Book of Why

01Why is asking 'why' crucial in scientific inquiry?

Ever wondered why the sun rises in the east and sets in the west? Or why an apple falls to the ground instead of floating in the air? These are 'why' questions, and they are the heart and soul of scientific inquiry. They push us to dig deeper, to uncover the hidden mechanisms of the world around us. They are the driving force behind every major scientific discovery, from gravity to genetics. Think of 'why' questions as keys. Just as a key unlocks a door, a 'why' question unlocks understanding. It opens up a world of cause and effect, of actions and their consequences. It's not enough to know that the sun rises and sets; we want to know why. We want to understand the cause (the rotation of the Earth) and the effect (the apparent movement of the sun across the sky). But here's the rub: traditional statistical methods, the tools we often use to answer scientific questions, are not very good at handling 'why' questions. These methods, like regression analysis or chi-square tests, are great at identifying patterns and associations. For example, they can tell us that people who smoke are more likely to develop lung cancer. But they can't tell us why. They can't tell us whether smoking causes lung cancer, or whether there's some other hidden factor at play. This is because correlation does not imply causation. Just because two things happen together doesn't mean one causes the other. Maybe people who smoke are also more likely to live in polluted areas, and it's the pollution, not the smoking, that's causing the cancer. Traditional statistical methods can't tease apart these possibilities. They can't answer 'why'. Enter causal inference, the superhero of scientific inquiry. Causal inference is a set of tools and techniques that can determine cause-and-effect relationships. It goes beyond correlation, beyond association, to uncover the true causes of the phenomena we observe. Here's how it works. First, we formulate a hypothesis about the cause and effect. For example, we might hypothesize that smoking causes lung cancer. Then, we collect data and use causal inference techniques to test this hypothesis. These techniques can account for other factors, like pollution, that might be confounding the relationship. If the data supports our hypothesis, we can conclude that smoking does indeed cause lung cancer. In the "Book of Why", Judea Pearl uses the example of the link between smoking and lung cancer to illustrate the power of causal inference. Despite the strong correlation between smoking and lung cancer, it took decades of research and the application of causal inference techniques to definitively establish smoking as a cause of lung cancer. So, why is asking 'why' crucial in scientific inquiry? Because it pushes us to uncover the true causes of the phenomena we observe. Because it challenges us to go beyond correlation to causation. And because, with the help of causal inference, it allows us to unlock a deeper understanding of the world around us. So, the next time you find yourself wondering why the sun rises in the east, or why an apple falls to the ground, remember the power of 'why'. And remember that, with the right tools, we can find the answers.