Correlation not implying causation is not the same as correlation not implying relation. When data correlates, that means that there is a liklihood that there is some connection. For any two correlating datasets, there are 3 explanations, 1) coincidence 2) causation 3) relation to a shared casual link. Figuring out which it is just requires more data, experimentation, and/or an understanding of the mechanisms of their relation. We use correlation of datasets as a guide, and even as a proof of theory given enough experimentation and correlating data to show a casual link all the time in science.
I think that the liklihood that leaded gasoline is connected to the rates of serial killers and other forms of violent crime is high not just because of the correlation, but because of that and the fact that we have studies showing how lead poisoning can effect people’s behavior. We know it can effect behavior, and we know that lead levels in the air peaked in the mid 70s before leaded gasoline was banned. It is not a leap to jump to the hypothesis that leaded gasoline causing high lead levels in the air from pollution may have effected human behavior. And then the data of serial killings and violent crime actually showing a correlation with those lead levels strengthens that hypothesis. I wouldn’t say that it’s proof, far from it. But I do think it’s likely the truth.
Right, I’m just venting my old frustration with that specific book because they only used the correlation as “proof”, rather than indeed looking at more causal signals like studies on lead poisoning.
It is certainly also true that correlation doesn’t mean that there’s no causation, even in cases were there are no other experiments yet to support a causal relationship.
Correlation not implying causation is not the same as correlation not implying relation. When data correlates, that means that there is a liklihood that there is some connection. For any two correlating datasets, there are 3 explanations, 1) coincidence 2) causation 3) relation to a shared casual link. Figuring out which it is just requires more data, experimentation, and/or an understanding of the mechanisms of their relation. We use correlation of datasets as a guide, and even as a proof of theory given enough experimentation and correlating data to show a casual link all the time in science.
I think that the liklihood that leaded gasoline is connected to the rates of serial killers and other forms of violent crime is high not just because of the correlation, but because of that and the fact that we have studies showing how lead poisoning can effect people’s behavior. We know it can effect behavior, and we know that lead levels in the air peaked in the mid 70s before leaded gasoline was banned. It is not a leap to jump to the hypothesis that leaded gasoline causing high lead levels in the air from pollution may have effected human behavior. And then the data of serial killings and violent crime actually showing a correlation with those lead levels strengthens that hypothesis. I wouldn’t say that it’s proof, far from it. But I do think it’s likely the truth.
Yup. There’s a reason it’s called co-relation.
Right, I’m just venting my old frustration with that specific book because they only used the correlation as “proof”, rather than indeed looking at more causal signals like studies on lead poisoning.
It is certainly also true that correlation doesn’t mean that there’s no causation, even in cases were there are no other experiments yet to support a causal relationship.