0552: "Correlation"

This forum is for the individual discussion thread that goes with each new comic.

Moderators: Magistrates, Prelates, Moderators General

0552: "Correlation"

Postby joee » Fri Mar 06, 2009 5:01 am UTC

Image

Title text:Correlation doesn't imply causation, but it does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there'.

Link: http://xkcd.com/552


I wish more people knew correlation does not imply causation. Like antivaxxers
Hi glasnt.
User avatar
joee
 
Posts: 227
Joined: Mon Dec 03, 2007 5:53 am UTC

"Correlation" Discussion

Postby gtkarber » Fri Mar 06, 2009 5:02 am UTC

Excellent work, again. That is awesome, and reminds me of a conversation I had with a friend where he kept insisting that because so many modern American presidents were in college fraternities, that you had to be in a college fraternity to get elected President.

Off to Wikipedia Obama...
gtkarber
 
Posts: 27
Joined: Wed May 30, 2007 12:57 pm UTC

Re: "Correlation" Discussion

Postby bieoe » Fri Mar 06, 2009 5:02 am UTC

Oh man, these recent statistics comics make me miss my statistics class last year.
User avatar
bieoe
 
Posts: 2
Joined: Thu Oct 30, 2008 8:20 pm UTC

Re: "Correlation" Discussion

Postby prokrastinatorSF » Fri Mar 06, 2009 5:03 am UTC

I’ve been on XKCD withdrawl since Wednesday and spent several hours reading Comic JK to try to fill the void. Then I come back to XCKD… three panels and one very heartfelt lawl. Nothing else can replace it.
prokrastinatorSF
 
Posts: 24
Joined: Fri Aug 08, 2008 1:05 pm UTC

Re: "Correlation" Discussion

Postby Forrest » Fri Mar 06, 2009 5:03 am UTC

This is the best comic I've seen in a while. It's ridiculously clever.
Forrest
 
Posts: 6
Joined: Sat May 03, 2008 1:31 am UTC

Re: "Correlation" Discussion

Postby athelas » Fri Mar 06, 2009 5:04 am UTC

I looked at this comic, and then I laughed. Coincidence?

EDIT: the burning-cheese thing is getting unfunny. Just sayin'.
Last edited by athelas on Fri Mar 06, 2009 5:45 am UTC, edited 1 time in total.
User avatar
athelas
A Sophisticated Plagiarism Engine
 
Posts: 584
Joined: Sat Oct 21, 2006 2:37 am UTC

Re: "Correlation" Discussion

Postby abstractpotato » Fri Mar 06, 2009 5:05 am UTC

The declining numbers of sea pirates (not software pirates) are causing global warming ;-)
abstractpotato
 
Posts: 44
Joined: Mon Jan 19, 2009 5:28 pm UTC
Location: California

Re: "Correlation" Discussion

Postby alias.exe » Fri Mar 06, 2009 5:05 am UTC

Clever and snappy. I like it.

Also, that was ridiculously quick thread-making gtkarber.
User avatar
alias.exe
 
Posts: 36
Joined: Thu Feb 12, 2009 11:18 am UTC

Re: "Correlation" Discussion

Postby Jasn » Fri Mar 06, 2009 5:05 am UTC

Is there a joke in this comic? If there is, I do not see it. I'm taking a statistics class right now.
Jasn
 
Posts: 5
Joined: Mon Jun 30, 2008 10:21 pm UTC

Re: "Correlation" Discussion

Postby prokrastinatorSF » Fri Mar 06, 2009 5:06 am UTC

Good point... did event A cause event B, is there a condition C that is causing both, or was there a warp in the time-space continuum and you actually read the webcomic BECAUSE you lawl'd?

