No. 248 of 500 No. 43 in Machine Learning

Practical Statistics for Data Scientists

50 Essential Concepts

By Peter Bruce, Andrew Bruce and Peter Gedeck

Published
June 16, 2020
Print length
360 pages
Reading level
Intermediate
ISBN-13
978-1492072942
Publisher
O'Reilly Media
Written for
Working data scientists and analysts who know R or Python but lack formal statistical training.

Synopsis

Statistics underlies nearly every data science technique, yet practitioners who come from programming or engineering often learned it piecemeal. Peter Bruce, Andrew Bruce and Peter Gedeck wrote this compact reference for them, organizing it around more than 50 concepts that working analysts actually use. Chapters move from exploratory data analysis and sampling distributions through experiments and significance testing, regression, classification, statistical machine learning and unsupervised learning. Each concept is defined with its key terms, explained in plain language and demonstrated in code.

The first edition, published in 2017, used R; the 2020 second edition adds parallel Python examples throughout. The authors explain where classical statistics matters less in data science, such as formal inference on very large samples, and where it remains essential, including sampling bias, experimental design and regression diagnostics. Readers gain a working vocabulary for collaborating with statisticians, a clearer sense of why models mislead and a quick refresher to keep near the keyboard. O'Reilly listed a third edition for mid-2026 under a new title, AI-Assisted Statistics for Data Scientists, with added chapters on neural networks, deep learning and large language models.

Scorecard

Editorial score

How it scored

Editorial score: 74.1 / 1005 weighted criteria

  • Influence30%

    22.5/30
  • Authority25%

    18.8/25
  • Practical value20%

    16.0/20
  • Currency15%

    9.8/15
  • Readability10%

    7.0/10
  • Editorial score

    74.1/100

How the rank was computed

Rank No. 248 of 500 comes from a composite of 55.0: observable signals 21.7 of 55 points plus editorial review 33.3 of 45 points.

All 11 inputs
InputPoints
Observable signals21.7/55
Reach (Amazon ratings volume)11.0/16.5
Consensus across best-of lists2.8/13.8
Awards and bestseller evidence0.0/8.3
Reader rating, sample-adjusted6.8/8.3
Amazon sales rank1.1/5.5
Recency0.0/2.8
Editorial review33.3/45
Author authority8.4/11.3
Influence10.1/13.5
Practical value7.2/9.0
Readability3.2/4.5
Currency4.4/6.8

Each criterion is scored from 1 to 10 and weighted, and the points add up to the editorial score. The rank combines observable signals (55 percent) with this score (45 percent). Read the methodology.

Verdict

A compact, practitioner-focused statistics reference that explains which classical methods matter for data science and which can safely be skipped.

Strengths

  • Concise coverage of 50-plus essential concepts
  • Side-by-side R and Python code examples
  • Clear guidance on what matters in practice

Keep in mind

Explanations are brief, and some code and figures appear with little commentary, so readers without basic statistics may need a gentler companion text.

Key takeaways

  1. Exploratory data analysis comes first: summary statistics, distributions and simple plots reveal data problems before any model is fit.
  2. Random sampling and attention to selection bias still matter with big data, because a huge biased sample yields confidently wrong answers.
  3. Resampling methods such as the bootstrap and permutation tests offer intuitive, computation-based alternatives to formula-driven inference for many practical questions.
  4. Regression and classification models should be judged with diagnostics, cross-validation and attention to unbalanced classes, not by fit statistics on training data alone.

Notable facts

  • Elder Research describes the first edition as an O'Reilly best-seller that was translated into Japanese. Source (opens in a new tab)
  • A third edition, retitled AI-Assisted Statistics for Data Scientists and adding chapters on neural networks, deep learning and large language models, was listed by O'Reilly for July 2026. Source (opens in a new tab)

About the author

Peter Bruce, Andrew Bruce and Peter Gedeck

Peter Bruce founded the Institute for Statistics Education at Statistics.com and holds degrees from Princeton, Harvard and the University of Maryland. Co-author Andrew Bruce is a principal research scientist at Amazon with a statistics PhD from the University of Washington. Peter Gedeck, a senior data scientist at Collaborative Drug Discovery, holds doctorates in chemistry and mathematics and co-wrote Data Mining for Business Analytics.

Questions

What is Practical Statistics for Data Scientists about?
The book is a concise reference to the statistical ideas data scientists use most. It covers exploratory data analysis, sampling, experiments and significance testing, regression, classification, statistical machine learning and unsupervised learning. Each concept is explained briefly and illustrated with R and Python code, with notes on which classical methods matter in data science work and which matter less.
Is Practical Statistics for Data Scientists good for beginners?
It suits readers who already code in R or Python and have met basic statistics, rather than complete beginners. The explanations are compact and some code samples carry little commentary, so newcomers may want an introductory statistics text alongside it. For analysts and engineers moving into data science, it is an efficient way to fill gaps in statistical reasoning.
Should I buy the second edition or the newer AI-Assisted Statistics for Data Scientists?
The 2020 second edition remains a solid guide to core statistics with R and Python. O'Reilly's 2026 successor, retitled AI-Assisted Statistics for Data Scientists, keeps the same 50-plus concept structure but adds chapters on neural networks, deep learning and large language models. Readers who want that newer material should choose the third edition; others can rely on the second.

Sources

As an Amazon Associate, Best AI Books earns from qualifying purchases. Best AI Books is sponsored by Iternal.ai, whose founder and CEO, John Byron Hanby IV, wrote The AI Strategy Blueprint, our #1 ranked book. How we rank books.