Correlation Does Not Equal Causation



Nothing helps an argument like poorly assembled and decidedly misinterpreted statistics (when your opponent starts to point out your flawed reasoning, call him a Nazi). Still, Vali Chandrasekaran of Business Week thinks that we should all be careful drawing conclusions from merely correlated data points. There are several more humorous examples at the link.

Link -via @MarilynTerrell | Previously: The Science News Cycle

Newest 5
Newest 5 Comments

One of the most useful classes that I took in library school was on social science research methods. It taught me a lot about how to design and implement a valid test, as well as draw conclusions from the data. And that was just what I picked up while I was awake.
Abusive comment hidden. (Show it anyway.)
Correlation Causation

and furthermore

Statistics Science

It's amazing how many people confuse statistics and science, especially people who should know better.
Abusive comment hidden. (Show it anyway.)
Fantastic. I've studied Research Methodology, and I hated how some academics jumped to conclusions just because there was correlation; or even worse, ignored or inflated some variables to get the necessary correlation so they can call it causation.

A great deal of bad policy - including economic policy - is created because of a faith in correlation=causation.

We are warned about this, but it's such a common mistake by most.
Abusive comment hidden. (Show it anyway.)
The mountain range one is really amazing, assuming it's a real picture. But the others share only one data point, so they're not that significant. The trend lines aren't even that close.
Abusive comment hidden. (Show it anyway.)
Commenting is closed.





Check out Twaggies' very funny clip:

Tech Fails - Twaggies by Twaggies
Email This Post to a Friend
"Correlation Does Not Equal Causation"

Separate multiple emails with a comma. Limit 5.

 

Success! Your email has been sent!

close window