Liberty Vittert's illustrated primer on 50 data science ideas and uses, from regression and sampling bias to dating apps, each in a short entry.
30-Second Data Science belongs to Ivy Press's 30-Second series, where each topic gets a single illustrated spread meant to be read in a few minutes. Edited by statistician Liberty Vittert, a professor of the practice of data science at Washington University in St. Louis, with entries written by a group of contributors, the 160-page hardback was published in September 2020.
The book is less a course than a tour. A short first section explains basic ideas such as data collection, visualization, regression, clustering and neural networks, and a second covers uncertainty: sampling, correlation, confidence intervals, overfitting and bias. The rest shows data science at work in science, society, business and everyday life, with brief profiles of figures such as Florence Nightingale, Ada Lovelace and John Tukey.
This is a reference to dip into. Entries are self-contained, so you can open it at any page, read one idea in a few minutes and move on. Reading the Basics and Uncertainty sections first gives the vocabulary that the application entries use, but it is not essential. Each section opens with a short glossary, so it is worth scanning that page before the entries. For a classroom or study group, a single entry makes a good warm-up: read it together, then ask where the same idea shows up in your own work or data. If an entry sparks real interest, follow it up with a full guide or course on that topic, since the book deliberately stops after the core idea.
The book suits curious beginners, students deciding whether to study data science, managers who want a quick sense of the field, and teachers looking for short readings to spark discussion. It also makes a good gift for non-specialists.
It will not teach you to do data science. There are no exercises, no code and only brief explanations of methods, so anyone who already works with data will find it too light.
Pros
Cons
Is this book for beginners? Yes. It assumes no background in statistics or programming.
Does it cover generative AI? No. It was published in 2020, before tools like ChatGPT became widespread.
How does it compare with Naked Statistics? Naked Statistics explains statistical reasoning in more depth through longer stories. This book covers more topics in much less detail.
Is it a textbook? No. It is an illustrated primer for general readers.
Check current editions and prices if you want a light, illustrated introduction to share with someone new to data.
Cole Nussbaumer Knaflic's widely-recommended book on data visualization, teaching chart selection and narrative structure through real.
A Python textbook by Shmueli, Bruce, Gedeck and Patel on machine learning for business, from prediction to text mining and generative AI.
Sharda, Delen and Turban's managerial textbook covering BI, descriptive, predictive and prescriptive analytics, AI tools, and the ethics of analytics.