Edit: the joke is that statistics teaches that just because two things are correlated does not mean one is causing the other. So just because he happened to stop believing correlation = causation after taking a stat class, doesn't mean taking the class caused him to believe this.
prokrastinatorSF
 
Posts: 24
Joined: Fri Aug 08, 2008 1:05 pm UTC

Re: "Correlation" Discussion

Postby gtkarber » Fri Mar 06, 2009 5:07 am UTC

I didn't even make it first! I couldn't delete it before someone else posted, either--so now I look like that guy.
gtkarber
 
Posts: 27
Joined: Wed May 30, 2007 12:57 pm UTC

Re: "Correlation" Discussion

Postby gtkarber » Fri Mar 06, 2009 5:08 am UTC

jasn: The joke is that you really can't be sure if the statistics class changed his opinion unless you perform an experiment with variable manipulation.

/worst way to explain the joke
gtkarber
 
Posts: 27
Joined: Wed May 30, 2007 12:57 pm UTC

Re: "Correlation" Discussion

Postby alias.exe » Fri Mar 06, 2009 5:08 am UTC

Oh dear. Now to copypasta my post into that other thread, and compliment him instead. Sigh. Life is hard.
User avatar
alias.exe
 
Posts: 36
Joined: Thu Feb 12, 2009 11:18 am UTC

Re: "Correlation" Discussion

Postby alias.exe » Fri Mar 06, 2009 5:09 am UTC

Clever and snappy. I like it.
User avatar
alias.exe
 
Posts: 36
Joined: Thu Feb 12, 2009 11:18 am UTC

Wait for it...

Postby calico » Fri Mar 06, 2009 5:15 am UTC

I got to the end of this one and felt like I missed something. It suddenly hit me about 2 seconds later... so marvelously subtle, I love it!
calico
 
Posts: 10
Joined: Tue Nov 18, 2008 2:09 am UTC
Location: The Lappy

Re: "Correlation" Discussion

Postby gtkarber » Fri Mar 06, 2009 5:15 am UTC

Hey, what's up, alias? Thanks for not having the gall to actually copy and paste the whole post and transfer your compliment. Now I will treasure it forever.

(Until the duplicate post is deleted.)
gtkarber
 
Posts: 27
Joined: Wed May 30, 2007 12:57 pm UTC

Re: "Correlation" Discussion

Postby kriel » Fri Mar 06, 2009 5:16 am UTC

gtkarber wrote:jasn: The joke is that you really can't be sure if the statistics class changed his opinion unless you perform an experiment with variable manipulation.

/worst way to explain the joke
It may have been the worst way to explain it, but I didn't even get that aspect of the joke until I came here. I was just cackling at the alt-text.
User avatar
kriel
 
Posts: 922
Joined: Thu Feb 07, 2008 2:58 pm UTC
Location: Somewhere I'm not.

Re: "Correlation" Discussion

Postby dennisw » Fri Mar 06, 2009 5:17 am UTC

gtkarber wrote:I didn't even make it first! I couldn't delete it before someone else posted, either--so now I look like that guy.

It looks pretty closely correlated to me.
Try the Printifier for xkcd. You can now scale the comic between 50 and 150%.

I find these very useful: Common Errors in English Usage (web site) and Eats, Shoots & Leaves (book). You may, too.

e pluribus unum
Unleash unlicensed ungulates!
User avatar
dennisw
 
Posts: 438
Joined: Wed Nov 05, 2008 9:09 am UTC
Location: Appearing pro se AND pro bono!

Re: "Correlation" Discussion

Postby dennisw » Fri Mar 06, 2009 5:22 am UTC

Jasn wrote:Is there a joke in this comic? If there is, I do not see it. I'm taking a sadistics class right now.

fix'd, so that there's a correlation
Try the Printifier for xkcd. You can now scale the comic between 50 and 150%.

I find these very useful: Common Errors in English Usage (web site) and Eats, Shoots & Leaves (book). You may, too.

e pluribus unum
Unleash unlicensed ungulates!
User avatar
dennisw
 
Posts: 438
Joined: Wed Nov 05, 2008 9:09 am UTC
Location: Appearing pro se AND pro bono!

Re: "Correlation" Discussion

Postby kev015 » Fri Mar 06, 2009 5:40 am UTC

I lawl'd

I remember statistics, and the whole "Correlation does not imply causation" It was sort of like a meme, with the textbooks and videos saying the same thing over a few times, accompanied by funny illustrations. The only other memories I have of that class is wasting time playing calculator games, not taking notes, and distributing coke.

