Introduction: The Human Ability to Ask Why
Humans possess a unique cognitive gift that sets them apart from all other species, which is the ability to ask why. Tens of thousands of years ago, our ancestors began to realize that certain actions lead to specific results. This discovery allowed them to tinker with their environment, leading to the birth of organized societies and the technological world we live in today. This mental process of managing causes and effects is the most advanced tool in the human brain.
Despite our natural talent for causal thinking, science has historically struggled to put these ideas into mathematical formulas. For over a century, the field of statistics operated under a self-imposed prohibition on discussing causality. Founders of the field discovered that data could reveal patterns, but they failed to embrace the logic of causation. Instead, they focused entirely on correlation, which is a measure of how two things change together without explaining the underlying force.
This focus on data alone created a significant gap in scientific language. A scientist could write an equation showing that a barometer reading tracks atmospheric pressure, but the math could not distinguish which one caused the other. In the eyes of traditional algebra, the pressure causing the barometer to move was no different than the barometer causing the pressure to change. Because scientists lacked a formal language for causes, these essential truths were left to intuition rather than rigorous analysis.
The problem with relying solely on data is that raw numbers cannot explain the mechanisms behind the patterns they show. Data can tell us that people who take a certain medicine recover faster, but it cannot explain the reason for the recovery. Perhaps those patients were wealthier or had better diets, and they would have recovered anyway. Without a model of the world, we are trapped in a cycle of observing associations without ever understanding how things actually work.
The Causal Revolution has finally provided the tools to break this cycle by introducing a calculus of causation. This new framework consists of causal diagrams, which are simple maps using dots and arrows to show which variables influence one another. These diagrams make our assumptions explicit and transparent so that scientists can mathematically predict the results of an intervention. This framework forms a Ladder of Causation, moving from basic association to active intervention, and finally to imagining alternative realities.
Full summary available in the Readsome app
