Further Reading: Communicating Results: Reports, Presentations, and the Art of the Data Story

Communication is a skill that improves with study and practice. The resources below range from foundational books on data storytelling to practical guides on writing, presenting, and visualization design. Many data scientists cite these books as transformative for their careers.

Tier 1: Verified Sources

Cole Nussbaumer Knaflic, Storytelling with Data: A Data Visualization Guide for Business Professionals (Wiley, 2015). The single most recommended book on data communication for practitioners. Knaflic, a former Google data analyst, teaches how to transform cluttered charts into clear, audience-focused visualizations. Her framework for eliminating clutter, choosing appropriate chart types, and telling stories with data is immediately actionable. If you read one book from this list, make it this one.

Cole Nussbaumer Knaflic, Storytelling with Data: Let's Practice! (Wiley, 2019). The companion workbook to the above. It provides exercises and before/after examples that let you practice the principles from the first book. Excellent for self-study or classroom use.

Edward Tufte, The Visual Display of Quantitative Information (Graphics Press, 2nd edition, 2001). The classic text on data visualization integrity and design. Tufte's concepts of "chartjunk" and "data-ink ratio" are foundational for anyone creating visualizations for communication. More philosophical than practical, but deeply influential.

Barbara Minto, The Pyramid Principle: Logic in Writing and Thinking (Pearson, 3rd edition, 2008). The original text on the Pyramid Principle discussed in this chapter. Minto developed the framework at McKinsey, and it has become the standard approach for structuring business communication. The book is dense but rewarding — it will change how you organize any written or verbal communication.

William Zinsser, On Writing Well: The Classic Guide to Writing Nonfiction (Harper Perennial, 30th anniversary edition, 2006). Not a data science book, but essential for any data scientist who writes (which is all of them). Zinsser's principles — simplicity, clarity, brevity, and humanity — apply directly to reports, memos, executive summaries, and blog posts. The chapters on science writing and business writing are particularly relevant.

Nancy Duarte, Slide:ology: The Art and Science of Creating Great Presentations (O'Reilly, 2008). A comprehensive guide to slide design, from layout and typography to visual storytelling. Duarte's work with organizations like Apple and Al Gore's climate presentations informs practical, evidence-based advice on creating slides that communicate rather than confuse.

Tier 2: Attributed Resources

Nancy Duarte, Resonate: Present Visual Stories that Transform Audiences (Wiley, 2010). Duarte's second book focuses less on slide design and more on the narrative structure of presentations. She analyzes famous speeches (Steve Jobs, Martin Luther King Jr.) to extract principles that apply to any presentation, including data-driven ones. Particularly relevant for the narrative arc discussion in this chapter.

Garr Reynolds, Presentation Zen: Simple Ideas on Presentation Design and Delivery (New Riders, 3rd edition, 2019). An influential book on minimalist slide design — the idea that less text, fewer bullets, and more visual thinking lead to better presentations. Reynolds draws on Japanese aesthetic principles (simplicity, naturalness, subtlety) to argue for presentations that are both beautiful and effective.

Jake Knapp and John Zeratsky, Sprint: How to Solve Big Problems and Test New Ideas in Just Five Days (Simon & Schuster, 2016). While not specifically about data communication, the Sprint framework includes rapid prototyping and stakeholder communication techniques that are directly applicable to presenting data analysis results. The emphasis on "decision-making presentations" resonates with this chapter's themes.

The Storytelling with Data blog and podcast (Cole Nussbaumer Knaflic). Ongoing examples of before-and-after visualization makeovers, with detailed explanations of what was changed and why. An excellent resource for seeing communication principles applied to real charts. Search for "storytelling with data blog."

Tufte's one-day course, "Presenting Data and Information." Edward Tufte periodically teaches a one-day course on data presentation. Attendees receive four of his books. The course covers principles of analytical design, sparklines, and the visual presentation of evidence. Check availability through his website.

  • If you want to immediately improve your charts: Read Knaflic's Storytelling with Data and apply its principles to your next three visualizations. The before-and-after transformation is often dramatic.

  • If you want to write better reports and summaries: Read Zinsser's On Writing Well, focusing on the chapters on simplicity and clutter. Then read Minto's The Pyramid Principle for structural guidance. Practice by rewriting a past report using the Pyramid structure.

  • If you want to give better presentations: Read Duarte's Slide:ology for design principles and Resonate for narrative structure. Then practice: record yourself giving a 5-minute presentation, watch it, and revise.

  • If you want to understand the ethical dimensions of data communication: Jump ahead to Chapter 32 (Ethics in Data Science) and then revisit the communication ethics section (31.10) of this chapter. Also read Tufte's chapter on "The Cognitive Style of PowerPoint," which argues that the slide format itself can distort analytical thinking — a provocative and relevant critique.

  • If you want to build dashboards: The dashboard design principles in this chapter are framework-agnostic. For tool-specific guidance, consult the documentation for Streamlit (Python, rapid prototyping), Plotly Dash (Python, more customizable), or Tableau (GUI-based, widely used in industry). Each has excellent tutorials and galleries.

  • If you are preparing for job interviews: Data science interviews increasingly include a "present your analysis" component. Practice the assertion-evidence slide format and the Pyramid Principle. Being able to clearly communicate a technical analysis to a non-technical audience is often the differentiating skill among candidates with similar technical abilities.

A Final Thought

There is a tendency in data science education to treat communication as a "soft skill" — something nice to have, but secondary to the "real" skills of coding and statistics. This is a mistake. In practice, communication is the skill that determines whether your work has impact. The best analysis in the world, poorly communicated, changes nothing. A solid analysis, well communicated, can change a policy, redirect a budget, or save a program.

Invest in communication the way you invest in technical skills: with practice, study, and deliberate improvement. Your future self — and your future audiences — will thank you.