Ngesa, O. and Ziegler, A. (2015). Review of "Analysis of Categorical Data with R". Biometrical Journal 57(3), 517-518.

    Quotes:

• This book demonstrates how to handle categorical data in R practically, and we strongly believe that it will be a valuable asset to any person who wants to analyze categorical data.
• Bilder and Loughin demystify categorical data analysis using a simple approach, with enough statistical theory to allow the reader to understand the underlying assumptions of the analyses involved, but with minimal, unintimidating mathematical symbols, and equations. The authors have managed to explain the statistics involved in categorical data analysis in unadorned semantics and accompanied them with corresponding R codes, giving categorical data analysis a practical touch.
• Overall, the book is well written: It contains easy-to-follow R codes, footnote explanations of material that could not be explained within the text, and plenty of exercises at the end of each chapter. ... An online resource accompanies the book, available at chrisbilder.com/categorical. Excellent videos of Bilder teaching the material in class, full R codes, and corresponding data, each arranged by chapter, are also available on this website. These resources make it easy for the readers to acquire a deeper understanding of categorical data analysis.
• Throughout the book, the authors approach the material in an easy-to-understand manner, which will appeal to practical users.
• This book is a must-have tool for any biostatistician analyzing categorical data in R. It could very well be used as a text in intermediate-to-advanced applied courses in practical analysis of categorical data.

 

Park, T. (2015). Review of "Analysis of Categorical Data with R". Biometrics 71(4), 1198-1199.

    Quotes:

• Unlike other CDA books, this book focuses on how to analyze categorical data properly, and it is a modern account using the vastly popular R software. The authors use R not only as a data analysis method but also as a learning tool. ... While putting emphasis on R, this book does not require any prior experience with R.
• I think this book is a well-organized self-teaching book.
• All issues on logistic regression are comprehensively covered, such as estimation and hypothesis testing. For example, odds ratio interpretation [for] interaction, even convergence issue, and Monte Carlo simulation are well described.
• Chapter 4 is for analyzing a count response. ... it covers special cases that are used to describe situations that do not fit clearly into the standard Poisson regression framework. ... I like this last part “Zero inflation” the most because it provides a good real example for clear conceptual illustration and provides a perfect solution to demonstrate how to handle it properly.
• Over-dispersion, which is one of most common phenomena in CDA, is then covered. It is very impressive that its causes, interpretations, detection, and solutions are completely described.
• In summary, I think this book is well organized and nicely written. I really enjoyed reading it ... I want to use this book as a textbook in a graduate course for CDA. This book has many advantages. Compared to other standard textbooks, its complete coverage of examples from many different research areas and the R codes would let the students ([and] other readers) become experts in CDA in fields. Use of the same examples throughout different chapters consistently provides excellent process of data analysis. Furthermore, an extensive set of exercises at the end of each chapter (over 65 pages on all) that differ in scope and subject manner would be good supporting materials for enhancing practical experiences of real data analysis.

 

Liu, I. (2016). Review of "Analysis of Categorical Data with R". Australian & New Zealand Journal of Statistics 58(1), 141-142.

    Quotes:

• I really enjoyed reading it due to its unique examples and extensive R code. The R code provided not only shows how to fit specific models, but also how to obtain further information after the model fitting is completed.
• The book would be a great textbook for advanced undergraduate or postgraduate courses, especially if training in R programming is also a learning objective.
• A self learner with basic knowledge of categorical data analysis would find the book easy to follow.
• Chapters 1 and 2 cover analyses for binary variables, including analyses based on the widely used logistic regression model. I particularly like the section that discusses the convergence problems that occur when the glm() function in R is used. In practice, researchers often forget how serious it might be to ignore the warning message: algorithm did not converge.
• By reading through the two examples [in Chapter 5], I also found useful tricks to check whether the model assumptions are valid.
• The last chapter deals with several additional topics and their applications using R. Among these topics is one to which Bilder and Loughin have made a significant research contribution, namely the analysis of ‘choose all that apply’ data where respondents may select more than one response item. This has many practical uses in the analysis of surveys.
• Given the series of in-class videos provided on the associated website and all the R code available online at http://chrisbilder.com/categorical, there is no doubt that this book would be a great textbook. Personally I would like to congratulate Bilder and Loughin on the writing of this valuable book. Even before I had finished reading the book, I had already recommended it to my students. Now, I highly recommend this book to all readers.

 

Liu, S. (2016). Review of "Analysis of Categorical Data with R". International Statistical Review 84(1), 162-163.

    Quotes:

• This book presents an extensive introduction to analysis of categorical data with R. The context is relevant for a multitude of application areas such as biology, ecology, medicine and sports just to name a few.
• Throughout the book, R is used not only as a data analysis tool but also as a learning tool.
• The book takes an easy-to-understand approach by partnering practical explanations with numerous illustrative examples. These step-by-step examples are supportive and cover the underlying definitions, ideas and methods behind the practical data analysis using R code. A number of examples use the same data set, but each example focuses on a different aspect, giving students a broader understanding of the data set.
• To help students apply their knowledge, the book has also provided an extensive number of exercises.
• The book has a website http://www.chrisbilder.com/categorical with the data sets and R code used for the worked examples and also the authors’ in-class recorded lectures, which supports students to be flexible in their learning. The textbook can also be a very useful reference.

 

Endorsement by Deborah Rumsey, Professor in the Department of Statistics at Ohio State University

Bilder and Loughin have worked as a dynamic duo for a number of years, and they clearly are blending their knowledge, talents, experience, and teamwork to create this valuable book. Analyzing categorical data correctly and in-depth is not as simple as it appears in many courses and textbooks. As a result, many people can get the wrong idea about what could and should be with categorical data, and hence their results can be inconclusive or incorrect. This book gives users the full scoop when it comes to analyzing categorical data of all types, and it does so in an easy to understand way, giving confidence to the reader to go ahead and apply the ideas in practice. The use of R for analyzing data is becoming a worldwide phenomenon and a staple for data analysts on every level. As its popularity grows, it becomes critical for beginners to become comfortable with understanding and using R to analyze their data. Through the special attention paid to teaching the basics of R, as well as providing step-by-step particulars in using R in each separate analysis, Bilder and Loughin help establish and promote a group of confident, comfortable users of this software that can seem a mystery to many. I highly and happily recommend this book to anyone who plans to analyze categorical data in their careers – which includes most all of us!