The Causal Mindset Handbook: A practical guide to the science of cause and effect for evidence-based decision making

“The book is an excellent pick for managers, PMs, or any decision-maker who wants to understand the impact of their decisions. It presents the challenge of untangling causation from correlation with rigor, without delving into the complicated math of causal inference."

Matheus Facure Alves, Staff Data Scientist at Nubank and author of Causal Inference in Python (O'Reilly Media) and Causal Inference and Personalization (Manning)

“I had the pleasure of reading an advance copy of Quentin’s forthcoming book, The Causal Mindset Handbook. I highly recommend it.

With this book, Quentin makes causality both accessible and urgent. As he writes, “data is dumb”: numbers do not speak for themselves. In a fast-changing world marked by uncertainty, hallucinating chatbots, and ever-new conspiracies, distinguishing correlation from causation has become essential.

The book requires no background in econometrics or statistics. Through clear language and concrete examples from a wide range of contexts, Quentin guides readers step by step toward sound causal reasoning, showing that causal claims must always be questioned and updated as new evidence emerges.

Above all, this is a practical toolkit for better judgment. It teaches readers to ask the right questions: Is there another explanation? Could the causality run in reverse? Are there missing factors?

By the end, you are not just more informed but better equipped to think critically. This book is an excellent guide to developing what Quentin calls a true causal mindset."

Guido Palazzo, Professor of Business Ethics, HEC, University of Lausanne

“The Big Data Revolution of the early 2000s transformed decision-making. By enabling the collection and analysis of massive datasets, it produced practical advances, popularized statistical inference and machine learning, and helped lay the foundation for today’s wave of AI innovation.

Yet the revolution, in some sense, also ate its own children.

In promising trustworthy decision-making at scale, it also overpromised. A belief took hold that sufficiently large datasets could reveal the causal structure of problems on their own, reducing causal inference to what Bertrand Russell once called a “relic of the past.”

An emblematic example was an infamous tweet by technology investor Keith Rabois claiming that “with very large numbers of n’s you don’t need randomization,” later dubbed one of the most “confidently incorrect” statistical opinions by the statistics community.

But this mindset did not remain confined to social media. It still echoes today in boardrooms and across data science teams. Supervised machine learning is often treated as the default even when the goal is not prediction but better decisions. Leaders are encouraged to “just look at the dashboard” to judge whether a campaign worked, while unseen factors that shape the results are quietly ignored.

The result is familiar. Organizations invest heavily in ever more complex decision-support systems, yet the returns are often incremental.

The reason is simple. These systems are built to predict outcomes from historical data, while the questions businesses actually need answered are causal:

• What should we do next?
• Was the last campaign profitable?
• What policy will outperform the competition?

Neither model complexity nor sheer data volume can answer such questions reliably.

In this book, Quentin provides a clear framework for developing the causal mindset leaders will need to move beyond the lingering illusions of the Big Data era.

Aleksander Molak, founder of Causal Python and host of CausalBanditsPodcast.com; author of Causal Inference and Discovery in Python

With deep expertise and a passion for causality, Dr. Quentin Gallea has published research in top journals, addressing timely issues like the effects of COVID lockdowns or weapon imports on conflict. He is known for his unique ability to make complex topics accessible without compromising rigor. His practical approach has empowered over 15,000 people from C-suites to experienced researchers to apply causal thinking and causal inference in their respective fields. Today, Quentin is self-employed and provides advisory, training, public speaking, and advisory services across the world with a particular focus on measuring the impact of AI. In addition, he is a Senior Advisor at Enlighten Advisory, offering his expertise to support strategic decisions.