Customer Reviews

Missing Data (Quantitative Applications in the Social Sciences)

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

 

 

I echo wired weird's comments about this monograph. Allison has written some very useful applied statistics books that often include instructions for implimenting the methods in SAS. He writes very well. The series of Sage monographs is usually of high quality, informative and concise and this one clearly fits that mold. These little and inexpensive paperback monographs are also good reference guides. You can't find anything better for under $20.

As usual, Paul Allison has produced an accessible and practical treatment of conceptual and methodological issues that commonly confound social scientists. His discussion of the meaning, effects, and remedies for missing data is thorough and clear. In particular, the section on multiple imputation is extremely well-done.

This is a reference work that will improve the scholarship of even the most rigorous researcher, and yet can serve as a wonderful introductory text on the subject of missing data for students at many levels.

Beginning stats students never see the real world of dirty data. They imagine that everyone responds fully to their surveys, and that every experiment yields legible results. Oh, for such a simple world.

Allison deals with the harsh reality of incomplete data sets. The book starts with a brief description of techniques that drop incomplete data from analysis. The large majority of the book, however, discusses ways to fill in the blanks.

The author rightly points out that "imputation", or creating values to replace what's missing, is not to be taken lightly. He gives techniques, each suited to the statistical character of some set of problems, and each matched to some technique for analysis. The mathematical goal is to create proxy values that won't upset the outcome of analysis.

That is quite a bit different from finding values that represent reality. Even though imputation is supposed to be mathematically innocuous, faking experimental data seems almost immoral to me. My data sets are about as dirty as any around. Also, they have the opposite of usual form: instead of a few dozen measurements on large numbers of samples, they have thousands of measurements on relatively few individuals. I have not convinced myself that Allison's manipulations are valid in this case. I would have been grateful for more discussion of techniques for stepping around the dropouts, and for statistically deciding whether I can ignore them.

Still, this book has worthwhile content. It's brief, clear, and informative about a very important topic. I will refer back to it, but maybe not the way the author intended.

I found the Allison book well worth the money. Consider it an overview of missing value analysis and multiple imputation (MVA/ MI). It is like seeing the forest, but not really seeing the trees.

By trees, I mean the intricacies of how to deploy MVA and MI through a standard software package. I work in SPSS, which usually has excellent documentation. I find, though, that SPSS's MVA and MI routines were much easier for me to grasp given I had read Allison's book first.

I was almost not so lucky. My university could not get SPSS installed for about a week, giving me time to discover Allison's book. The one-day shipping worked well, even to my relatively remote location.

One of the software packages Allison mentions looks to me like a beta version or a graduate student's thesis. If you know as much about MVA and MI as the software's author, it might work well enough. I, personally, would be more comfortable with something well-established and commercial like SAS or SPSS.

This is a small little volume that has a wonderful writing style showing the author's comfort that comes through in the LOGIC and COHERENCE that is so rare these days. Many authors write so badly about these things, as if to prove how smart and rigorous they are (resulting in a useless document). This writer simply spills the goods about how to handle missing data, and a brief explanation of why. The booklet is designed to help you solve the problem. It is working for me. The strategies are the same as I got in a sit-down meeting with one of our statistics professors (a senior guy who wrote a lot of papers on this subject). Since he had the same idea, this booklet appears to tell us how to carry it out. Great!

Allison spells out all of the steps to multiple imputation - I found it very helpful.