Deaths by Swimming Pool Drowning vs. Nicholas Cage Films and Other Spurious Correlations

Wednesday, May 14, 2014 - 09:06 AM

Spurious Connections

It is by now an age old adage that "correlation doesn't equal causation," but the internet just loves stories that make spurious correlations. Just yesterday there was an article floating around from Time magazine about a study that showed bullies have a lower risk of chronic diseases, with the headline "Bullying Is Good For Your Health." Wouldn't it be nice if there was a website that put lie to this idea of correlation/causation by taking it to ridiculous extremes? Enter Spurious Correlations.

The brainchild of Harvard Law School student Tyler Vigen, Spurious Connections simply takes events that have similar statistical variances over time and charts them on a graph. It's an object lesson in how easily two completely unrelated events can be shown to have some kind of relationship. Here are just a few examples:

Tyler himself doesn't see the project in the same light as I do. According to his website, he's just interested in the way people read statistics:

I created this website as a fun way to look at correlations and to think about data. Empirical research is interesting, and I love to wonder about how variables work together. The charts on this site aren't meant to imply causation nor are they meant to create a distrust for research or even correlative data. Rather, I hope this projects fosters interest in statistics and numerical research.

Regardless of his intent, the Spurious Correlations website works because it forces is us to think about our relationship to statistics and the way they are presented, both visually and in relation to one another. 


More in:

Comments [6]

Francisco from Newcastle upon Tyne, UK

Thank you Taylor. You reminded me of other studies:

From what I recall from documentaries I've seen and news items over the years: Studies in humans show that social rank is the most important componant of life expectancy (even if you account for other factors such as: diet, exercise, access to healthcare, etc).[1] Also studies show that those who have won Nobel prizes live, on average, two years longer than their peers.

One of the known factors in stress is how much control you feel you have in your life. One of the main theories mentioned to explain the first observation is that the higher your rank the less your are stressed because you have more options. Lower ranked individuals have more of their choice limited by higher ranked individuals.

[1] I think some of that came from a BBC series about stress a few years ago.

May. 22 2014 03:11 AM
Brian Dempsey from NYC

As someone that has created charts for clients for my entire career, this is fun and fascinating.

May. 15 2014 09:58 AM
JC from NJ

Cage has some really good movies (Raising Arizona, Leaving Las Vegas) and some unfathomably bad ones

May. 15 2014 08:16 AM

Tonight thousands of people across the United States will lie in bed unable to sleep because they're afraid of being killed by their bedsheets.

May. 14 2014 03:50 PM
SteveJ from southern California

I wonder what will happen when climate-change deniers get a hold of this? "This is what we've been saying all along. The "link" between greenhouse gasses and glacier melting is just a spurious correlation!" Coming soon to the Fox News Channel.

May. 14 2014 12:32 PM
Taylor Vik from Saint Paul, MN

That Time study may not be as much bunk as you portrayed it as in this article. Some studies on primate rank have shown increases in cortisol levels in low ranking(bullied) primates can have very large effects on health and general life outcome.

May. 14 2014 12:26 PM

Leave a Comment

Email addresses are required but never displayed.

Supported by

Embed the TLDR podcast player

TLDR is a short podcast and blog about the internet by Meredith Haggerty. You can subscribe to the TLDR podcast here. You can follow our blog here. I tweet @manymanywords and @tldr.

Subscribe to Podcast iTunes RSS