# when is correlation not causation? **URL:** \ **Category:** Factual Questions\ **Created:** [February 19, 2009, 11:32pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633 "2009-02-19T23:32:08Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![CC](https://avatars.discourse-cdn.com/v4/letter/c/f1d935/32.png) [@CC](https://boards.straightdope.com/u/CC)\ **Post date:** [February 19, 2009, 11:32pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/1 "2009-02-19T23:32:08Z")
Maybe this doesn’t go in GQ, and I’ll seek it out elsewhere if the mods move it - but, I’m looking for a couple of simple and dramatic examples to show that correlation does not necessarily mean causation. Dopers - any help? xo, C. ---
**Author:** ![Bill\_Door](https://avatars.discourse-cdn.com/v4/letter/b/50afbb/32.png) [@Bill\_Door](https://boards.straightdope.com/u/Bill_Door)\ **Post date:** [February 19, 2009, 11:34pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/2 "2009-02-19T23:34:14Z")
The trees moving does not make the wind blow. ---
**Author:** ![Cagey\_Drifter](https://avatars.discourse-cdn.com/v4/letter/c/b2d939/32.png) [@Cagey\_Drifter](https://boards.straightdope.com/u/Cagey_Drifter)\ **Post date:** [February 19, 2009, 11:35pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/3 "2009-02-19T23:35:58Z")
the famous example is that July has the most ice cream sales and also the most rapes. The sale of ice cream does not cause people to be raped. ---
**Author:** ![Vlad\_Igor](https://avatars.discourse-cdn.com/v4/letter/v/7feea3/32.png) [@Vlad\_Igor](https://boards.straightdope.com/u/Vlad_Igor)\ **Post date:** [February 19, 2009, 11:42pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/4 "2009-02-19T23:42:40Z")
Correlation is not causation when there is no demonstrable causative link between two phenomenon other than a co-occurance. IOW, you have to see the transmission turn in order to say unequivocally that the engine drives the wheels of a car. Another example I heard several years ago was that there was an increase in DUIs and in the number of Baptist ministers. Corr=Caus would imply that Baptist ministers were responsible for the DUIs, when in fact both were a reflection of an increasing population in the US. Vlad/Igor ---
**Author:** ![Kevbo](https://avatars.discourse-cdn.com/v4/letter/k/e47774/32.png) [@Kevbo](https://boards.straightdope.com/u/Kevbo)\ **Post date:** [February 19, 2009, 11:46pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/5 "2009-02-19T23:46:56Z")
40% of automotive collisions are caused by drunk drivers. Therefore we can conclude that sobriety causes 60% of collisions. ---
**Author:** ![ultrafilter](https://avatars.discourse-cdn.com/v4/letter/u/3d9bf3/32.png) [@ultrafilter](https://boards.straightdope.com/u/ultrafilter)\ **Post date:** [February 19, 2009, 11:48pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/6 "2009-02-19T23:48:27Z")
Outside of a properly designed and controlled experiment, correlation never implies causation. ---
**Author:** ![Just](https://avatars.discourse-cdn.com/v4/letter/j/4af34b/32.png) [@Just](https://boards.straightdope.com/u/Just)\ **Post date:** [February 19, 2009, 11:50pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/7 "2009-02-19T23:50:04Z")
Wiki has some examples: [http://en.wikipedia.org/wiki/Correlation\_causation](http://en.wikipedia.org/wiki/Correlation_causation) > [@](#): > > In a widely-studied example, numerous epidemiological studies showed that women who were taking combined hormone replacement therapy (HRT) also had a lower-than-average incidence of coronary heart disease (CHD), leading doctors to propose that HRT was protective against CHD. But controlled trials showed that HRT caused a small and significant increase in risk of CHD. Re-analysis of the data showed that women undertaking HRT were more likely to be from socio-economic groups ABC1, with better than average diet and exercise regimes. The two were coincident effects of a common cause, rather than cause and effect as had been supposed.[1] ---
**Author:** ![pravnik](https://avatars.discourse-cdn.com/v4/letter/p/8edcca/32.png) [@pravnik](https://boards.straightdope.com/u/pravnik)\ **Post date:** [February 19, 2009, 11:50pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/8 "2009-02-19T23:50:42Z")
On Monday, I drank gin and tonic, and got drunk. On Tuesday, I drank vodka and tonic, and got drunk. On Wednesday, I drank scotch and tonic, and got drunk. On Thusday, I drank rum and tonic, and got drunk. On Friday, I drank rye and tonic and got drunk. Clearly, tonic water makes me drunk. ---
**Author:** ![Chessic\_Sense](https://avatars.discourse-cdn.com/v4/letter/c/7c8e57/32.png) [@Chessic\_Sense](https://boards.straightdope.com/u/Chessic_Sense)\ **Post date:** [February 19, 2009, 11:51pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/9 "2009-02-19T23:51:09Z")
The more ice cream one eats, the lower the chance one will commit a crime. Thefore, ice cream stops crime. 8th graders are taller than 3rd graders. Therefore, one must grow tall in order to graduate. Just think of any scenario where Z causes both X and Y. Then make the ridiculous statement that X causes Y. ---
**Author:** ![Spiratu](https://avatars.discourse-cdn.com/v4/letter/s/47e85d/32.png) [@Spiratu](https://boards.straightdope.com/u/Spiratu)\ **Post date:** [February 20, 2009, 12:28am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/10 "2009-02-20T00:28:17Z")
At the risk of turning this into a great debate, another classic case might be that where [the number of pirates in the world is inversely correlated with the rise in average global temperature.](http://www.venganza.org/about/open-letter/) ---
