Welcome to Science is So Sexy!!


For more weekly science articles by Esmeralda,


visit www.mybugsandi.com.


See you Soon for more Sexy Science
Great value Unlimited Broadband from an award winning provider

Sunday, 1 June 2014

Difference between Correlation and Causation

My Dear Sexy Readers,

Maybe you've seen this blog on Correlations on Facebook like I have, it was posted through a group called "I -Blipping- Hate PseudoScience" . Now, you might wonder why the Sexy Hell I would talk about Correlations!!! Well, this is kind of a fun explanation on the difference between Correlation and Causation. So I thought I would apply the concept to something I wrote previously and which I know you guys are very interested in.
You might recall this previous Sexy article on Parabens and the bit about Breast Cancer:
"It has been suggested that the use of Parabens in cosmetics and especially in deodorants and anti-perspirants might contribute to the high incidence of this type of cancer. Parabens were detected in tissue samples from human breast tumors........ It has to be noted that in that famous study (Darbre, 2004) that sparked the whole controversy on Parabens, there were no control tissues to demonstrate specificity of association between Parabens and breast cancer, ie. normal healthy tissues could still contain Parabens and be harmless, the presence of Parabens not being the cause of cancer but merely an innocent spectator. To date, no other study has repeated this 2004 study with the appropriate controls. There were however two epidemiological studies (by questioning patients, no lab testing involved) attempting to address the link between breast cancer and deodorant/antiperspirants. One reported no difference of use between cancer patients and non cancer people. The second one reported an earlier onset of the breast cancer with the use of  underarms cosmetics. But again, both studies lacked appropriate controls and certainly lab experiments to attest the presence of Parabens."
 Now, this is an example of graph you can find on this extraordinary blog:

Correaltion
Correlation between Divorce rate in Maine and Consumption of margarine per capita. From HERE

This graphs shows that Divorce rate in Maine CORRELATES with consumption of margarine (per capita) in the US - However it doesn't mean that if you eat margarine and you live in Maine, it will CAUSE you to get divorced or that if you eat margarine, people in Maine will have an increased chance of getting a divorce.

Correlation no causation
Correlation between the age of Miss America and the number of murders by steam, hot vapours and hot objects. From HERE

This graphs shows that the Age of Miss America CORRELATES with the number of Murders by steam, hot vapours and hot objects - However, it doesn't mean that if Miss America is 23 years old, it will CAUSE 7 murders due to steam, hot vapours and hot objects.

So, of course these examples are dramatic but I think they illustrate quite well the difference between Correlation and Causation, and they make me laugh so much, I thought I would share it with you, Sexy Reader!
Now... Coming back to the above correlation about Parabens and Breast cancer:

If you find Parabens in nanograms in breast cancer tissue, it doesn't mean that it was the CAUSE of breast cancer, nor doesn't it mean that if you use anti-perspirant, it will cause you to be more likely to develop breast cancer.

This infamous 10 year old study has never seen its sequel, maybe simply because there is NO causation.

See you Soon for more Sexy Science,






Disclaimer: I haven't come across any new study on this but I can't keep up to date with everything, so apologies if the causative link has been scientifically proven and I'll be happy to amend my articles.

0 Sexy People gave their opinion:

Post a Comment

Note: only a member of this blog may post a comment.

Sharing is Sexy

Great value Unlimited Broadband from an award winning provider