Dec 24, 2016 08:15 PM
(This post was last modified: Dec 24, 2016 08:32 PM by Yazata.)
Correlation isn't Causation... or maybe it is.
US spending on science, space and technology has a 99.79% correlation with suicides by hanging, strangulation and suffocation.
The number of drownings by falls into swimming pools has a 66.6% correlation with the number of films that Nicholas Cage appears in annually.
Worldwide consumption of mozzarella cheese has a 95.86% correlation to the number of civil engineering degrees awarded.
The age of Miss America has an 87% correlation with murders by steam, hot vapors and hot objects.
The annual divorce rate in Maine has a 99.26% correlation with per-capita consumption of margarine.
Tyler Vigen, a former military intelligence analyst turned Harvard law student, has a computer algorithm that detects correlations in fluctuations in numerical time-series data. So just shovel in the data and watch to see what weird correlations the computer finds.
http://www.tylervigen.com/spurious-correlations
It really makes me wonder about the credibility of so-called "social sciences" where statistical correlations between A and B are often the best evidence that they can produce.
Number of math doctorates awarded has a 95.23% correlation to amount of uranium stored at nuclear power plants! (Who knew?)
US spending on science, space and technology has a 99.79% correlation with suicides by hanging, strangulation and suffocation.
The number of drownings by falls into swimming pools has a 66.6% correlation with the number of films that Nicholas Cage appears in annually.
Worldwide consumption of mozzarella cheese has a 95.86% correlation to the number of civil engineering degrees awarded.
The age of Miss America has an 87% correlation with murders by steam, hot vapors and hot objects.
The annual divorce rate in Maine has a 99.26% correlation with per-capita consumption of margarine.
Tyler Vigen, a former military intelligence analyst turned Harvard law student, has a computer algorithm that detects correlations in fluctuations in numerical time-series data. So just shovel in the data and watch to see what weird correlations the computer finds.
http://www.tylervigen.com/spurious-correlations
It really makes me wonder about the credibility of so-called "social sciences" where statistical correlations between A and B are often the best evidence that they can produce.
Number of math doctorates awarded has a 95.23% correlation to amount of uranium stored at nuclear power plants! (Who knew?)
