Data Analysis Using Regression and Multilevel/Hierarchical Models

Analytical Methods for Social Research

by Andrew Gelman, Jennifer Hill

Data Analysis Using Regression and Multilevel/Hierarchical Models is a comprehensive manual for the applied researcher who wants to perform data analysis using linear and nonlinear regression and multilevel models. The book introduces a wide variety of models, whilst at the same time instructing the reader in how to fit these models using available software packages. The book illustrates the concepts by working through scores of real data examples that have arisen from the authors' own applied research, with programming codes provided for each one. Topics covered include causal inference, including regression, poststratification, matching, regression discontinuity, and instrumental variables, as well as multilevel logistic regression and missing-data imputation. Practical tips regarding building, fitting, and understanding are provided throughout. Author resource

Genres: Science, Mathematics, Reference, Textbooks, Nonfiction, Technical, Artificial Intelligence

648 pages, Paperback

First published December 1, 2006

Reviews

[A Mig]

Obviously a go-to book for multilevel modelling but far from my favourite books on statistics. First, one should pass all the sections on probability distributions and linear regression, since there is much better elsewhere on the same topic (and with R codes), such as 'An Introduction to Statistical Learning: With Applications in R'. One should then start reading this book at chapter 9. The causal inference view was very interesting and I especially enjoyed the simple R snippets on propensity scores. Yet, I remain unsatisfied, not really sure why.

[Terran M]

This is my recommended book on multilevel models, and it's also much more than that. Even if you have no interest whatsoever in multilevel models, the first part of this book has very useful things to say about designing and interpreting experiments for causal inference, a topic which is sorely neglected in many modeling and machine learning books.

One caveat is that all the MCMC examples in this book use Bugs, which was Windows-only and is now somewhat obsolete. You should not actually use Bugs, but rather JAGS instead, which is mostly syntax-compatible.

[Dan]

Now I feel the gravity of names Gelman and Hill.
I thank them for sharing their thinking processes with detailed examples.
It was not an easy read, it took a very long time, I skipped many details, and sometimes needed my patience. It was rewarding as much as it was challenging to read.
The book will serve as a guide to my data journey.

[Jenna]

First rate statistics reference! This book cleared up many things I did not understand concerning linear regression modeling.

[Kathryn Morrison]

We read this as part of a statistics book club and I enjoyed it a lot. I wish it had solutions to the exercises and went into a little more theory.

[Steve]

This is the one I recommend to people for practical regression help, and it's the one I go to when my brain stops working and I need to refresh myself on the basics of mixed-effects regression modeling. Probably the only stats book that is (a) practical and focused on reasoning about the data and model rather than "procedural" ; and (b) opinionated about how you should think about your data and modeling without being dogmatic. Detractors will probably say there's not enough rigorous theory or that the R code examples aren't exactly boilerplate, but the whole point of the book is to provide a foundation for reasoning about data rather than the former or latter. It's focused, with very little extraneous information and avoids spending too much time on narrow technical details that are not generalizable to practical data analysis. Overall, highly accessible and probably the best textbook I use for basic statistical modeling.

[Harlan]

A good comprehensive survey of the topics. But, different sections assume different levels of background knowledge, from nearly nothing to grad-level statistics theory. I like their views on the relative importance of modeling vs. hypothesis testing, and in particular the emphasis on graphs/visualization. Also like the use of R/lmer and BUGS, and am sympathetic to their somewhat critical view of the terminology of mixed-effects models, despite the close connection to their preferred Bayesian view.

[Asa]

This is my favorite statistics book, written by a former professor at the Columbia stats department. Its my number 1 reference book on my desk at work.

Lots of coding examples with R in applied contexts. Great with interpreting model results, model building, and running diagnostics. Limited matrix alegebra is a plus for those of us who arent very interested in the proofs. For quantitative social science stuff if I had to pick one book this would be it.

[Justin]

Excellent reference.

[Jeff Carnegie]

So far the overview of regression has been great.

[Jewel]

One of the best books on multi-level models. It was a great read and I loved the examples.

[Iakovos (Jake)]

Read read read it. The bible of stats. Essential. It helped me a lot in Social sciences. I had a non mathematic background.