Oh, and get out of my textbook, Randall.
Last edited by kev015 on Fri Mar 06, 2009 5:43 am UTC, edited 1 time in total.
50% Fascist Bastard. 25% Damn Commie. 25% Yuppie Weasel.
User avatar
kev015
 
Posts: 12
Joined: Fri Apr 11, 2008 4:37 am UTC

Re: "Correlation" Discussion

Postby prometheus3737 » Fri Mar 06, 2009 5:41 am UTC

This comic reminds me of the thoroughly well-proven fact that the decline of 18th century style pirate is the direct cause of global warming, as illustrated by this graph:
Image
prometheus3737
 
Posts: 5
Joined: Tue Jan 20, 2009 3:42 am UTC

Re: "Correlation" Discussion

Postby Editer » Fri Mar 06, 2009 5:46 am UTC

Nearly every time I see an xkcd comic I laugh out loud. Coincidence?
These days, if you don't have ADD, you not paying close enough attention. -- J.P. Barlow
User avatar
Editer
 
Posts: 65
Joined: Mon Mar 31, 2008 4:17 am UTC

Re: "Correlation" Discussion

Postby berto17 » Fri Mar 06, 2009 5:54 am UTC

Haha :) I got it right away, which was nice.
IN/ RAINBOWS
IN RAIN/BOWS
IN RAINBOW/S
IN RAINBOWS/
IN RAIN_BOWS
RA D IOHE _AD
_RAD IO HEA D
User avatar
berto17
 
Posts: 9
Joined: Fri Dec 26, 2008 8:27 am UTC

Re: "Correlation" Discussion

Postby shazbot » Fri Mar 06, 2009 5:58 am UTC

David Hume did a much more thorough and effective job of destroying causality for me than my statistics textbook could have ever achieved.
User avatar
shazbot
 
Posts: 1
Joined: Fri Mar 06, 2009 5:54 am UTC
Location: Oklahoma

Re: "Correlation" Discussion

Postby speqter » Fri Mar 06, 2009 6:01 am UTC

To waggle is to move something from side to side.
Those in favor of changing "waggle" to "wiggle", clap your hands. :wink:
speqter
 
Posts: 13
Joined: Mon May 12, 2008 8:01 am UTC

Re: "Correlation" Discussion

Postby PhatPhungus » Fri Mar 06, 2009 6:05 am UTC

athelas wrote:EDIT: the burning-cheese thing is getting unfunny. Just sayin'.


Just because every time you type l o l it comes out lol doesn't mean it's because you type l o l.
__________
_____
__
_
User avatar
PhatPhungus
 
Posts: 321
Joined: Wed Aug 22, 2007 5:40 pm UTC

Re: "Correlation" Discussion

Postby russianspy1234 » Fri Mar 06, 2009 6:05 am UTC

i actually very recently got into an argument about this in a chat. turns out, the actual statistical definition of "implies" is different from the day to day usage, and it does actually mean "proves", which is what my argument was, that it does imply causation, but doesnt prove it.
russianspy1234
 
Posts: 51
Joined: Mon Sep 10, 2007 4:43 am UTC

I lol'ed.

Postby godlygeek » Fri Mar 06, 2009 6:14 am UTC

Good comic. :-)
godlygeek
 
Posts: 2
Joined: Sat Jan 31, 2009 6:49 am UTC

Re: "Correlation" Discussion

Postby Ciega » Fri Mar 06, 2009 6:17 am UTC

russianspy1234 wrote:i actually very recently got into an argument about this in a chat. turns out, the actual statistical definition of "implies" is different from the day to day usage, and it does actually mean "proves", which is what my argument was, that it does imply causation, but doesnt prove it.

