Customer Reviews

Statistical Methods in Education and Psychology (3rd Edition)

5 star:		(2)
4 star:		(3)
3 star:		(2)
2 star:		(2)
1 star:		(2)

 

 

When the first edition (Glass and Stanley) appeared, in 1970, it was widely acclaimed as the most readable treatment of these methods. Despite the appearance since then of numerous competitors, it has held up well. I can follow a much more mathematical treatment, but this is still the best explanation of what to do when -- and WHY. Perhaps it's confusing to those who only want to know how to do procedures -- but then they have to ask someone else what procedures to use. This book takes the reader a long way toward real insight into statistical thinking.

It is amazing to read other reviews, and it became clear how we all come from varied perspectives and view things differently. I have read couple of statistics books trying to understand one thing or the other before, and have not been lucky finding a real fair text (no stat book could really be a jelly anyway!!!). However, I had the hard luck of doing stats for my M.Sc program...and G&H has been wonderful. I can't complain at all. This text is truly great...and note that I am not a prof. So, if non-profs and lay stat. takers like me could benefit from the book...then it is pretty good.

G&H is a GOOD book. I have taught graduate students using several editions of this book for many years (David Howell's book is good too). The primary advantage of this book is that it does NOT contain a great many errors. Maybe there are some typos but at least it does not give bad and incorrect advice. This is not true of many books geared toward non-statistics students.

I have to say that students do not like the book. They think it is too hard. They want something easy and COMPLETELY non-technical (and this book is not really very technical), If students are going to learn the material, which is by its nature technical, the book has to be somewhat technical. I try to ease the tedium by supplementing the book with MANY handout and other materials. For what it is the _Cartoon Guide to Statistics_ is actually pretty good and also not full of errors. This latter book is a good supplement to G&H. The cartoons add some fun but G&H is not really much more technical.

My advice to students is to go to the library and find lots of different stats books. Everyone learns differently and find one that helps you. Be aware though that the non-technical, really simple books tend to be written by people who don't know what they are talking about and so it's the blind-leading-the-blind. The best way to survive stats is to study every day. If you don't understand something find your prof or ta and have them explain it until you get it. Good luck & persevere!

I agree with most the reviewers. This book was clearly written for other professors and advanced statisticians and definetely not students. If you get assigned this book for an introductory statistics class, buy or check out other books from the library.

On the other hand, this book is not totally worthless. If you are well versed in statistics and have had several advanced classes, this book serves as an actually decent review manual.

Overall, in retrospect it was worth the buy. However, I am amazed by the number of professors who actually think this book is adequate for an introductory statistics class. (The typical professor retort "the authors are respected in the field and have published prolifically" doesn't really mean a lot in the real world, where people are more interested in learning and not really impressed by the number of publications a professor has).

This is one of the worst textbooks I've ever bought. It is written in a way that makes the concepts seem harder than they actually are, and does not really describe the equations and their use. It just gives you a bunch of problems that do not always correlate with or are not explained in the chapter.

I'm not terrible with math by any means, but I can't say I've ever enjoyed it or its bast*rd cousin, statistics. This textbook was the required reading for my graduate statistics course in Psychology that I'm just finishing now, and I have to say that these past few months, supplemented well by this book, was as interested as I have ever been in stats - and I think this is saying a lot.

As someone else here pointed out, this text takes a very conceptual approach and tries very hard (and I think often successfully) to explain to you what exactly is going on with these various statistical tests and methods, why they are done in such a way, the mathematical and indeed practical tests which show that they are useful, and so on and so forth. I remember doing almost all of these tests as an undergraduate at some point or other, but I never had any real notion of what they meant or why I would do one versus the other - all I wanted to see was a little asterisk pop up in my software, denoting that the test was significant and I could revel in my results.

This book (and my class, which follows the book very closely), however, has really given me a much better grasp of the real strengths, and serious shortcomings, of all the core statistical techniques used in Psychology. I can hardly recommend it as voluntary reading, but if you are stuck with this as a textbook for a class I think you should actually rejoice. A semester going through this stuff and you will likely understand statistics in a deep and meaningful (if not very mathematical) way. I have to concur with the authors (and my professor) that the mathematical side, though obviously crucial, is less and less relevant to researchers themselves. Only a maniac would sit down and compute these values by hand nowadays; in many cases this is impossible anyway, or would take hundreds of hours. The fact is that almost everyone is going to use software to perform these tests regardless - so the least we can do is make sure that the tests are understood well theoretically by researchers. This book will give you just such an understanding.

