Statistics: A First Course (8th Edition) by John E. Freund and Benjamin M. Perles

It's taken me a little less than two and a half months of my spare time to work my way through every single one of the nearly 350 examples and end-of-section practice exercises for which Statistics: A First Course, 8th edition provides full solutions ... but I'm finally finished and I'd like to share my thoughts on the book.

I think that it's good - but not great. Be advised, however, that this is the first statistics book in which I've invested so much time and effort. Montgomery and Runger's Applied Statistics and Probability for Engineers (3rd edition) and Larsen and Marx's An Introduction to Mathematical Statistics and Its Applications (4th Edition), both of which assume a bit more mathematically-savvy reader, are sitting on my to-read stack, but I've only flipped through them as of yet.

My hope is that, despite (or maybe even because of) my limited perspective, my comments here will help you make an informed purchase - whether you're a teacher considering using it for a statistics course in a high school, college, or university or are thinking about buying a copy for self-study, as I did. Instructors can get exam copies of textbooks from major publishers, but the impression of a book that you can get from flipping through it briefly or tackling a couple of sections chosen at random isn't going to be as detailed or nuanced as the one you'll end up with if you basically live with it for a couple of months.

Book dimensions and appearance

Not counting the appendices, bibliography, statistical tables, answers and index (which add another 80 pages or so), SAFC weighs in at 461 pages. That makes it a slim book by the standards of introductory college texts. It's also physically smaller than most of the usual doorstops - just an inch thick from cover to cover and about nine and a half inches tall by seven and a half inches wide. Its size and slightly washed-out-looking Aquamarine and Cadet Blue colorscheme reminded me a bit of some of my primary and middle school math books:

Preface: truths, truths with caveats, and fibs

Here, from the preface, is the closest thing that you'll find to a description of the book's intended audience:

To flesh that out a bit, this is an introductory stats text that you can tackle without having taken a course in Calculus. This doesn't seem to be xplicitly stated until about halfway through the book when the absence of formal definitions for the mean and standard deviation of a continuous distribution is explained as follows:

The equations for the statistical distributions used in the book aren't given either:

The preface itself makes several assertions about the book, some of which my experiences have borne out to be true, some that are true with caveats, and a few that are outright false (details highlighted in yellow, unhighlighted sentences are taken verbatim from page ix of SAFC):

1. TRUE: The book contains a wide selection of nearly 1000 exercises, presented throughout the text. The book also offers a large number of detailed illustrations and examples, in each chapter, designed to provide guidance to readers.
2. TRUE WITH CAVEAT: Important formulas, definitions, and rules are highlighted within colored boxes. None of them are numbered, which makes referring to a specific formulas, definitions, or rule difficult and awkward - even for the authors of the book.
3. TRUE WITH CAVEAT: The frequently used tables for normal and t distributions are repeated on the inside back cover, and the inside front cover contains an indexed glossary of statistical symbols. The indexed glossary of symbols is a great idea, but is not complete. You will frequently encounter symbols in the text that do not appear in this list ... and aren't clearly defined in the adjacent text.
4. FALSE: As in previous editions, controversy has not been avoided. The reader is exposed to the weaknesses of statistical techniques as well as their strengths. It is hoped that this honest approach will provide a stimulus as well as a challenge. The challenge here would be to find anything controversial in the book. I suppose that the stuff about exposing readers to the weaknesses of statistical techniques could be a reference to the guidelines (which, inexplicably, are not always followed by the text itself) about sample sizes with respect to small vs. large sample statistical techniques, but that seems like a bit of a stretch.
5. POSSIBLY TRUE: For instructors who have used previous editions of this textbook, it should be noted that the problem sets have been extensively revised. Many additional real data-based [sic] problems have been added.
6. FALSE: Internal referencing within the problem sets has been minimized. Where necessary, pertinent data has been repeated to free students from the unproductive "busy work" of flipping back to previous problems. False! False! A thousand times false! Especially in the final several chapters, examples reference previous earlier examples, practice exercises refer back to examples, and practice exercises reference preceding practice exercises. Many examples and exercises begin with Rework the previous example using [...], With reference to exercise [...], Calculate [something] for the example on page [...] or Based on the data on page [...]. In one case (Chapter 12), nearly all of the examples and practice exercises in the entire chapter concerned a single dataset - the number of years that applicants for certain foreign service jobs have studied German in high school or college and the grades that they received on a proficiency test in that language.

Again, SAFC is an OK book. Most of the explanations in the text are clear enough, there are relatively few mistakes or typos (the publisher, Pearson Prentice Hall, doesn't seem to be keeping a list, but I only found 8), and the writing seems engaging enough given the subject matter and the fact that this is an introductory college textbook. On the other hand, don't look for any historical vignettes, derivations or proofs, or cookbook-style advice on which techniques to use in different real-world situations.

