Syphilis (Or Was It Facebook?) Blamed For People Not Understanding That Correlation Does Not Mean Causation
from the not-without-a-chi-square! dept
I really really really wasn’t going to write this post, but so many people kept submitting it, I figured it needed to be done. The Telegraph has some ridiculous story claiming, without any actual evidence, that Facebook is “linked to the rise in syphilis.” Quite a claim. The evidence? Oh, that’s not included. There’s just some public health guy claiming that there’s evidence — without presenting any. About the only thing in the article is that (a) more people in this particular area of the UK seem to be reporting that they got syphilis (b) people in that area are also (marginally) more likely than in other areas to use social networking (c) at least some of the people who got syphilis mentioned that they have met sexual partners via Facebook.
So, yes, you have a bit of weak correlation combined with self-selected anecdotal bias. And that proves what? Uh, absolutely nothing. So, please, for the sake of the sanity of statisticians everywhere, please learn to practice safe statistics, where before you claim something is linked to something else, you actually use “protection” in the form of some real data.
Filed Under: causation, correlation, social networks, statistics, syphilis, uk
Comments on “Syphilis (Or Was It Facebook?) Blamed For People Not Understanding That Correlation Does Not Mean Causation”
Hmm perhaps that pub(l)ic health guy was having trouble distinguishing between the two, because he suffers from ‘statiticsyphilis’, could have been ‘numbersgonorrhea’ too.
Please don your internet condoms before plugging into the net. We’ll all be safer.
Is there an AV program for this?
Re: Internet condom
I call it Linux.
(sorry, i had to 🙂 )
Re: Internet condom
Darn kids, quit setting your wireless card to Promiscuous mode and get off my LAN!
I like Facebook's response
One of the lines from the Facebook spokesperson quoted in the article:
“Facebook is no more responsible for STD transmission than newspapers responsible for bad vision.”
Re: I like Facebook's response
Given the logic of CNN or Fox News, that could be anywhere from “not at all responsible” to “completely responsible” depending upon which talking head is on…
Re: Re: I like Facebook's response
New study: AARP membership linked to death!
Re: Re: Re: I like Facebook's response
I remember someone (perhaps it was James Randi?) once arguing that the best predictor of death we have is what century you were born in.
It turns out that 100% of the people born in the 18th century are dead. Ergo, if you don’t want to die, don’t get born in the 18th century.
Re: Re: Re:2 I like Facebook's response
while not the 18th century, still damned old:
1895, for fucks sake!
Re: Re: Re:3 I like Facebook\'s response
“while not the 18th century, still damned old:”
Math fail. The 18th century was from 1701-1800.
If you don’t believe me, what century was year 1-100?
Re: Re: Re:4 I like Facebook\'s response
That was the 4th century.
Stop being a smart ass.
Re: I like Facebook's response
Welll… as someone who started reading before the muscles that focus the eye were fully developed, that’s an argument that you could ‘almost’ make, and not be totally wrong.
You’d still be stupid regardless.
“Pratice Safe Statistics”
“Real Data is Your Best Protection”
That should be your next t-shirt.
Facebook is no more responsible for the rise in STDs than man is responsible for the earth’s temperature.
Re: Global Warming
So, you want to exonerate Facebook at the cost of refuting global warming?
Re: Global Warming
Unless you take into account the lack of pirates. Clearly you are uninformed.
Well we need to ban dihydrogen monoxide as well since 100% of people who ingest it end up dead at some point
I gave a presentation in College once where I provided evidence that air was responsible for all the horrors of the world. I used every dirty trick in the book to hide, skew, and misrepresent legitimate sources (like an article from the american lung association) to support my claim. I was trying to show my classmates that just because someone shows you numbers, graphs, and diagrams doesn’t mean they’re telling you the absolute truth.
My teacher gave me 100% on it too. 🙂
Not the first time, not the last time
It is sad that a lot more people take this sort of thing seriously when the claim is that the economic and technological progress since the industrial revolution is causing an increase in cancer etc.
I just had to freakin’ shake my head at this claim… which tweaked my neck, so I think it’s safe to say that TechDirt is causing chiropractic injuries among it’s readership!
