To paraphrase a popular political meme, “What should entry-level data analysts know and when should they know it?” And then, how should they learn it? Certain data exploration and analysis programming skills, for R, Python, and SQL, are obvious starting points, and there are now dozens of books focused on those topics titled “X for data analytics” or “X for data science” where “X” is one of those three programming tools. Authors of these books include academics and industry practitioners, each taking their own approach to data analytics instruction, for beginner through expert level. There is no ideal, one-size-fits-all methodology for such learning, whether through self-study, commercial and free online courses and certifications, or academic degree programs. So, if you are looking for references to learn or to teach data analytics, you’ll need to evaluate multiple sources for content, level, and presentation style to find an effective strategy for successful learning.

One popular series of books comes from Murach, the well-known publisher of textbooks for 40-plus years covering more than 50 programming languages and methods, including two specifically for data analysis, one for Python and one for R.

Scott McCoy is the author of Murach’s R for data analysis, his first book for this publisher. It is definitely directed at beginners with “basic computer literacy,” yet starts with two programming-focused chapters on the R language, including work environment setup using RStudio, and then a (perhaps premature) detailed coverage of R functions, data structures, expressions, and control statements. A simpler lead-in to what’s needed just to start dataset analysis might be better for learners who have never written code in any language. However, once past that hurdle, the author presents well-structured and illustrated analysis examples, including dataset intake from various source types (CSV, Excel, database, and JSON), data transformation and cleaning, and basic summary statistics and visualizations. Later chapters cover a variety of analytics case studies with relevant accompanying R code examples and output. There is a section on modeling, covering simple and multiple regression and classification, but this should probably be paired with supplemental instruction on basic statistics and more coverage on data types and how to properly interpret statistical test values.

There are many code and visualization examples in the book, and it can certainly serve as a reference for students getting started with data exploration. The final section on presentation skills using Jupyter-like R Markdown has useful advice and examples.

Each chapter ends with a summary and exercises, and two appendices show how to set up the work environment and required R packages on either Microsoft Windows or Apple’s macOS. The publisher’s website for the book includes example datasets and R source code, along with exercise hints and solutions. Overall, this contribution to the growing library of “how-to” books for data analysis is well organized and attractively presented for its target readers. Review it along with similar texts to match your students’ backgrounds, learning objectives, and instructional style.

More reviews about this item: Amazon