An Easy Guide to Factor Analysis
Kline, Paul. 1993. An Easy Guide to Factor Analysis. 1st ed. Routledge.
Rating:
6
Summary:
The book is, as it is titled, a guide to factor analysis – a statistical technique for reducing scale measures down to their underlying factors or concepts. The book includes a basic introduction to some of the more common statistical measures (correlations, standard deviations, etc), but quickly moves past the introduction into the heart of factor analysis. The bulk of the text focuses on factor analysis with its many variations and complications. Also included in the text is a brief chapter on confirmatory factor analysis and path analysis as they go hand-in-hand and use advanced statistical programs (e.g. LISREL).
Review:
As far as the book living up to its title, it isn’t too far off, but it kind of misses the mark on the ‘easy’ part. I think it would be more accurate to call it a ‘quick & dirty guide to factor analysis as the author doesn’t really simplify the concepts but instead just avoids lengthy explanations and theoretical discussions. The result is a bare minimum type presentation – it will give you just enough information to do factor analysis and generally understand it, but you will not be an expert on factor analysis after reading this book. For instance, while the author presents a few mathematical calculations and plenty of formulas, there is no attempt to explain why or how it works – you just have to accept that it works.
I certainly don’t want to give the wrong impression about the book. It’s not a bad book, it’s just that it is kind of awkward to read. I’m sure some of that has to do with the author being British and using some British jargon. But what I believe really makes the book awkward is the style of presentation. For some reason the author believes that after one quick explanation of a topic, he has completely explained a concept and will say something like, “Now that you have a clear understanding of that issue, I will now explain the next important thing you need to know.” Some of his explanations are pretty good and leave one with a clear understanding, but far more of the explanations aren’t quite there and could use at least one or two more attempts at it before just assuming that the reader ‘got it’. You just kind of get a sense that the author is, perhaps, a bit too confident in his ability to explain things.
The fact that he uses many of his own studies for examples of ‘what to do’ (and not ‘what not to do’) reiterates this sense. This is also reaffirmed by the constant use of absolutes. The author says things as though that is the way they are, end of story. For example, “A final example will illustrate the power of exploratory factor analysis as a statistical method” (p. 10). In this sentence, he is basically telling you that this example is all you need. Maybe I’m just used to the wishy-washy format of social scientific writing where the sentence would have said, “A final example may help illustrate the power…” Either way, this is kind of a minor criticism, even though it makes the reading of the text fairly awkward.
Overall, while this is a good introduction to the topic, it should be noted that the book assumes the reader is familiar with basic statistics (up through multiple regression analysis). In fact, I wouldn’t recommend reading this book unless you are familiar with statistics up to that point. If you can look past the odd language and aren’t particularly concerned about understanding what you are doing (just how to do it), this is a pretty good book on factor analysis.