Nov

2

A L D A"Applied Longitudinal Data Analysis" by Judith Singer and John Willett is simply the best book on longitudinal studies I have read.

It is pedagogical in the extreme, clearly written with the intention to teach something practical to the reader. There is very little math, and many real world examples. The authors even manage to explain maximum likelihood estimation in plain English, without formulas!

Actually, sometimes it is so didactic, so simple, that I couldn't help thinking "come on, I am not that stupid," and found myself wishing the authors were a bit faster and less detailed. But I'd rather have it this way, than some other books that read like the author is writing for aspiring Field Medalists. And clearly, the authors have some classroom experience. Where they are slow and repetitive must be where they found their students had difficulties.

So overall, an almost perfect book and I would be happy if all statistics books were like this one.

It is missing only three things:

- A chapter about combining longitudinal analysis with advanced time series methods, for instance what happens when the individual time series are GARCH or something. This book is oriented toward medicine or the social sciences, so it is lacking a bit on time series.

- Resampling methods.

- Some R examples. The book mentions almost every statistical software under the sun, except R.

But except for the R aspect, the other subjects are perhaps a bit too advanced and could be the object of a second book. In its present state, this book can be read by someone with very little math and statistics background. Some knowledge of regression is enough to start with, and the reader walks out with the capability to perform real-world longitudinal analysis. Adding advanced stuff would be for a second book, which I hope they'll write.


Comments

Name

Email

Website

Speak your mind

Archives

Resources & Links

Search