The books use of MINITAB and the TI-83

In addition to the gripes mentioned in my tour of the first bit of the preface (above), I was a bit let down by the authors' choices of "technology" for problem-solving - MINITAB (non-free software) and the TI-83 calculator. I would have liked to see GNU R (a programming language and software environment for statistical computing and graphics), a GPL'd implementation of S, used instead of MINITAB. R is free as in speech and free as in beer and, judging from Wikipedia's Comparison of statistical packages article, does more than MINITAB. Flipping through the other introductory stat texts that I have on hand, I noticed that they all used MINITAB too, but it's no less annoying for being common.

How useful the MINITAB bits of the text even are is questionable, since they mostly consist of screencaps of the software with a figure label like MINITAB printout for [...] and a single sentence somewhere nearby in the text that reads like A computer printout of the [...] is shown in Figure X..

The book came with a CD-ROM glued to the front of the inside cover (containing data files, according to the preface), which I didn't touch until after I'd begun this writeup. Amazingly, the publishers actually wasted a whole CD-ROM to hold 2 sets (one in plain .txt format and the other in MINITAB's .MTPformat) of data files, eah just a few kB in size, for 9 different exercises in the text. All of the last-modified timestamps on the files indicate that they date from October 1998.

If those dates are correct, then the absence of GNU R makes a bit more sense. The opening copyright date on the general GNU R FAQ is 1998 and the FAQ states that Since mid-1997 there has been a core group (the 'R Core Team') who can modify the R source code archive. If R was new in the mid/late-90s and the MINITAB stuff in SAFC was added or last updated at about that time, then I can see why R wasn't a contender for use in the text. Though R is sometimes referred to as 'GNU S' and S (in the form of S-PLUS) was already long-mature by that time ... the company that sells S-PLUS doesn't even give pricing info on its website, which suggests that the cost is prohibitive, so it wouldn't have been a viable option either.

I don't have access to previous editions of this book, but the timestamps on those files and my gut instincts lead me to suspect that Pearson Prentice Hall has been churning out "maintenance releases" of the book for at least the last several editions and isn't on the verge of introducing GNU R anytime soon, which sucks because the book itself, minus the old tech, is actually pretty decent.

The TI-83 came onto the market in 1996 and I wonder whether the USING TECHNOLOGY: The Graphing Calculator sections scattered throughout the book might not have been introduced at the same time as the MINITAB coverage. To their credit, the TI-83 bits include step-by-step instructions on how to obtain the results shown - stuff like obtaining the area under the normal curve over a given interval, ANOVA, etc.

For my part, I appreciate that the book was written in such a way that neither MINITAB nor a graphing calculator were necessary accessories. As I moved through the book, I found myself using a combination of GNU R (even knowing only as much as I could pick up quickly through Google, it came in handy in chapters 7-10) and, though I could just as easily have used OO.o Calc, Excel (in chapters 10-13) to tackle the problems in the text. While I did break out my trusty old TI-85, it only saw number crunching duty - no graphing or TI-BASIC programming occurred.

Future editions

Shortly after I purchased the book, I did a bit of Googling and discovered that the lead author, John E. Freund, a professor emeritus at Arizona State University and author or coauthor of numerous statistics texts besides this one, had passed away on August 14th 2004 - at age 83. His coauthor on SAFC, Benjamin M. Perles, a professor at Suffolk University, is still kicking and Pearson Prentice Hall has gone on to publish new editions of at least one other Freund-Perles book since Freund's death with the same author billing, Modern Elementary Statistics (12th edition), which came out this year (2007). Alternatively, they might go the route they did with John E. Freund's Mathematical Statistics with Applications (7th edition), released in 2004, where Freund's name is in the title, but he's not listed as one of the authors.

Though I don't doubt that minor changes and tweaks have been made to the book over the past several editions, I would guess that there haven't been any major changes since the MINITAB and TI-83 content was bolted on sometime in the late 90s. Pearson Prentice Hall could probably go on publishing warmed-over editions of SAFC pretty much indefinitely.

