Regression Modeling Strategies (Hardcover)

~ Frank E. Harrell (Author) "Statistics comprises among other areas study design, hypothesis testing, estimation, and prediction..." (more)
Key Phrases: restricted cubic spline function, sibsp parch, function analytic representation, Higher Order Factors, Kaplan Meier, Dxy Gamma Tau-a (more...)

Editorial Reviews

Review

From the reviews:

TECHNOMETRICS
"The book is an ambitious, and mostly successful, attempt to disseminate effective strategies for the use of regression techniques. Many of the examples are from the medical area, in which the author has worked for many years and has accumulated a wealth of experience. It is written in a clear and direct style…definitely a valuable reference for modern applications of commonly used regression techniques. Data analysis, particularly users of S-PLUS, with experience in the application of these tools will benefit the most from this book."

SHORT BOOK REVIEWS

"This is a book that leaves one breathless. It demands a lot, but gives plenty in return.  ... The book has many sets of programming instructions and printouts, all delivered in a stacato fashion. Sets of data are large. Many different types of models and methods are discussed. There are many printouts and diagrams. Computer oriented readers will like this book immediately. Others may grow to like it. It is an essential reference for the library."

STATISTICAL METHODS IN MEDICAL RESEARCH

"This is the latest volume in the generally excellent Springer Series in Statistics, and it has to be one of the best. Professor Harrell has produced a book that offers many new and imaginative insights into multiple regression, logistic regression and survival analysis, topics that form the core of much of the statistical analysis carried out in a variety of disciplines, particularly in medicine. ... Regression Modelling Stategies is a book that many statisticians will enjoy and learn from. The problems given at the end of each chapter may also make it suitable for some postgrdauate courses, particularly those for medical students in which S-PLUS is a major component. Working through the case studies in the book will demonstrate what can be achieved with a little imagination, when modelling complex and challenging data sets. So here we have a truly excellent, informative and attractive text that is highly recommended."

MEDICAL DECISION MAKING

"Over the past 7 years, I have probably read this book, on its preversion, a half-dozen times, and I refer to it routinely. If my work bookshelf held only one book, it would be this one. The book covers, very completely, the nuances of regression modeling with particular emphasis on binary and ordinal logistic regression and parametric and nonparametric survival analysis...Harrell very nicely walks the reader through numerous analyses, explaining and defining his model-building choices at each step in the process. It is refreshing to have an author present choices and actuallly defend an approach, and in this manner."

"This book emphasizes problem solving strategies that address the many issues arising when developing multivariable models … . The author has a very motivating style and includes opinions, remarks and summary … . The logical path chosen on how to present the material is excellent. … considering the fun I had reading the book, I think that the author’s aims are met and I highly recommend everybody to have a look at the book. Moreover, I recommend purchasing the book to any library." (Diego Kuonen, Statistical Methods in Medical Research, Vol. 13 (5), 2004)

"It is a book that tries to show us how many different tools may be used in combination for regression analysis. … The author gives us plenty of references (466!) to textbooks and papers where we may read more about individual topics; most chapters end with suggestions for further reading and problems. … Many tools are illustrated in five chapter-long case studies. … the author has written a very inspiring book which should be able to teach most of us something … ." (Søren Feodor Nielsen, Journal of Applied Statistics, Vol. 30 (1), 2003)

"This book could serve as a wonderful textbook for a graduate-level or upper undergraduate-level data-analysis class. There are plenty of hands-on exercises … . From a researcher’s perspective, there are enough interesting ideas to easily stimulate research on other fruitful avenues. From an applied statistician’s perspective, the book fills an important gap in the field and would serve as an ideal resource. … a well laid-out, enjoyable book. I wholeheartedly recommend it … to anyone interested in the strategies of intelligent data analysis." (Sunil J. Rao, Journal of the American Statistical Association, March, 2003)

"Regression Modeling Strategies is largely about prediction. … The book is incredibly well referenced, with a 466-item bibliography. … Harrell very nicely walks the reader through numerous analyses, explaining and defining his model-building choices at each step in the process. It is refreshing to have an author present choices and actually defend an approach … . I found his arguments very convincing. Certainly, if you are interested in developing or validating prediction models, you will likely find this book to be very valuable." (Mike Kattan, Medical Decision Making, March/April, 2003)

"Professor Harrell provides descriptions of statistical strategies intended for the analysis of data using linear, logistic and proportional hazard regression models. … Harrell combines statistical theory with a modest amount of mathematics, data in the form of case studies, implementation of regression models, graphics and interpretation making it attractive to Masters or PhD level graduate students as well as biomedical researchers. … this is an excellent book for serious researchers." (Max K. Bulsara, Lab News, August/September, 2002)

