Very strong book recommendation: The Book of Why, by Judea Pearl.
It's about the science of cause and effect -- gives a precise and also intuitive mathematical formalism for understanding the relationships between correlation and causation. It's also a popular intellectual history of statistics and causal inference. It's an accessible read for anyone who's somewhat numerate, used to thinking about probabilities and looking at numbers.
There's chapters explaining the history of how people concluded that tobacco causes lung cancer, a chapter that makes sense of the Monty Hall problem and Simpson's paradox, explanations of when you should/shouldn't adjust for a variable in a statistical analysis, etc.
I would say the conceptual tools are about as useful as having an understanding of probability and expected value -- strong claim but I think it's true.
Very strong book recommendation: The Book of Why, by Judea Pearl.
It's about the science of cause and effect -- gives a precise and also intuitive mathematical formalism for understanding the relationships between correlation and causation. It's also a popular intellectual history of statistics and causal inference. It's an accessible read for anyone who's somewhat numerate, used to thinking about probabilities and looking at numbers.
There's chapters explaining the history of how people concluded that tobacco causes lung cancer, a chapter that makes sense of the Monty Hall problem and Simpson's paradox, explanations of when you should/shouldn't adjust for a variable in a statistical analysis, etc.
I would say the conceptual tools are about as useful as having an understanding of probability and expected value -- strong claim but I think it's true.