Update

Randy K. Schwartz, a professor in the Department of Mathematics at Schoolcraft College, was kind enough to email me regarding my review. In addition to sharing a much more complete list of errata, linked with his permission in the next section, he had some advice on a suitable replacement text:

Errata for Statistics: A First Course (8th Edition) by John E. Freund and Benjamin M. Perles

Page #	Location	Description
99	Solution to Practice Exercise 3.95	Solution begins The median is and does indeed go on to give the calculation for the median ... but the variable shown is x-bar (sample mean, in this text) rather than x-tilde (sample median).
150	Example 5.4	Question statement begins With reference to example 5.1, the two-salespersons example, which of the following pairs of events are mutually exclusive: and proceeds to list 2 pairs of sets. The problem is that the sets used in the question are developed in Example 5.2, which itself references Example 5.1. One of many instances where the reader might flashback to the statement in the book's preface that Internal referencing within the problem sets has been minimized.
276	Example 8.5	The example problem statement begins as follows: With reference to the illustration on page 270,. Unfortunately, there is no illustration on that page and none on any adjacent pages that seem relevant to the problem at hand.
362	Solution to Practice Exercise 10.43	Result is incorrect since the value for x-bar1 changes from 8160 in the problem statement to 8106 in the solution.
371	last paragraph	Typo where a section of a sentence (from about midway through and on to the end) is repeated.
375	Equation for statistic for a test concerning the differences among proportions	Missing equals sign.
413	Final mathematical result on page.	Incorrect result. (697-381.5)/10 = 31.55 not 31.35.

The publisher, Pearson Prentice Hall, doesn't seem to be maintaining any sort of errata list, so here are the ones that I noticed.

In addition to the typos and errors listed above, the original contents of the bottom halves of pages 281, 282, 303, and 304 were covered by glued-on sections - most likely to correct printing defects.

Update

Randy K. Schwartz, a professor in the Department of Mathematics at Schoolcraft College, was kind enough to email me regarding my review. In addition to mentioning a possible replacement text (see previous section), he shared a much more complete list of errata for SAFC, linked here with his permission: randy-k-schwartz-safc-errors.pdf.

Table of Contents

Adapted from the table of contents on the publisher's site:

1. Introduction: Numerical Data and Categorical Data. Nominal, Ordinal, Interval, and Ratio Data. Sample Data and Populations. Biased Data. Statistics, Past and Present. The Study of Statistics. Statistics, What Lies Ahead.
2. Summarizing Data: Listing and Grouping: Dot Diagrams. Stem-and-Leaf Displays. Frequency Distributions. Graphical Presentations.
3. Summarizing Data: Statistical Descriptions: Measures of Location: The Mean. Measures of Location: The Weighted Mean. Measures of Location: The Median and Other Fractiles. Measures of Location: The Mode. Measures of Variation: The Range. Measures of Variation: The Standard Deviation. Some Applications of the Standard Deviation. The Description of Grouped Data. Some Further Descriptions. Technical Note Summations.
4. Possibilities and Probabilities: Counting. Permutations. Combinations. Probability. Mathematical Expectation. A Decision Problem.
5. Some Rules of Probability: The Sample Space. Events. Some Basic Rules of Probability. Probabilities and Odds. Addition Rules. Conditional Probability. Independent Events. Multiplication Rules. Bayes' Theorem.
6. Probability Distributions: Probability Distributions. The Binomial Distribution. The Hypergeometric Distribution. The Poisson Distribution. The Multinomial Distribution. The Mean of a Probability Distribution. The Standard Deviation of a Probability Distribution. Chebyshev's Theorem.
7. The Normal Distribution: Continuous Distributions. The Normal Distribution. Some Applications. The Normal Approximation to the Binomial Distribution.
8. Sampling and Sampling Distributions: Random Sampling. Sampling Distributions. The Standard Error of the Mean. The Central Limit Theorem.
9. Problems of Estimation: The Estimation of Means. Confidence Intervals for Means. Confidence Intervals for Means (Small Samples). Confidence Intervals for Standard Deviations. The Estimation of Proportions.
10. Tests Concerning Means: Tests of Hypotheses. Significance Tests. Tests Concerning Means. Tests Concerning Means (Small Samples). Differences Between Means. Differences Between Means (Small Samples). Differences Between Means (Paired Data). Differences Among k Means. Analysis of Variance.
11. Tests Based on Count Data: Tests Concerning Proportions. Tests Concerning Proportions (Large Samples). Differences Between Proportions. Differences Among Proportions. Contingency Tables. Goodness of Fit.
12. Regression and Correlation: Curve Fitting. The Method of Least Squares. Regression Analysis. The Coefficient of Correlation. The Interpretation of r. A Significance Test for r.
13. Nonparametric Tests: The One-Sample Sign Test. The Paired-Sample Sign Test. The Sign Test (Large Samples). Rank Sums: The U Test. Rank Sums: The U Test (Large Samples). Rank Sums: The H Test. Tests of Randomness: Runs. Tests of Randomness: Runs (Large Samples). Tests of Randomness: Runs Above and Below the Median. Rank Correlation.