**Author:** ![Squink](https://avatars.discourse-cdn.com/v4/letter/s/b5e925/32.png) [@Squink](https://boards.straightdope.com/u/Squink)\ **Post date:** [February 20, 2009, 12:30am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/11 "2009-02-20T00:30:59Z")
Every day the sun comes up, a man is murdered. That’s been true 365 days a year, probably for the last 10,000 years. ---
**Author:** ![AHunter3](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/ahunter3/32/368_2.png) [@AHunter3](https://boards.straightdope.com/u/AHunter3)\ **Post date:** [February 20, 2009, 1:14am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/12 "2009-02-20T01:14:25Z")
A more pernicious example is one in which the two elements being compared are correlated because they are not causal but are in fact two wordings (and/or two experimental operationalizations) of the exact same thing. Being a freshman neither causes nor is caused by your being a 1st year student in college. While this is obvious, there are plenty of less obvious situations. Language is messy and the experimental mechanism by which Variable 1 is implemented (“in our experiment, this is what it means to ‘be a freshman’…”) can look enough different from that used for Variable 2 that unless you are sufficiently familiar with the topic area of study you may not notice that the study has essentially proven that there’s a very high “correlation” between being a 1st year student and being a freshman among college students studied. ---
**Author:** ![Half\_Man\_Half\_Wit](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/half_man_half_wit/32/21766_2.png) [@Half\_Man\_Half\_Wit](https://boards.straightdope.com/u/Half_Man_Half_Wit)\ **Post date:** [February 20, 2009, 1:29am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/13 "2009-02-20T01:29:06Z")
There are also those cases where the occurrence of thing x doesn’t prevent thing y – the fact that everybody that eats bread will die eventually doesn’t mean that bread is lethal. ---
**Author:** ![Exapno\_Mapcase](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/exapno_mapcase/32/1051_2.png) [@Exapno\_Mapcase](https://boards.straightdope.com/u/Exapno_Mapcase)\ **Post date:** [February 20, 2009, 2:12am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/14 "2009-02-20T02:12:50Z")
TheDow Jones Average tends to rise in periods when womens’ hemlines also rise. ---
**Author:** ![slaphead](https://avatars.discourse-cdn.com/v4/letter/s/e9bcb4/32.png) [@slaphead](https://boards.straightdope.com/u/slaphead)\ **Post date:** [February 20, 2009, 9:03am UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/15 "2009-02-20T09:03:21Z")
> [@Cagey\_Drifter](#): > > the famous example is that July has the most ice cream sales and also the most rapes. The sale of ice cream does not cause people to be raped. Blimey, that’s a bit grim. When I was a schoolkid they used a graph showing number of stork sightings and number of births in sweden over a many-year period, which had a close correlation even though the two don’t have anything to do with each other. A quick google suggests it’s still very widely used in teaching, although I’m not 100% sure the example is factual. ---
**Author:** ![CC](https://avatars.discourse-cdn.com/v4/letter/c/f1d935/32.png) [@CC](https://boards.straightdope.com/u/CC)\ **Post date:** [February 20, 2009, 3:50pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/16 "2009-02-20T15:50:32Z")
Thank you, all. Could you also come up with some good, dramatic examples of the \*post hoc \*falacy? ---
**Author:** ![Isosleepy](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/isosleepy/32/479_2.png) [@Isosleepy](https://boards.straightdope.com/u/Isosleepy)\ **Post date:** [February 20, 2009, 4:03pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/17 "2009-02-20T16:03:04Z")
Post Hoc: Often, when a lot of people bring umbrellas, it will start to rain. ---
**Author:** ![RealityChuck](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/realitychuck/32/195_2.png) [@RealityChuck](https://boards.straightdope.com/u/RealityChuck)\ **Post date:** [February 20, 2009, 4:32pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/18 "2009-02-20T16:32:36Z")
The Super Bowl winner predicts if the stock market goes up or down. Post hoc: The rooster crowing causes the sun to rise. ---
**Author:** ![Don\_t\_Call\_Me\_Shirley](https://avatars.discourse-cdn.com/v4/letter/d/f4b2a3/32.png) [@Don\_t\_Call\_Me\_Shirley](https://boards.straightdope.com/u/Don_t_Call_Me_Shirley)\ **Post date:** [February 20, 2009, 4:41pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/19 "2009-02-20T16:41:12Z")
In children, there is a strong correlation between shoe size and reading ability. ---
**Author:** ![schindler](https://avatars.discourse-cdn.com/v4/letter/s/ba9def/32.png) [@schindler](https://boards.straightdope.com/u/schindler)\ **Post date:** [February 20, 2009, 5:22pm UTC](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633/20 "2009-02-20T17:22:13Z")
Johnny Damon playing for the Red Sox correlated well with the Yankees losing games against them. Since baseball is not basketball, soccer, hockey, or any other symmetrical team sport, there doesn’t seem to have been a causal link between his presence and the Yankees inferior performance as a team-- unless you believe in juju, karma, voodoo, or effecting metaphysical change by having really long hair. [Next page](https://boards.straightdope.com/t/when-is-correlation-not-causation/486633.md?page=2)