Information into Insights
March 9, 2022

Thinking with Data helps you turn information into insights

By Paul Laughlin

One of the perennial challenges that I hear data leaders face is how to train their analysts how to turn information into insights. Too many underwhelm stakeholders by just presenting data, facts, results without relevant insights. The book I am reviewing today, entitled “Thinking with Data”, should help those leaders & their analysts.

I was delighted to receive this book as a kind gift from Dante (thanks again) following a call. I’m delighted that he shared it with me as there are too few focused on this topic. In Thinking with Data” the author, Max Shron, has created a handy guide that could be used by almost any analyst. His practical experience from many years as a data strategy consultant shines through.

That said, if you buy this book you might be underwhelmed when it first arrives. Given the price point, you might have expected something longer. At only 75 pages, it looks like barely more than a pamphlet. But don’t be fooled. A surprising amount of value is packed in those few pages. Plus this means it’s quick for any time-poor leader or analyst to read.

What does Thinking with Data include?

Let’s start by giving you an overview of the content you can find in this book. It is arranged into 6 pithy chapters, followed by a shortlist of recommended books for further reading. These can be further grouped into these topics:

  1. Scoping (understanding Why? before starting on How?)
  2. What Next? (domain knowledge and verifying understanding of challenge)
  3. Creating Arguments (turning observations into knowledge):
    • Types of arguments
    • Patterns of reasoning
    • Special case (Causual reasoning)
  4. How to put all of this together (case studies/deep dives)

Hopefully, the language above helps you hear the practical focus of this book. It really is a short treasure trove in which any analyst will find at least one gold nugget. But beyond the practical methods & tips, there is theoretical underpinning. The author (Max Shron) does a great job of demonstrating the polymath nature of this craft. He shows that best practice draws on disciplines far beyond maths & stats. Including thinking models from English, Psychology, Political Science & many other humanities.

Scoping well, to turn information into insights

As Max highlights, many analysts have the bad habit of wanting to rush into action too soon. The temptation to start extracting data or using your analytics package/language can be too great. In the rush for progress, quality thinking at the outset can be missed. All too often this will come back to bite you. Ill-defined problems. Misunderstood needs. Unrealistic expectations. The source of most of those woes is a lack of time spent ‘scoping’ to understand both the real need and limits on what is to be done.

When I train analysts in the people skills they need to be effective, we cover Socratic Questioning to get to the implicit or underlying need. I really like how Max builds on that skill set with a simple mnemonic to guide such questioning. He uses this CoNVO model:

  • Co = Context (organisational priorities, interests, issues, how will this work further progress?)
  • N = Needs (needs that could be met by data, the Why?, key questions, action to be informed)
  • V = Vision (what will it look like to meet that need with data? envision impact & progress)
  • O = Outcome (what is to be produced, who will use it, what will change as a result?)

Such a focus can be very helpful. I also really support Max’s frequent call to write things down. Like the benefits of a Vision Script for leaders, writing down your understanding of each part in a short paragraph helps to clarify thinking. He couples this with a number of recommended forms to use. Mockups and Argument Sketches to capture a Vision. A clear written story to express all the above on one page.

Structuring how you will approach analytical work

Many analysts work in an ad-hoc manner. Some, who might be considered to represent best practice, use a consistent workflow or methodology (CRISP-DM etc). However, very few have a structured approach to thinking first. Planning out an appropriate critical thinking approach to suit this problem. That is some of the gold dust that Max shares in chapters 2-5.

He starts by guiding the analyst to dig deeper into understanding the problem domain. Sense checking your understanding of what is needed and data sources or stakeholders who can help you learn what is needed. Max shares how to use the following techniques at this stage:

  • Interviews (knowledge elicitation from experts)
  • Rapid Investigation (order of magnitude estimates, easy graphs, BI for sense checking etc)
  • Kitchen Sink Investigation (like a detective asking everything & train of thought interrogation)
  • Working Backward (start with intended output, work back step by step what’s needed)
  • Mockups (sketching ideas of outputs and processes to get there)
  • Roleplaying (lay the part of the final consumer & think out loud)

Lots of good ideas there, but Max goes quite a bit deeper by then exploring how you can construct arguments via your data analysis. These next chapters are a useful guide on taking approaches including: Confirming audience & prior beliefs; Identifying claims that need to be made; presenting evidence, justification of claims & predicting rebuttals.

Learning in practice and from practical examples

Analysts will best learn these skills & techniques in practice. But a helpful first step is case studies or walkthrough examples. Max peppers this short book with such examples. It is helpful to follow the metamorphosis of some of these ‘Deep Dive’ sections through each chapter. He also illustrates bringing everything together in the final chapter through two longer such case studies.

Before that final chapter, Max brings to life some helpful patterns of reasoning that should guide analysts through this process. Drawing from both the legal & scientific disciplines he walks us through identifying & classifying different points of dispute to address. This brings to life how an analyst will need to take slightly different approaches to address disputes about facts, definitions, values & policies. He also provides extra advice for special types of arguments (optimisation, bounding cases, cost/benefit analysis & proving causation).

It is a credit to such a short book that I was reminded of relevant principles from much more in-depth studies. You can see the application of lessons I learnt in critical thinking from “Calling Bullshit“. There are also some of the perspectives recommended in How to make the world add up. Plus the chapter on causality was a useful primer to my current reading, a much deeper exploration in “The Book of Why” by Judea Pearl (review coming next month).

How are you turning information into insights?

So, I hope you can tell that I’m a fan of this book & despite the higher price tag for a small book would recommend it for analytics teams. But even more important is that you practice these techniques in the real world. Then share your experience. Recognise that as well as honing your technical skills, analysts need to develop their thinking skills and ability to question & plan well from the start.

What about you, dear reader? What has worked for you? Have you found other resources or approaches that have helped you better generate relevant insights for your business? If so, please let me know. I am keen to share more to help all analysts develop these skills. True transformation of organisations to be data-led needs much more than the mainstream focus on technology & technical skills. So, expect more on this topic in future. Happy thinking & I hope you are seeking success in delivering insights that drive valuable changes.