Customer Reviews

Psychometric Theory

5 star:		(2)
4 star:		(1)
3 star:		(4)
2 star:		(3)
1 star:		(0)

 

 

I am in a management PhD program and we have to read this book for our required class in psychometric theory. I totally agree with one of the other reviewers that almost no term is clearly defined by Nunnally and Bernstein in this 3rd edition. The book goes on and on and on talking about validity, reliability, scaling, ... without defining any single term in a concise manner. It is very frustrating!
So, my suggestion for everyone is to get the 2nd edition. I read it and was happily surprised. Nunnally is great, Ira Bernstein messed the 3rd edition up (Nunnally died a while ago and Bernstein was responsible for the writing of this edition). The previous edition is much, much shorter and has better organized chapters that go right to the point (well, relatively speaking ). In addition, I recommend several short Sage books (e.g., factor analysis from Kim and Mueller), which are much clearer.
In any case, this book or better the 2nd edition, is a must have for any social science researcher (or wanna be researcher ).

The thing I most admire about Nunnally is how well his work holds up even decades after the book was first written, and Nunnally's own death. Although academic works such as this typically have a half life of two or three years, it seems that Nunnally may be even more useful now than it was twenty-five years ago. There are other books that address the same type of material, but they all cite Nunnally, and none have, as yet, effectively replaced him.

It's a very concise book and describes the theory in a very didatic way. The only problem of the book is the little enphasis to the Item Response theory (IRT).

This is one of the landmark Measurement books for Psychologists. It does present a relatively comprehensive treatment of the issues facing researchers when developing measures. Unfortunately, the style of writing used in the book makes it exceedingly difficult for students to extract the useful information from the chapters. Specifically, the chapters are not particularly well organized - particularly the ones with fewer equations in them - often jumping back and forth between topics rather than presenting them more systematically. Furthermore, the prose explaning concepts and equations is basically written in an overly complex and sometimes cryptic style more appropriate for mathematicians and psychologists from the 1950's than for graduate students or modern consumers. I only bought the book to augment the graduate level measurement class that I teach and despite the fact that I have a solid background in mathematics, I grown inwardly every time I have to pick up a chapter in this book and read it.

I'm in a Ph.D. program, and this is the required reading for our psychometric testing course. I was looking on the Border's web site to find a different book to read that would cover the same material, that would not be so difficult to understand. Nunally has a nasty habit of poorly defining terms, which makes it extremely difficult to grasp what he is talking about. It's challenging enough to understand psychometric theory, let alone with a practically illegible textbook! This book needs rewriting! I've given it two stars because supposedly the book contains a lot of valuable material. Of course, this doesn't matter one whit when you can't even read the darn thing!
So professors, please, don't do this to your students!!!

I can tell the book is very comprehensive.
But the book lacks examples and the wording makes it more difficult for the readers to follow.

I bought the book b/c I had read parts of the 2nd edition of Nunnally's book and loved how well he organized his points and related psychometric theory together. I think the new author may have screwed the book up by inputting (his/her) own jargon. I HIGHLY RECOMMEND ANYONE INTERESTED IN THIS BOOK TO GET THE 1st or 2nd EDITION - don't make my mistake. Nunnally passed away in 1982 and this is copyrighted 1994 ... stick to the work he did when he was alive.

As have several other people who have reviewed this book I would suggest purchasing the 2nd edition. I have both of them sitting side by side on a shelf and use the 2nd edition much more than I use the 3rd one. It is not written in as clear a manner as the 2nd edition and sought to expand beyond psychometric theory which might have watered it down some. I was surprised that the reviewer who wrote that the 3rd edition is longer than the 2nd is correct as the 2nd is thicker - but it does have fewer pages.

Way back in the late '60's when I was a graduate student I was trying to master a now-antiquated technique called scalogram analysis. The procedure had been used by sociologists as quantitatively sophisticated as the late Paul Lazarsfeld in producing widely read research such as that included in the classic multi-volume work The American Soldier (1950).

Scalogram analysis is really a pretty simple technique for creating ordinal level attitudinal variables. It comes with a variety of measures, called coefficients of reproducibility, normed to range between 0 and 1, which purport to gauge the reliability of the variables created, such as tolerance of ethnic diversity. This technique always seemed like an iffy and unduly contrived way of measuring attitudes and creating variables to be used in statistical analyses. Still, it had the saving grace of reasonable looking coefficient(s) of reproducibility. When challenged, analysts could always look to a coefficient of reproducibility and say something like "Yeah, but it's pretty reliable. We got a coefficient of reproducibility value of .80 for a statistic that maxes out at 1.0"

In 1954, however, the psychologist Leon Festinger published an article in which he demonstrated that, given the way coefficients of reproducibility were calculated, values as high as .85 could easily be achieved just due to chance. One response to this challenge to the utility of coefficients of reproducibility, and, by implication, scalogram analysis itself, was publication of two articles in a 1959 edition the journal Psychometrica, one by Philip Sagi and the other by Leo Goodman, that presented tests of statical significance for some measures of reproducibility. I found the articles unreadable, and hoped to find a source that would provide clarification.

By chance, I stumbled across the first (1967) edition of Nunnally's Psychometric Theory. Nunnally's book did not address the issue of tests of significance for coefficients of reproducibility, but I was stunned by the clarity of Nunnally's prose. All of a sudden, measurement, a topic I had found unfathomable and deadeningly boring came to life. Nunnally was a gifted writer who made complex technical material accessible even to those of us who had little or no talent for that sort of thing. Reading it made me feel empowered.

Publishing textbooks is a money-making racket, so when Nunnally died, his publisher recruited a co-author, Bernstein, to periodically update Nunnally's book. Bernstein may be an unusually accomplished tests and measurement guy, but his prose rendering of technical material is not nearly as lucid as Nunnally's. I doubt that Bernstein tries to make measurement more difficult than it has to be, but he definitely lacks Nunnally's gift for making technical material understandable.

Psychometric Theory has gotten thicker, covering more material over the years. Nevertheless, if I were starting out or starting over, I'd try to find a copy of Psychometric Theory published before Nunnally's death in 1982, after which he posthumously acquired a co-author. Nunnally's first edition still provides a solid treatment of classical testing theory. Who knows? You may find all you need for your specific purposes in an earlier edition, saving yourself a lot of grief and, with any luck, a lot of money. Textbook publishing really is a racket.

This is the kind of text that anyone who's heavily involved in educational measurement needs to own! It truly is a classic text, and is both full of information and accessible.