...yeah, you have to be careful with that word "imply". And as someone who, after taking AP Statistics, is incapable of describing anything as "significantly ______" outside of an actual significance test, I understood the punchline immediately. That way of thinking is hard to get rid of, once you start doing it...
Ciega
 
Posts: 16
Joined: Mon Jul 28, 2008 4:12 pm UTC

Re: "Correlation" Discussion

Postby sje46 » Fri Mar 06, 2009 6:20 am UTC

Randall, you dick.
I hate you so called "scientists" explaining away the Truth by using your faux-philosophy.
"Oh, the reason why the amount of atheists in a city increases with the amount of crime isn't because God-less evil baby-killing atheists cause more crime, but because as the population goes up, so does the amount of people in every demographic you see there is a third variable in which the cotangent of sigma x bla bla bla."
Don't give me that, obscuring everything with complicated math and logic. This is called a proof by verbosity, and it is a logical fallacy. I took Do you really mean to suggest that atheism doesn't cause crime? Come on. ATheists reject the word of Jesus Our Savior and spits in everyone's faces. Of course the more they increase in a locality, the more morality goes down. STop making us into an unloving, uncaring, unGodfearing country, with your God denying, truth twisting atheist douchebag scientists, and let the Love of Jesus Fill your heart!

Not cool, not funny, not a good comic.
General_Norris: Taking pride in your nation is taking pride in the division of humanity.
Pirate.Bondage: Let's get married. Right now.
sje46
 
Posts: 4724
Joined: Wed May 14, 2008 4:41 am UTC
Location: New Hampshire

Re: "Correlation" Discussion

Postby phlip » Fri Mar 06, 2009 6:24 am UTC

russianspy1234 wrote:i actually very recently got into an argument about this in a chat. turns out, the actual statistical definition of "implies" is different from the day to day usage, and it does actually mean "proves", which is what my argument was, that it does imply causation, but doesnt prove it.

Not just in statistics... "implies" has that definition in all of mathematics.

Strictly, the sentence "Correlation does not imply causation" is equivalent to "There exist scenarios where A and B are correlated, but A does not cause B." (Alternatively, "Correlation does imply causation" is equivalent to "In all situations where A is correlated to B, A causes B.")

[edit] sje: admittedly, the fact that your fake rants got very old quite a while ago and the fact that they're really not that funny are correlated, but that doesn't imply causation. But still.
While no one overhear you quickly tell me not cow cow.
but how about watch phone?
User avatar
phlip
Restorer of Worlds
 
Posts: 7165
Joined: Sat Sep 23, 2006 3:56 am UTC
Location: Australia

Re: "Correlation" Discussion

Postby bungadunga » Fri Mar 06, 2009 6:37 am UTC

My stats teacher'll love this.


Oh, and AP level stats is so INCREDIBLY easy. It's just "Run these numbers through that formula. Then write 3 sentences about what the number it spits out means." So. Easy.
bungadunga
 
Posts: 16
Joined: Mon Aug 25, 2008 4:05 am UTC

Re: "Correlation" Discussion

Postby alias.exe » Fri Mar 06, 2009 6:43 am UTC

This whole "correlation != causation" could be the beginning of a very slippery slope...
User avatar
alias.exe
 
Posts: 36
Joined: Thu Feb 12, 2009 11:18 am UTC

Re: "Correlation" Discussion

Postby iabervon » Fri Mar 06, 2009 6:44 am UTC

I'm just waiting for the day when the statement "past performance is no guarantee of future results", which has always performed well in the past, stops being a reliable predictor of its future behaviour. Eventually, it has to, and then everything will be predictable from there on out. Right?
iabervon
 
Posts: 32
Joined: Fri Nov 03, 2006 5:25 am UTC

Re: "Correlation" Discussion

Postby LuNatic » Fri Mar 06, 2009 6:47 am UTC

phlip wrote:
russianspy1234 wrote:i actually very recently got into an argument about this in a chat. turns out, the actual statistical definition of "implies" is different from the day to day usage, and it does actually mean "proves", which is what my argument was, that it does imply causation, but doesnt prove it.

Not just in statistics... "implies" has that definition in all of mathematics.

