Not too long ago, a startling finding was published in the prestigious 
_Proceedings of the Royal Society B: Biological Sciences_ . Translated 
from boring science-speak into attention-grabbing journalistese, it 
claimed that to make boys, eat cereal. The press went crazy.

(e.g. see http://www.news.com.au/story/0,23599,23589385-1702,00.html )

The Kellogg bros who invented breakfast cereal (and who thought it was 
only good for good health and possibly to cure masturbation) would be 
delighted. But just as hordes of boy-preferring parents were girding 
their loins to produce boys by having potential mommies chow down on corn 
flakes (plus sex, of course, which the Kelloggs weren't so keen on), 
there came a sober second thought from elsewhere.

The party-pooping thought was to check the statistics in the article.  
Sure enough, our favourite boogy-man,  multiple uncorrected comparisons,  
makes an appearance (264 of them, to be exact).

Conclusion: not cereal but chance was most likely responsible for the 
slight excess of male births, and for lack of a Bonferroni,  the 
conclusion was lost. 

See:  Study Refutes Notion That Eating A Certain Cereal Will Result In 
More Male Babies
http://www.sciencedaily.com/releases/2009/01/090114075759.htm

The published article is:

Cereal-induced gender selection? Most likely a multiple testing false 
positive. Proceedings of the Royal Society B: Biological Sciences. 
Authors: S. Stanley Young, Heejung Bang and Kutluk Oktay  
Published online Jan 13/09. 

You can get a peek at the first page at:
http://tinyurl.com/9afxrb

 Stephen
-----------------------------------------------------------------
Stephen L. Black, Ph.D.          
Professor of Psychology, Emeritus   
Bishop's University      e-mail:  [email protected]
2600 College St.
Sherbrooke QC  J1M 1Z7
Canada

Subscribe to discussion list (TIPS) for the teaching of
psychology at http://flightline.highline.edu/sfrantz/tips/
-----------------------------------------------------------------------

---
To make changes to your subscription contact:

Bill Southerly ([email protected])

Reply via email to