I really appreciate that the goal of proving correlation != causation could have been demonstrated with like five of these examples but instead the list of stuff they find is absolutely endless....
I really appreciate that the goal of proving correlation != causation could have been demonstrated with like five of these examples but instead the list of stuff they find is absolutely endless.
Statistically they must eventually run into one that actually turns out to be causally related.
Side note: The number of printing press operators in Rhode island fluctuates a lot more than I would expect.
Yes, this is even addressed in the "why this works" section:
Statistically they must eventually run into one that actually turns out to be causally related.
Yes, this is even addressed in the "why this works" section:
Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
I was thinking more of a correlation that appears absurd on the surface but are causally related through some very unexpected means, like the connection between the size of the space shuttle and...
I was thinking more of a correlation that appears absurd on the surface but are causally related through some very unexpected means, like the connection between the size of the space shuttle and the width of an elephant.
<offtopic-noise> I'm reasonably confident that it ought to be "effects" here, since the correlations are between things happening. As posted ("Website showing spuriously correlated affects" ...?),...
<offtopic-noise>
I'm reasonably confident that it ought to be "effects" here, since the correlations are between things happening. As posted ("Website showing spuriously correlated affects" ...?), this title feels incomplete; the reader is left wondering "what is affected by these spurious correlations?"
Just one of my pet peeves.
Perhaps better yet would be to just replace it with "statistics," eg. "Website showing spuriously correlated statistics."
I really appreciate that the goal of proving correlation != causation could have been demonstrated with like five of these examples but instead the list of stuff they find is absolutely endless.
Statistically they must eventually run into one that actually turns out to be causally related.
Side note: The number of printing press operators in Rhode island fluctuates a lot more than I would expect.
Yes, this is even addressed in the "why this works" section:
I was thinking more of a correlation that appears absurd on the surface but are causally related through some very unexpected means, like the connection between the size of the space shuttle and the width of an elephant.
Big fan of the R2 = 0.902 on the correlation between the distance between Jupiter and the Sun and the number of secretaries in Alaska
I adore the correlation between library science degree awards and Google "how to hide a body" searches. The AI-generated "explanation" is chef's kiss.
I'm reasonably confident that it ought to be "effects" here, since the correlations are between things happening. As posted ("Website showing spuriously correlated affects" ...?), this title feels incomplete; the reader is left wondering "what is affected by these spurious correlations?"
Just one of my pet peeves.
Perhaps better yet would be to just replace it with "statistics," eg. "Website showing spuriously correlated statistics."
</offtopic-noise>