Product Description

There are many books that are excellent sources of knowledge about individual stastical tools (survival models, general linear models, etc.), but the art of data analysis is about choosing and using multiple tools. In the words of Chatfield "...students typically know the technical details of regressin for example, but not necessarily when and how to apply it. This argues the need for a better balance in the literature and in statistical teaching between techniques and problem solving strategies." Whether analyzing risk factors, adjusting for biases in observational studies, or developing predictive models, there are common problems that few regression texts address. For example, there are missing data in the majority of datasets one is likely to encounter (other than those used in textbooks!) but most regression texts do not include methods for dealing with such data effectively, and texts on missing data do not cover regression modeling.

Product Details

• Hardcover: 600 pages
• Publisher: Springer; Corrected edition (January 10, 2001)
• Language: English
• ISBN-10: 0387952322
• ISBN-13: 978-0387952321
• Product Dimensions: 9.4 x 7.1 x 1.3 inches
• Shipping Weight: 2.5 pounds (View shipping rates and policies)
• Average Customer Review: 4.7 out of 5 stars  See all reviews (9 customer reviews)
• Amazon.com Sales Rank: #448,223 in Books (See Bestsellers in Books)

Customer Reviews

Most Helpful Customer Reviews

26 of 26 people found the following review helpful:

5.0 out of 5 stars advanced topics in regression with emphasis on model selection, January 23, 2008

By	Michael R. Chernick "statman31147" (Holland PA) - See all my reviews (REAL NAME)

Frank Harrell is a Professor who does a lot of consulting in medical research. This book covers a wide variety of topics in regression analysis including many advanced techniques including data reduction, smoothing techniques, variable selection, transformations, shrinkage methods, tree-based methods and resampling. But note the title "Regression Modeling Strategies". Unlike most advanced texts in regression this book emphasizes modeling strategies. So the focus is on things like variable selection and other techniques to avoid overfitting models and diagnostics to look for violations in assumptions such as variance homogeneity or normality and independence of residuals, or stability problems like colinearity.
The book covers an extensive collection of modern techniques for exploratory data analysis. Inferential methods are also considered and he deals appropriately with important issues (particularly for medical research) such as imputation of missing values. Many examples are considered and illustrated in S-PLUS.

Harrell also provides many rules of thumb based on his own experience building models. A lot of the techniques are illustrated using data from the Titanic where it is interesting to see which factors affected the probability of survival. My only disappointment was that there is perhaps too much emphasis on this one particular data set.

A standard regression text would be expected to include linear and nonlinear regression. Harrell goes much deeper including nonparametric regression, logistic regression and survival models (e.g. the Cox proportional hazards model).

32 of 36 people found the following review helpful:

4.0 out of 5 stars You need to be an expert in statistics to understand this.., September 20, 2001

By A Customer

This is clearly an advanced text that mathematicians and PhD students in statistics would find valuable. It is not for an engineer or novice statistican in industry (like myself) who has to come up with an accurate regression model with quantitative and qualitative data in a short period of time. My rating is four stars: buy this book only if you have the advanced statistical training to understand it, otherwise buy a simpler book if you want to get a basic understanding of the subject.

10 of 10 people found the following review helpful:

4.0 out of 5 stars Practical and insightful, January 30, 2006

By	Brant Inman (Somewhere out there) - See all my reviews (REAL NAME)

This is a very special statistics book and is unlike any other that I have encountered. Instead of being focused on a specific statistical technique (or family of techniques), Harrell presents a wholistic view of regression modeling for describing real datasets. He starts with the basics of regression assumptions and techniques (splines, shrinkage, etc...), moves on to data management (imputation and reduction), and then addresses the specifics of linear regression, binary logistic regression, ordinal logistic regression, parametric survival regression and Cox regression. Each regression method is approached first with a clear explanation of what the technique is doing and what the critical assumptions are. Then, Harrell demonstrates how to do the analysis in S-Plus/R using a real dataset.

Though I lack the advanced mathematical background necessary to fully explore many statistical textbooks, I did not find this to be a problem for this one. The presentation is that of a teacher: clear with developed reasoning. The production of nomograms was a particularly useful exercise and the S-plus code was also very useful.

I find his opinions on model building strategies to be well though out and persuasive...though I suspect that many may find them controversial. Overall, this is one of the best statistics books that I have purchased.