INFORMATION

This website uses cookies to store information on your computer. Some of these cookies are essential to make our site work and others help us to improve by giving us some insight into how the site is being used. For further information, see our Privacy Policy. Continuing to use this website is acceptance of these cookies.

Correlation v causation

Any topic related to science can be discussed here.
Post Reply
Message
Author
User avatar
Alan H
Posts: 24067
Joined: July 3rd, 2007, 10:26 pm

Correlation v causation

#1 Post by Alan H » April 16th, 2015, 1:40 pm

...or storks v births...

Cigarettes, damn cigarettes and statistics

A very easy and informative read.
Alan Henness

There are three fundamental questions for anyone advocating Brexit:

1. What, precisely, are the significant and tangible benefits of leaving the EU?
2. What damage to the UK and its citizens is an acceptable price to pay for those benefits?
3. Which ruling of the ECJ is most persuasive of the need to leave its jurisdiction?

Ron Webb
Posts: 289
Joined: May 9th, 2009, 11:21 pm

Re: Correlation v causation

#2 Post by Ron Webb » May 7th, 2015, 3:37 pm

Interesting, and well worth the read.

I loved his last paragraph. I have to admit I missed the sarcasm the first time I read it, and was momentarily bewildered. (There is definitely something to be said for smilies. :wink: )
It’s not clear why Huff and Fisher were so fixated on the idea that the growing evidence on smoking was a mere correlation. Both of them were paid as consultants by the tobacco industry and some will believe that the consulting fees caused their scepticism. It seems just as likely that their scepticism caused the consulting fees. We may never know.

thundril
Posts: 3607
Joined: July 4th, 2008, 5:02 pm

Re: Correlation v causation

#3 Post by thundril » May 7th, 2015, 5:04 pm

Ron Webb wrote:Interesting, and well worth the read.

I loved his last paragraph. I have to admit I missed the sarcasm the first time I read it, and was momentarily bewildered. (There is definitely something to be said for smilies. :wink: )
"There is no font called ironic".
Dunno who first said that, but IIRC, it was pre-internet.

stevenw888
Posts: 694
Joined: July 16th, 2010, 12:48 pm

Re: Correlation v causation

#4 Post by stevenw888 » May 12th, 2015, 2:00 pm

Yes, correlation vs causation is a fascinating subject area. It brings me to the subject of high heels.
An American cancer specialist, Dr David Agus claims (I'm not sure if this is peer-reviewed) that wearing high heeled shoes can lead to increased risk of Alzheimer's (as well as heart-disease and cancer).

The correlation is straightforward. Women (generally) wear high heeled shoes. Men do not. Alzheimers disease is not equally present between the sexes. 66% of elderly people with alzheimer's are women, and only 34% men (source David Sheard - Dementia Care Matters 2012). There must be a reason why more women get Alzheimers than men. But is it high heeled shoes? If the cause is high heeled shoes, do more women get cancer more than men? I guess it depends on the type of cancer.
Definitely more research required here. But it's easy to jump to the causation link, once your mind has spotted the correlation link.
"There are old pilots and there are bold pilots, but there are no old, bold pilots." - From the film "Top Gun"

User avatar
Altfish
Posts: 1821
Joined: March 26th, 2012, 8:46 am

Re: Correlation v causation

#5 Post by Altfish » May 12th, 2015, 3:53 pm

stevenw888 wrote:Yes, correlation vs causation is a fascinating subject area. It brings me to the subject of high heels.
An American cancer specialist, Dr David Agus claims (I'm not sure if this is peer-reviewed) that wearing high heeled shoes can lead to increased risk of Alzheimer's (as well as heart-disease and cancer).

The correlation is straightforward. Women (generally) wear high heeled shoes. Men do not. Alzheimers disease is not equally present between the sexes. 66% of elderly people with alzheimer's are women, and only 34% men (source David Sheard - Dementia Care Matters 2012). There must be a reason why more women get Alzheimers than men. But is it high heeled shoes? If the cause is high heeled shoes, do more women get cancer more than men? I guess it depends on the type of cancer.
Definitely more research required here. But it's easy to jump to the causation link, once your mind has spotted the correlation link.
You could argue that it is caused by wearing bras.

stevenw888
Posts: 694
Joined: July 16th, 2010, 12:48 pm

Re: Correlation v causation

#6 Post by stevenw888 » May 12th, 2015, 4:56 pm

You could indeed, Altfish. Hence the feminist chant...
"There are old pilots and there are bold pilots, but there are no old, bold pilots." - From the film "Top Gun"

User avatar
Alan H
Posts: 24067
Joined: July 3rd, 2007, 10:26 pm

Re: Correlation v causation

#7 Post by Alan H » June 13th, 2015, 8:08 pm

I think we may have had this before, but... Spurious correlations
Alan Henness

There are three fundamental questions for anyone advocating Brexit:

1. What, precisely, are the significant and tangible benefits of leaving the EU?
2. What damage to the UK and its citizens is an acceptable price to pay for those benefits?
3. Which ruling of the ECJ is most persuasive of the need to leave its jurisdiction?

thundril
Posts: 3607
Joined: July 4th, 2008, 5:02 pm

Re: Correlation v causation

#8 Post by thundril » June 17th, 2015, 4:16 pm

:pointlaugh: Extremely useful for deflating conspiracy theorists!

User avatar
Dave B
Posts: 17809
Joined: May 17th, 2010, 9:15 pm

Re: Correlation v causation

#9 Post by Dave B » June 17th, 2015, 4:46 pm

Alan H wrote:I think we may have had this before, but... Spurious correlations
Think we have but worth a review.

Hmm, cheese and death by bed sheet? I know that cheese in the evening gives me weird dreams . . .
"Look forward; yesterday was a lesson, if you did not learn from it you wasted it."
Me, 2015

User avatar
Tetenterre
Posts: 3244
Joined: March 13th, 2011, 11:36 am

Re: Correlation v causation

#10 Post by Tetenterre » June 18th, 2015, 9:31 am

If you go to the old version of the site, you can choose your own correlations from drop-down lists.
Steve

Quantum Theory: The branch of science with which people who know absolutely sod all about quantum theory can explain anything.

Post Reply