Correlation: Difference between revisions

[[File:Quincunx.jpg|450px|thumb|center|A [[quincunx]], yesterday]]}}The idea, following from Sir Francis Galton’s experiments with a [[quincunx]] and first articulated by statistician Karl Pearson<ref>So [https://slate.com/technology/2012/10/correlation-does-not-imply-causation-how-the-internet-fell-in-love-with-a-stats-class-cliche.html Slate Magazine] argues, at any rate.</ref> that a relationship between two variables could be characterised according to its statistical strength and expressed in numbers, regardless of any perceived causal connection between them.

Well, in some cases you can, in some cases you can’t<ref>There are whole websites devoted to spurious correlations. Like, well, http://www.spuriouscorrelations.com.</ref> but — irony upcoming — without a sophisticated theory of ''causality'', it will be hard to tell them apart. That is to say, a bare [[correlation]] won’t tell you whether there is a causal arrow at all. much less — if there is — which way it flows.

“Correlation”<ref>“A mutual relationship or connection between two or more things.”</ref> ''ought to be'' a synonym for “coincidence”<ref>“A remarkable concurrence of events or circumstances without apparent causal connection,” sayeth the Google.</ref>, though in its more fashionable usages, especially among [[big data]] freaks, this tends to be get — well — ''buried'' in the [[signal-to-noise ratio|noise]]. There may be something profound, reflexive and ironic about this, but it's too early in the morning to figure out out. The more data you have the, the more noise to the [[signal-to-noise ratio|signal]]. At any rate, automatically chanting “correlation does not imply causation” in a sing-song voice whenever anyone cites a correlation annoys the ''hell'' out of big data freaks.