Ok, I know it’s really all the stupid people doing stupid things that causes pain… but in true litigious form, we have to blame those with the deepest pockets regardless of fault… right?
I blame that TV channel with the CG monster movies and wrestling.
I’d like to add to that and suggest that syphilis has a bad connotation around the term nowadays, I suggest we rename it to syfyless.
since reading newspapers in poor light
will harm vision.
Facebook is admitting they are guilty. Quick get me my lawyer, and a computer that does not practice safe sex.
according to the linked article:
“There has been a fourfold increase in the number of syphilis cases detected with more young women being affected.
“I don’t get the names of people affected, just figures, and I saw that several of the people had met sexual partners through these sites.
“Social networking sites are making it easier for people to meet up for casual sex.”
In Teesside there were 30 recorded cases of syphilis last year, but the true figures are expected to be much higher.
Research has shown that young people in Sunderland, Durham and Teesside were 25 per cent more likely to log onto social networking sites than those in the rest of Britain.
A Facebook spokesman said: “The assertion that Facebook is responsible for the transmission of syphilis is ridiculous. Facebook is no more responsible for STD transmission than newspapers responsible for bad vision. Today’s reports exaggerate the comments made by the professor, and ignore the difference between correlation and causation.
“As Facebook’s more than 400 million users know, our website is not a place to meet people for casual sex – it’s a place for friends, family and co-workers to connect and share.”
Re: since reading newspapers in poor light
OH i am certainly connecting and sharing with friends families and co-workers. 😉
cue horrified responses in…
Re: Re: since reading newspapers in poor light
hopefully just not all at once.
it is the same sort of babble that made freakenomics so popular.
Ben Goldacre, author of the Gurdian’s weekly Bad Science coulmn has been trying to get to the actual evidence all week. You can follow his progress on Twitter http://twitter.com/bengoldacre, but be warned it might give you gonorrhea 😉
Re: Bad Science
Nobody gave me gonorrhea, I earned it!
Re: Re: Bad Science
best comment yet!
cum se cum sa
Actually, I think I can create an equally plausible hypothesis that syphilis causes Facebook:
If people are finding that the risky ways they meet sexual partners are leading them to acquire too much venereal disease, then they might look for alternative methods to better screen potential partners.
An online system that would all people to vet potential partners by reading about them, and validating them through their community of friends might be useful.
Therefore, people who suffer from venereal disease might tend to populate such online social networks. Their use of these networks might contribute to the critical mass necessary to make the networks sustainable.
So, stamp out venereal disease and Facebook might just go away!
fish and chips must be wrapped in *something*
From my distant vantage point it seems that British newspapers are astonishingly bad at science. Is that true? And if so, why does anyone pay attention to their science stories?
Re: fish and chips must be wrapped in *something*
It’s not just science, but practically everything but the football results these days. The better ones are under intense pressure to get a story out ahead of the blogosphere and other new media, which means fact-checking often falls by the wayside in the rush to beat the print deadline. The rest of them seem to have just said “fuck it” and started making stories up as they go along.
Well would we now call Syphilis a computer virus?
Then we can sue Norton/Mcafee etc as they did not protect you from getting it.
Also sue Google, in Italy you could get away with it
I suppose we could except that syphilis is caused by a bacteria.
all such a study really shows -
“Tortured statistics… will confess to anything.”
Headline: Facebook Users Prefer Dial Soap.
I’m making this statement based off the fact that everyone of my friends that every time I go over to a friend’s house, that has a Facebook account, they have Dial soap in their bathroom.
Wow, what a joke..
Hey, it is the perfect platform for syphilis.
Someone just now needs to write an app providing an easy way to tell your “friends” you tested positive, and leaderboards for Most Infected.
Correlation: The most abused statistic
Anyone who has taken a serious class in statistics knows the worthlessness of correlation figures. They also know that correlation is THE most abused of statistics. If you ever see anyone attempting to state cause and effect based upon correlation data, you know right off the bat that they are deadly desperate to have something to prove. Not gonna happen. Correlation has no statistical significance.
wear latex gloves when you check your facebook then???