Amadio, Dean wrote:
> You may be misinterpreting my posts. My interpretation of your posts was that 
> you were negating all correlational research. I'm not sure if you meant this, 
> but it's what I gathered from your posts. When I questioned calling "these 
> studies ridiculous" - I thought you were referring to ALL correlational 
> studies, not just the current study.
>
>   
Dean,

You continue to recycle this crude misrepresentation of my view despite 
my repeated explanations. I'll say it one last time. One can 
legitimately draw from correlational studies only the conclusions 
appropriate to correlation. They might suggest the possibility of a 
casual link, but they cannot establish one, and it is irresponsible for 
one (whether the researcher or the media) to announce that a causal link 
has been discovered on the basis of a correlational study alone. The 
very first sentence of the article read, "Consuming just one drink a day 
causes an extra 7,000 cancer cases - mostly breast cancer - in UK women 
each year." The tobacco-cancer link was not based on correlational 
studies alone, so the analogy is spurious. (By the way, I never wrote 
"these ridiculous studies." If you are going to use quotation marks, 
please quote. What I wrote was "...ridiculous correlational studies that 
are sensationally publicized as finding causation effects." What is 
ridiculous is the misinterpretation that makes a mildly interesting 
finding seem like a crisis. Perhaps you haven't been on this list very 
long, but we have a member who collects correlation-causation confusions 
of this sort into a website for his students, and several TIPSters 
periodically contribute new examples. This was one.)

What you have not responded to  is my running of the numbers. EVEN IF 
this causal link had been established, we are talking about an increase 
in risk of about 2 in 10,000. Does that strike you as Big News? By 
contrast the increased risk of developing lung cancer from smoking is 
about 130 in 1000 -- 1300 in 10,000, to put it on an equivalent base.* 
So, there is simply no reasonable comparison between the two effects: 2 
vs. 1300.


Chris

*see http://www.ncbi.nlm.nih.gov/pubmed/7895211. I simply averaged 
across male and female numbers. The risk probably higher than this 
because there are more male than female smokers.

-- 

Christopher D. Green
Department of Psychology
York University
Toronto, ON M3J 1P3
Canada

 

416-736-2100 ex. 66164
[email protected]
http://www.yorku.ca/christo/

==========================


---
To make changes to your subscription contact:

Bill Southerly ([email protected])

Reply via email to