- Membership
- Publications
- Meetings
- Competitions
- Community
- Programs
- Students
- High School Teachers
- Faculty and Departments
- Underrepresented Groups
- MAA Awards
- MAA Grants

- News
- About MAA

Publisher:

Chapman & Hall/CRC

Publication Date:

2010

Number of Pages:

476

Format:

Hardcover

Price:

79.95

ISBN:

9781439805688

Category:

Textbook

[Reviewed by , on ]

Robert W. Hayden

09/9/2010

This book is a curious mixture of strengths and weaknesses. Your colleagues in Business may like it. Most of the examples and exercises sound like business applications, though few involve real data or research. The communication function of graphics is presented rather than just the analytical use of graphics. Spreadsheets are integrated throughout. In most cases, the treatment is generic, but when functions are given by name they are *Excel* functions. The integration is sometimes subtle. Computations are laid out in a tabular format that fits a spreadsheet rather than a plugging-numbers-into-formula layout.

For the mathematician, this text does an outstanding job of integrating things on the mathematical level. The situations where one test is a special case of another (say, two-sample *t* of ANOVA) are mentioned, as are similarities in formulae. For example, many test statistics look like a measure of discrepancy between the data and a model for the data, divided by a measure of variability in the data. This is one of the few texts to try to make plausible the complex formula for two-sample *t* degrees of freedom when we do not assume the two variances are equal.

Perhaps the only people *not* happy will be statisticians. Consider the section on comparing two means as an example. The pattern is to present some numbers to use to show the steps of computing a hypothesis test. Then this is followed by multiple examples of carrying out these computations, in turn followed by exercises asking students to do more computations with their spreadsheet. There is not a single graph of any of the data. About the only assumption addressed is whether the two populations have the same variance, and that is addressed later in the text with the usual *F*-test for two variances. Unfortunately, that test is much more subject to assumption violations than is the *t*-test, and using it in this fashion is generally held in disrepute by statisticians. No attention is given to study design, and interpretation of the results is limited to the decision on whether to reject the null. In general, this text puts most of the emphasis on formulae and computations, with very little that matches the recommendations of the joint ASA/MAA committee on the teaching of statistics. (You can find one statement of those recommendations in Teaching Statistics.)

That leaves the students. What will they think of this book? They will like the clear and to the point writing. The book is very plain, with no color and no pictures, but then the price is far below most of the more colorful textbooks. It is reasonably compact and shorter than most business statistics textbooks. Some students will like the routine of not being asked to do more than crunch numbers, while others will miss being challenged to grapple with real data and real research issues.

After a few years in industry, Robert W. Hayden (bob@statland.org) taught mathematics at colleges and universities for 32 years and statistics for 20 years. In 2005 he retired from full-time classroom work. He now teaches statistics online at statistics.com and does summer workshops for high school teachers of Advanced Placement Statistics. He contributed the chapter on evaluating introductory statistics textbooks to the MAA's Teaching Statistics.

**Introduction to Statistics**

What Is Statistics Good for?

Some Further Applications of Statistics

Some Basic Statistical Ideas

On Studying Statistics

**Describing Data: Tables and Graphs**

Looking at a Single Variable

Looking for Relationships

Looking at Variables over Time

**Describing Data: Summary Statistics**

When Pictures Will Not Do

Measures of a Single Numeric Variable

Measures of a Single Categorical Variable

Measures of a Relationship

**Basic Probability**

Why Probability?

The Basics

Computing Probabilities

Some Tools That May Help

Revising Probabilities with Bayes’ Theorem

**Probability Distributions**

Discrete Random Variables

The Binomial Probability Distribution

Continuous Random Variables

The Normal Distribution: The Bell-Shaped Curve

The Normal Approximation to the Binomial

**Sampling and Sampling Distributions**

Sampling

What Are Sampling Distributions and Why Are They Interesting?

The Sampling Distribution of a Proportion

The Sampling Distribution of a Mean: σ_{X}* *Known

The Sampling Distribution of a Mean: σ_{X}* *Unknown

Other Sampling Distributions

**Estimation and Confidence Intervals**

Point and Interval Estimators of Unknown Population Parameters

Estimates of the Population Proportion

Estimates of the Population Mean

A Final Word on Confidence Intervals

**Tests of Hypotheses: One-Sample Tests**

Testing a Claim: Type I and Type II Errors

A Two-Tailed Test for the Population Proportion

A One-Tailed Alternative for the Population Proportion

Tests for the Population Mean

A Two-Tailed Test for the Population Mean

A One-Tailed Alternative for the Population Mean

A Final Word on One-Sample Tests

**Tests of Hypotheses: Two-Sample Tests**

Looking for Relationships Again

A Difference in Population Proportions

A Difference in Population Means

A Difference in Means: σs Known

A Difference in Means: σs Unknown but Equal

A Difference in Means: σs Unknown and Unequal

A Difference in Means: Using Paired Data

A Final Word on Two-Sample Tests

**Tests of Hypotheses: Contingency and Goodness-of-Fit**

A Difference in Proportions: An Alternate Approach

Contingency Tables with Several Rows and/or Columns

A Final Word on Contingency Tables

Testing for Goodness-of-Fit

A Final Example on Testing for Goodness-of-Fit

**Tests of Hypotheses: ANOVA and Tests of Variances**

A Difference in Means: An Alternate Approach

ANOVA with Several Categories

A Final Word on ANOVA

A Difference in Population Variances

**Simple Regression and Correlation**

The Population Regression Line

The Sample Regression Line

Evaluating the Sample Regression Line

Evaluating the Sample Regression Slope

The Relationship of *F *and *t*: Here and Beyond

Predictions Using the Regression Line

Regression and Correlation

Another Example

Dummy Explanatory Variables

The Need for Multiple Regression

**Multiple Regression**

Extensions of Regression Analysis

The Population Regression Line

The Sample Regression Line

Evaluating the Sample Regression Line

Evaluating the Sample Regression Slopes

Predictions Using the Regression Line

Categorical Variables

Estimating Curved Lines

Additional Examples

**Time-Series Analysis**

Exploiting Patterns over Time

The Basic Components of a Time Series

Moving Averages

Seasonal Variation

The Long-Term Trend

The Business Cycle

Putting It All Together: Forecasting

Another Example

**Appendix A
Appendix B: Answers to Odd-Numbered Exercises
Appendix C**

**Index**

- Log in to post comments