One star off because it is fairly obtuse at times; it is ludicrously expensive for such an old book that has barely been updated in decades (my copy came with a floppy disk containing the practice data sets, for crying out loud!); and occasional typos/computational gaffs throughout.

This is a decent book, with many helpful explanations and examples, but I actually never need it except for the table of z-scores in the back, because my instructor provides all the necessary notes in class.

Forget about the countless times you have computed a basic chi-square. This book will undermine any confidence that you ever had in your ability. If you like a text that gets to the point and applies the issues in a pertinent and concise manner, see Cohen, Howell, etc... Anything but this. Still, it does make for an interesting read at times. One additional caveat concerning this text is its data set. Although the authors suggest that these are "real" data, no references are given.Hmmmmm.

I cannot abide statistics. Not math, simply statistics. I am sure my opinions on this topic have been tainted by the books on eugenics, which I have been reading for the last two years. Having said that, I was told I needed to take a couple of measurement classes to fill my requirements for my Ph.D. (at the last minute of course...)

Two books were required reading for this course. One was this book, and the other is Reading Statistics and Research by Huck.
I'll 'get' to that book later.

This book is another typical example of a textbook that was written not to provide understandable explanations of its topic to the students who are required to buy it. Rather, it seems to be written to impress the professors and other professionals who are in the same field. It is bad enough that the book does a poor job of explaining. It skips all over the place, and uses language in such a manner as to make statistics more difficult than it absolutely needs to be. When the students read paragraphs over and over again, and still have to ask the professor for an explanation (and he provides one in a simple sentence), then something is very wrong about the text.

Not only that, but the book is chock-full of typographical errors. In many places the profesor in my class had to draw our attention to an equation which was wrong. Other typos include wrong answers obtained for data used (when everyone in the class gets the same answer and its not the one in the book you begin to wonder who proof-read this thing!) Another place, the printing got lighter and lighter, and there were equal signs missing...

The book is accessible to humanities students and covers necessary topics in statistics. However, it is important to note that the text is riddled with scientific and mathematical inaccuracies. I wrote a very polite letter to the author about the errors that I found in chapter 2, and he had the audacity to reply as copied below. I think a person has a lot of nerve to charge $118 for a third edition with significant errors, and then to mock a customer:

Date: Tue, 29 Jun 2004 18:34:54 -0600

From: Gene V Glass <glass@[blocked for privacy]>
Content-Length: 1656

nice joke. very funny.

Leah S. Gordon wrote:
> Dear Professors Glass and Hopkins,
>
> I recently purchased your book, _Statistical Methods in Education
> and Psychology_ (3rd edition) for a Statistics course at Boston
> College.
> The book was expensive (well over $100), but I had been told that
> it was a good text. I have been dismayed to find careless errors
> in the scientific examples in the text.
>
> For example, in section 2.8, the table refers to "Running Speed" but
> gives measurements in seconds (a unit of time). In section 2.5, temperature
> is given as an example of "Interval Measurement" when measured in
> degrees Fahrenheit. While technically this is a reasonable example
> of a variable that has consistent intervals and no "zero," it is a poor
> example because in fact there is such a thing as absolute temperature
> (Kelvin), with equivalencies in Fahrenheit, where there is a ratio
> correlation of heat and temperature. (By the way, you may have made
> an editorial error in referring to degrees Celsius in section 2.9 while
> you had Fahrenheit in the preceding.)
>
> (I am happy to list other errors if you wish.)
>
> I do not want to be too cranky, but I must say that I am disappointed
> to find this kind of carelessness in such an expensive and popular book.
> It would be great if I could have at least a partial refund. Please let
> me know whom to contact, as I'm sure it is not the responsibility of
> the authors.
>
> Thank you so much for your attention to this matter.
>
> Very Truly Yours,
> Leah S. Gordon