Strictly, the sentence "Correlation does not imply causation" is equivalent to "There exist scenarios where A and B are correlated, but A does not cause B." (Alternatively, "Correlation does imply causation" is equivalent to "In all situations where A is correlated to B, A causes B.")

[edit] sje: admittedly, the fact that your fake rants got very old quite a while ago and the fact that they're really not that funny are correlated, but that doesn't imply causation. But still.


Wait, how? Doesn't imply = implicit?
Cynical Idealist wrote:
Velict wrote:Good Jehova, there are cheesegraters on the blagotube!

This is, for some reason, one of the funniest things I've read today.
User avatar
LuNatic
 
Posts: 973
Joined: Thu Nov 20, 2008 4:21 am UTC
Location: The land of Aus

Re: "Correlation" Discussion

Postby PhantomPhanatic » Fri Mar 06, 2009 6:52 am UTC

Gotta say, I loved the alt text on this one. As if the comic itself didn't make me laugh enough, the imagery of waggling eyebrows really got me.
We can lick gravity, but sometimes the paperwork is overwhelming.
-- Wernher Von Braun
User avatar
PhantomPhanatic
 
Posts: 84
Joined: Thu Nov 13, 2008 5:32 am UTC

Re: "Correlation" Discussion

Postby godlygeek » Fri Mar 06, 2009 7:01 am UTC

LuNatic wrote:
phlip wrote:
russianspy1234 wrote:i actually very recently got into an argument about this in a chat. turns out, the actual statistical definition of "implies" is different from the day to day usage, and it does actually mean "proves", which is what my argument was, that it does imply causation, but doesnt prove it.

Not just in statistics... "implies" has that definition in all of mathematics.

Strictly, the sentence "Correlation does not imply causation" is equivalent to "There exist scenarios where A and B are correlated, but A does not cause B." (Alternatively, "Correlation does imply causation" is equivalent to "In all situations where A is correlated to B, A causes B.")


Wait, how? Doesn't imply = implicit?


Not in mathematics. :D A implies B means "if A is true, then B must also be true", or, alternately, A implies B unless A and not B.

Truth table for logical implication:
Code: Select all
+===+===+=============+
| A | B | A implies B |
+===+===+=============+
| F | F |      T      |
| F | T |      T      |
| T | F |      F      |
| T | T |      T      |
+===+===+=============+
godlygeek
 
Posts: 2
Joined: Sat Jan 31, 2009 6:49 am UTC

Re: "Correlation" Discussion

Postby stone915 » Fri Mar 06, 2009 7:11 am UTC

(p implies q) == (p -> q) == (if p, then q) == (q if p) == (q whenever p) == (p only if q (contrapositive))

discrete math classes are fun!
stone915
 
Posts: 42
Joined: Wed Jan 07, 2009 4:31 am UTC

Re: "Correlation" Discussion

Postby dabigkid » Fri Mar 06, 2009 7:19 am UTC

Something tells me that the music-SAT score thing inspired this comic (which isn't really bullshit because of correlation/causation but for statistical quirks and unreliable self-reporting).
wut
dabigkid
 
Posts: 56
Joined: Wed May 09, 2007 3:09 am UTC
Location: NJ

Re: "Correlation" Discussion

Postby fabiocbinbutter » Fri Mar 06, 2009 8:20 am UTC

prometheus3737 wrote:This comic reminds me of the thoroughly well-proven fact that the decline of 18th century style pirate is the direct cause of global warming, as illustrated by this graph:
Image


Lol... I liked the comic, but I liked this post more... this graph makes no sense! :shock: It looks like they put the X-axis on the data labels, put the data values along the X-axis, then just made whatever curve they thought looked pretty. I don't know what's worse, the ludicrous statement they were mocking or the patently incorrect way they did so.
fabiocbinbutter
 
Posts: 13
Joined: Sat Oct 18, 2008 4:55 am UTC

Next

Return to Individual XKCD Comic Threads

Who is online

Users browsing this forum: dalcde, Hiferator, Klear, orthogon and 12 guests