The book title is an excellent starting point for the reader to assess whether this is the resource for her but not the only mechanism. The book cover or sleeve synopsis and publisher description can also fail to capture the whole story, and some statistical treatises, both introductory and advanced, necessarily invoke related principles and topics [13]. As the objective expert of that specific text, an introduction to the necessity, scope, depth, and breadth of the topic in general can inform the reader on the challenges and solutions, including types of data or domains of inquiry that this field examines. Place the work within the span of the literature with a brief explanation of the area in which it is embedded. The goal of the first rule is therefore to ensure that the reader is in right place—conceptually, at least.

Most technical book reviews state the level of expertise required by the reader. This is a critical form of synthesis that should be mentioned, even in brief, in a book review for statistics. The most typical categories range from introductory to advanced, with relatively higher-level offering described by “graduate student” and beyond as the reader. If the text is a blend of theory and practice with significant programming, the review should further explain the relative expertise needed for each and whether both dimensions are aligned in the assumed relative audience. Book reviews can also take the opportunity here to frame this assessment by the expertise of the referee (i.e., it is sometimes useful to know if the book reviewer is a statistician, a programmer, or a domain-specific end-user) or by the intended use of the text, such as primer, guide, in-depth treatise, or textbook appropriate for instruction at a given level.

If more than one edition exists, it is useful to describe the revisions to the more recent version of a book. Professional and teaching textbooks can be relatively expensive, and a critical assessment of value can provide instructors with the merits associated with potentially higher costs to students of purchasing a newer text. At minimum, a list of additions will facilitate a more informed choice for the reader and instructor, and mention of case studies, updates to code and data sets, and addition of supplements are all important criteria for the choice to learn or seek solutions from a specific edition.

Organization of the content matters to all learning [15], and content provides context [16]. The structure of statistical and programming texts can vary significantly. The length and complexity of chapters, use of headings and subsections within chapters, and end-of-chapter summaries are not always needed but often do no harm. Case studies, appendices, data sets, and location of supplements and supporting materials should be described. Contemporary texts in statistics are often a hybrid of print and electronic resource materials, and description of the extent that a text functions in this capacity can influence the decision by the reader based on her preferred modality of learning and the rationale for exploring this topic. This is also a good place to mention the different formats of the book (if available in print and online). As the reviewer, use parsimony and caution in deciding what level of detail to describe for the structural elements of a book—focus only on those elements that promoted the most effective learning.

These are the results, so to speak, similar to a conventional scientific publication or study report. The description should be brief, topological, and highlight the most substantive elements of the book. This component of the book review need not be unduly critical but should provide an overview of the what the text offers. Some reviews take this description of what is done to also highlight what is done best and list the most valuable chapters to the reader. This can be a useful guide to the potential reader and a means to assess expectations from the book as a whole. If there are data sets or case studies that are revisited throughout the book or across multiple chapters, the extent that the chapters connect to one another can also be summarized. Mention whether the content of the book is serialized or if chapters can be read piecemeal.

Readability is an intuitive concept. It is the ease that one can comprehend writing [17, 18]. Complexity in syntax, vocabulary, and sentence structure should be described in a review of a statistical book. A technical book need not be a technical challenge to read. More broadly, appeal, style, and interest are important to all but the most committed readers, and it is reasonable to assume that a book on statistics provide some sense of enthusiasm for the topic, compel the reader to think deeply, and engage one with the challenges explored. Composition is critical, particularly in long-form writing endeavors.

Within the R statistics community, there are now over 11,000 packages that extend the base language archived on https://cran.r-project.org. SAS Procs and libraries in Python and MATLAB are also extensive. Some statistical texts are associated with not only a single statistical program or language but with a single package or library. A review of a statistical book should thus describe the specificity of the book, explain the extent that the book relies on single solution sets, or conversely contrasts alternatives in different languages, applications, packages, and/or libraries, and frame the programming (if provided) to general statistical theory and reasoning. At times, this can be self-evident if the title of the book includes mention of the programming language or software, but the breadth of the statistics and case studies illustrated is typically not evident without review of the book. If the book is not tied to a specific computation tool in any form, then the reviewer should mention that this is the case and state that the concepts described can be applied and transferred broadly from the book.

Compare and contrast. There is a wealth of both short- and long-form documentation available for many open coding languages used in statistics and data wrangling. There is also an extensive opportunity to seek specific solutions through numerous forums such as Stack Overflow (https://stackoverflow.com/questions/tagged/statistics), Cross Validated (https://stats.stackexchange.com), and Stack Exchange Mathematics (https://math.stackexchange.com). Online tutorials, blogs, carpentries, massive online open courses (MOOCs), and webinars often provide useful, and at times, deep-learning opportunities. A book review will certainly not comprehensively list all these options and compare and contrast to the principal subject text discussed, but if there is a significant alternative to consider, it should be mentioned. Finally, there are also other books. The reviewer should explicitly state the extent that she is contrasting to other resources, and due diligence by the reviewer suggests at the minimum a mention of the relative novelty and niche of the text in question.

Reading a book is a relationship. The content, style, and perspective of the author(s) becomes a shared, internalized form of knowledge in a good book. As the reviewer, it is legitimate and useful to others to mention the extent that one enjoyed the text, connected with the writing and concepts, or struggled with certain elements (i.e., comment on the quality of the relationship with the book). A review should also mention the time that the reader should set aside to read and/or fully digest the content. If the “summarize content” rule proposed above did not mention the standout, best chapters, this is an excellent spot to describe the chapters that provided the most for your buck and should not be skipped. This is also an ideal opportunity to consider describing whether this is was a read-the-book-straight-through or piecemeal technical read for critical needs.

In general, it is best to be decisive in writing reviews [9]. Evaluate the capacity that the book delivers on its stated goal. Accept that you are part of the review process and likely have your own, specific purpose in reading this text. Admit this in the review by articulating the need, success of text, and decision (or not) to use the described tools, framework, or theory. Being specific and listing criteria point-by-point is useful to editors, authors, and readers [9]. Similar to the peer review process for papers, be balanced, fair, and professionally critical by mentioning both strengths and weaknesses from your perspective. Do your best to reveal implicit biases in your review.