technology Help: Confidence Intervals for Proportions

Brief Cases: Investment

Forecasting Demand

 

12. Confidence Intervals for Means

Guinness & Co.

12.1 The Sampling Distribution for the Mean

12.2 A Confidence Interval for Means

12.3 Assumptions and Conditions

12.4 Cautions About Interpreting Confidence Intervals

12.5 Sample Size

12.6 Degrees of Freedom - Why (n-1)?

Ethics in Action

Technology Help: Inference for Means

Brief Cases: Real Estate

Donor Profiles

 

13. Testing Hypotheses

Dow Jones Industrial Average

13.1 Hypotheses

13.2 A Trial as a Hypothesis Test

13.3 P-values

13.4 The Reasoning of Hypothesis Testing

13.5 Alternative Hypotheses

13.6 Testing Hypothesis about Means - the One

13.7 Alpha Levels and Significance

13.8 Critical Values

13.9 Confidence Intervals and Hypothesis Tests

13.10 Two Types of Errors

*13.11 Power

Ethics in Action

Technology Help

Brief Cases: Metal Production

Loyalty Program

 

14. Comparing Two Groups

Visa Global Organization

14.1 Comparing Two Means

14.2 The Two-Sample t-Test

14.3 Assumptions and Conditions

14.4 A Confidence Interval for the Difference Between Two Means

14.5 The Pooled t-Test

14.6 Tukey's Quick Test

14.7 Paired Data

14.8 The Paired t-Test

Ethics in Action

Technology Help: Two-Sample Methods

Brief Cases: Real Estate

Consumer Spending Patterns (Data Analysis)

 

15. Inference for Counts: Chi-Square Tests

SAC Capital

15.1 Goodness-of-Fit Tests

15.2 Interpreting Chi-Square Values

15.3 Examining the Residuals

15.4 The Chi-Square Test of Homogeneity

15.5 Comparing Two Proportions

15.6 Chi-Square Test of Independence

Ethics in Action

Technology Help: Chi-Square

Brief Cases: Health Insurance

Loyalty Program

 

Case Study

 

Part IV. MODELS FOR DECISION MAKING

 

16. Inference for Regression

Nambé Mills

16.1 The Population and the Sample

16.2 Assumptions and Conditions

16.3 The Standard Error of the Slope

16.4 A Test for the Regression Slope

16.5 A Hypothesis Test for Correlation

16.6 Standard Errors for Predicted Values

16.7 Using Confidence and Prediction Intervals

Ethics in Action

Technology Help: Regression Analysis

Brief Cases: Frozen Pizza

Global Warming?

 

17. Understanding Residuals

Kellogg's

17.1 Examining Residuals for Groups

17.2 Extrapolation and Prediction

17.3 Unusual and Extraordinary Observations

17.4 Working with Summary Values

17.5 Autocorrelation

17.6 Transforming (Re-expressing) Data

17.7 The Ladder of Powers

Ethics in Action

Technology Help

Brief Cases: Gross Domestic Product

Energy Sources

 

18. Multiple Regression

Zillow.com

18.1 The Multiple Regression Model

18.2 Interpreting Multiple Regression Coefficients

18.3 Assumptions and Conditions for the Multiple Regression Model

18.4 Testing the Multiple Regression Model

18.5 Adjusted R2, and the F-statistic

*18.6 The Logistic Regression Model

Ethics in Action

Technology Help: Regression Analysis

Brief Case: Golf Success

 

19. Building Multiple Regression Models

Bolliger and Mabillard

19.1 Indicator (or Dummy) Variables

19.2 Adjusting for Different Slopes-Interaction

19.3 Multiple Regression Diagnostics

19.4 Building Regression Models

19.5 Collinearity

19.6 Quadratic

Ethics in Action

Technology Help: Regression Analysis on the Computer

Brief Cases: Paralyzed Veterans of America

 

20. Time Series Analysis

Whole Foods Market^®

20.1 What is a Time-Series?

20.2 Components of a Time Series

20.3 Smoothing Methods

20.4 Summarizing Forecast Error

20.5 Autoregressive Models

20.6 Multiple Regression-based Models

20.7 Choosing a Time Series Forecasting Method

20.8 Interpreting Time Series Models: The Whole Foods Data Revisited

Ethics in Action

Technology Help

Brief Cases: Intel Corporation

Tiffany & Co.

Case Study: title to come

 

PART V. SELECTED TOPICS IN DECISION MAKING

 

21. Design and Analysis of Experiments and Observational Studies

Capital One

21.1 Observational Studies

21.2 Randomized, Comparative Experiments

21.3 The Four Principles of Experimental Design

21.4 Experimental Designs

21.5 Issues in Experimental Design

21.6 Analyzing a Completely Randomized Design in One Factor-The One-Way Analysis of Variance

21.7 Assumptions and Conditions for ANOVA

*21.8 Multiple Comparisons

21.9 ANOVA on Observational Data

21.10 Analysis of Multi Factor Designs

Ethics in Action

Technology Help

Brief Cases: A Multifactor Experiment

 

22. Quality Control

Sony

22.1 A Short History of Quality Control

22.2 Control Charts for Individual Observations (Run Charts)

22.3 Control Charts for Measurements: X and R Charts

22.4 Actions for Out of Control Processes

22.5 Control Charts for Attributes: p Charts and c Charts

22.6 Philosophies of Quality Control

Ethics in Action

Technology Help: Quality Control Charts

Brief Cases

 

23. Nonparametric Methods

i4cp

23.1 Ranks

23.2 The Wilcoxon Rank-Sum/Mann-Whitney Statistic

23.3 Kruskal-Wallace Test

23.4 Paired Data: The Wilcoxon Signed-Rank Test

*23.5 Friedman Test for a Randomized Block Design

23.6 Kendall's Tau: Measuring Monotonicity

23.7 Spearman's Rho

23.8 When Should You Use Nonparametric Methods?

Ethics in Action

Brief Cases: Real Estate Reconsidered

 

 

24. Decision Making and Risk

Data Description, Inc.

24.1 Actions, States of Nature, and Outcomes

24.2 Payoff Tables and Decision Trees

24.3 Minimizing Loss and Maximizing Gain

24.4 The Expected Value of an Action

24.5 Expected Value with Perfect Information

24.6 Decisions Made with Sample Information

24.7 Estimating Variation

24.8 Sensitivity

24.9 Simulation

24.10 Probability Trees

*24.11 Reversing the Conditioning: Bayes's Rule

24.12 More Complex Decisions

Ethics in Action

Brief Cases: Texaco-Pennzoil

Insurance Services, Revisited

 

25. Introduction to Data Mining

Paralyzed Veterans of America

25.1 Direct Marketing

25.2 The Data

25.3 The Goals of Data Mining

25.4 Data Mining Myths

25.5 Successful Data Mining

25.6 Data Mining Problems

25.7 Data Mining Algorithms

25.8 The Data Mining Process

25.9 Summary

Ethics in Action

 

Case Study

 

*Indicates an optional topic

 

Appendices

A. Answers

B. XLStat

C. Photo Acknowledgments

D. Tables and Selected Formulas

E. Index