interesting correlations

Not open for further replies.
May 4, 2003
southeast US
US spending on science, space, and technology correlates with Suicides by hanging, strangulation and suffocation Correlation: 0.992082 Divorce rate in Maine correlates with Per capita consumption of margarine (US) Correlation: 0.992558 Honey producing bee colonies (US) inversely correlates with Juvenile arrests for possession of marijuana (US) and more: so much for statistics and data mining.
Last edited:
assuming linear relationship between Var_A over time and Var_B over time, then all you need to do is to find Var_A and Var_B to have the same slope and correlation would be 1.0 Or am I wrong?
There's and old saying: "There are lies, darn [didn't want to be censored] lies, and statistics." There's also "Correlation does not always equal causation." Intersting correlations? Sure. Meaningful? Nope.
There is sometimes a correlation between stats and funding. Recently a research group was tasked with a "cause of death in the US" study requiring rigorous documentation. On the first unpublished draft it was discovered that the number one cause of death in the US was "medical intervention", that is medical treatment gone wrong for whatever reason. Their funding disappeared that day. Some studies receive funding only if they come up with the "correct answers" which they may have in hand before the project begins. Once the money is in hand the true expertise in research sometimes comes down to how the words play so the funding stays put. This can make it difficult to segregate the good studies from the others.
You can make correlations between oddball measurements fairly easy if you look long enough. The chart above measures honey producing bee colonies, not the total amount of honey produced, a big difference.
I'm more intrigued by "Number of people who died by becoming tangled in their bedsheets" which was measured twice. I can't picture how that happens. I'm a thrasher in bed and I still can't see how it happens.
Not open for further replies.