Statistics for Business

Robert Stine holds a PhD from Princeton University. He has taught at the Wharton School since 1983, during which time he has regularly taught business statistics. During his tenure, Bob has received a variety of teaching awards. Bob also actively consults for industry. His clients include the pharmaceutical firms Merck and Pfizer, and he regularly works with the Federal Reserve Bank of Philadelphia on models for retail credit risk. This collaboration has produced three well-received conferences held at Wharton. His areas of research include computer software, time series analysis and forecasting, and general problems related to model identification and selection. Bob has published numerous articles in research journals, including the Journal of the American Statistical Association, Journal of the Royal Statistical Society, Biometrika, and The Annals of Statistics. He was recently awarded the 2011 Helen Kardon Moss Anvil Award for outstanding teaching quality at the Wharton School. Dean Foster holds a PhD from the University of Maryland. He has taught at the Wharton School since 1992 and previously taught at the University of Chicago. Dean teaches courses in introductory business statistics, probability and Markov chains, statistical computing, and advanced statistics for managers. Dean's research areas are statistical inference for stochastic processes, game theory, machine learning, and variable selection. He is published in a wide variety of journals, including The Annals of Statistics, Operations Research, Games and Economic Behaviour, Journal of Theoretical Population Biology, and Econometrica. Bob Stine and Dean Foster have co-authored two casebooks: Basic Business Statistics (Springer-Verlag) and Business Analysis Using Regression (Springer-Verlag). These casebooks offer a collection of data analysis examples that motivate and illustrate key ideas of statistics, ranging from standard error to regression diagnostics and time series analysis. They also have collaborated on a number of research articles.

Preface

Index of Application



PART ONE: VARIATION



1. Introduction

1.1 What Is Statistics?

1.2 Previews



2. Data

2.1 Data Tables

2.2 Categorical and Numerical Data

2.3 Recoding and Aggregation

2.4 Time Series

2.5 Further Attributes of Data

Chapter Summary



3. Describing Categorical Data

3.1 Looking at Data

3.2 Charts of Categorical Data

3.3 The Area Principle

3.4 Mode and Median

Chapter Summary



4. Describing Numerical Data

4.1 Summaries of Numerical Variables

4.2 Histograms

4.3 Boxplot

4.4 Shape of a Distribution

4.5 Epilog

Chapter Summary



5. Association between Categorical Variables

5.1 Contingency Tables

5.2 Lurking Variables and Simpson's Paradox

5.3 Strength of Association

Chapter Summary



6. Association between Quantitative Variables

6.1 Scatterplots

6.2 Association in Scatterplots

6.3 Measuring Association

6.4 Summarizing Association with a Line

6.5 Spurious Correlation

Chapter Summary

Statistics in Action: Financial Time Series

Statistics in Action: Executive Compensation



PART TWO: PROBABILITY



7. Probability

7.1 From Data to Probability

7.2 Rules for Probability

7.3 Independent Events

Chapter Summary



8. Conditional Probability

8.1 From Tables to Probabilities

8.2 Dependent Events

8.3 O rganizing Probabilities

8.4 O rder in Conditional Probabilities

Chapter Summary



9. Random Variables

9.1 Random Variables

9.2 Properties of Random Variables

9.3 Properties of Expected Values

9.4 Comparing Random Variables

Chapter Summary



10. Association between Random Variables

10.1 Portfolios and Random Variables

10.2 Joint Probability Distribution

10.3 Sums of Random Variables

10.4 Dependence between Random Variables

10.5 IID Random Variables

10.6 Weighted Sums

Chapter Summary



11. Probability Models for Counts

11.1 Random Variables for Counts

11.2 Binomial Model

11.3 Properties of Binomial Random Variables

11.4 Poisson Model

Chapter Summary



12. The Normal Probability Model

12.1 Normal Random Variable

12.2 The Normal Model

12.3 Percentiles

12.4 Departures from Normality

Chapter Summary

Statistics in Action: Managing Financial Risk

Statistics in Action: Modeling Sampling Variation



PART THREE: INFERENCE



13. Samples and Surveys

13.1 Two Surprising Properties of Samples

13.2 Variation

13.3 Alternative Sampling Methods

13.4 Questions to Ask

Chapter Summary



14. Sampling Variation and Quality

14.1 Sampling Distribution of the Mean

14.2 Control Limits

14.3 Using a Control Chart

14.4 Control Charts for Variation

Chapter Summary



15. Confidence Intervals

15.1 Ranges for Parameters

15.2 Confidence Interval for the Mean

15.3 Interpreting Confidence Intervals

15.4 Manipulating Confidence Intervals

15.5 Margin of Error

Chapter Summary



16. Statistical Tests

16.1 Concepts of Statistical Tests

16.2 Testing the Proportion

16.3 Testing the Mean

16.4 Significance versus Importance

16.5 Confidence Interval or Test?

Chapter Summary



17. Comparison

17.1 Data for Comparisons

17.2 Two-Sample z-test for Proportions

17.3 Two-Sample Confidence Interval for Proportions

17.4 Two-Sample T-test

17.5 Confidence Interval for the Difference between Means

17.6 Paired Comparisons

Chapter Summary



18. Inference for Counts

18.1 Chi-Squared Tests

18.2 Test of Independence

18.3 General versus Specific Hypotheses

18.4 Tests of Goodness of Fit

Chapter Summary

Statistics in Action: Rare Events

Statistics in Action: Data Mining Using Chi-Squared



PART FOUR: REGRESSION MODELS



19. Linear Patterns

19.1 Fitting a Line to Data

19.2 Interpreting the Fitted Line

19.3 Properties of Residuals

19.4 Explaining Variation

19.5 Conditions for Simple Regression

Chapter Summary



20. Curved Patterns

20.1 Detecting Nonlinear Patterns

20.2 Transformations

20.3 Reciprocal Transformation

20.4 Logarithm Transformation

Chapter Summary



21. The Simple Regression Model

21.1 The Simple Regression Model

21.2 Conditions for the SRM

21.3 Inference in Regression

21.4 Prediction Intervals

Chapter Summary



22. Regression Diagnostics

22.1 Changing Variation

22.2 Outliers

22.3 Dependent Errors and Time Series

Chapter Summary



23. Multiple Regression

23.1 The Multiple Regression Model

23.2 Interpreting Multiple Regression

23.3 Checking Conditions

23.4 Inference in Multiple Regression

23.5 Steps in Fitting a Multiple Regression

Chapter Summary



24. Building Regression Models

24.1 Identifying Explanatory Variables

24.2 Collinearity

24.3 Removing Explanatory Variables

Chapter Summary



25. Categorical Explanatory Variables

25.1 Two-Sample Comparisons

25.2 Analysis of Covariance

25.3 Checking Conditions

25.4 Interactions and Inference

25.5 Regression with Several Groups

Chapter Summary



26. Analysis of Variance

26.1 Comparing Several Groups

26.2 Inference in ANOVA Regression Models

26.3 Multiple Comparisons

26.4 Groups of Different Size

Chapter Summary



27. Time Series

27.1 Decomposing a Time Series

27.2 Regression Models

27.3 Checking the Model

Chapter Summary

Statistics in Action: Analyzing Experiments

Statistics in Action: Automated Modeling



Appendix: Tables

Answers

Photo Acknowledgments

Index



Supplementary Material (online-only)

Alternative Approaches to Inference

More Regression

2-Way ANOVA