(An idea I had while responding to this quotes thread)
"Correlation does not imply causation" is bandied around inexpertly and inappropriately all over the internet. Lots of us hate this.
But get this: the phrase, and the most obvious follow-up phrases like "what does imply causation?" are not high-competition search terms. Up until about an hour ago, the domain name correlationdoesnotimplycausation.com was not taken. I have just bought it.
There is a correlation-does-not-imply-causation shaped space on the internet, and it's ours for the taking. I would like to fill this space with a small collection of relevant educational resources explaining what is meant by the term, why it's important, why it's often used inappropriately, and the circumstances under which one may legitimately infer causation.
At the moment the Wikipedia page is trying to do this, but it's not really optimised for the task. It also doesn't carry the undercurrent of "no, seriously, lots of smart people get this wrong; let's make sure you're not one of them", and I think it should.
The purpose of this post is two-fold:
Firstly, it lets me say "hey dudes, I've just had this idea. Does anyone have any suggestions (pragmatic/technical, content-related, pointing out why it's a terrible idea, etc.), or alternatively, would anyone like to help?"
Secondly, it raises the question of what other corners of the internet are ripe for the planting of sanity waterline-raising resources. Are there any other similar concepts that people commonly get wrong, but don't have much of a guiding explanatory web presence to them? Could we put together a simple web platform for carrying out this task in lots of different places? The LW readership seems ideally placed to collectively do this sort of work.
There is in fact a d) A and not-B both can cause some condition C that defines our sample.
Example: Sexy people are more likely to be hired as actors. Good actors are also more likely to be hired as actors. So if we look at "people who are actors," then we'll get people who are sexy but can't really act, people who are sexy and can act, and people who can act and aren't really sexy. If sexiness and acting ability are independent, these three groups will be about equally full.
Thus if we look at actors in general in our simple model, 2/3 of them will be sexy and 2/3 of them will be good actors. But of the ones who are sexy, only 1/2 will be good actors. So being sexy is correlated with being a bad actor! Not because sexiness rots your brain (a), or because acting well makes you ugly (b), and not because acting classes cause both good acting and ugliness, or diet pills cause both beauty and bad acting (c). Instead, it's just because how we picked actors made sexiness and acting ability "compete for the same niche."
Similar examples would be sports and academics in college, different sorts of skills in people promoted in the workplace, UI design versus functionality in popular programs, and so on and so on.
What do you mean by "equally full"?