Statistical flaws revealed in top journals' papers

AI Thread Summary
Recent findings indicate that two prominent scientific journals, Nature and the British Medical Journal, have been identified for frequently publishing articles with statistical inaccuracies. Spanish researchers conducted an analysis revealing that 38% of papers in Nature and 25% in the BMJ contained at least one statistical error. The study also suggested that approximately 4% of results deemed statistically significant may actually lack significance. This raises concerns about the reliability of published research and suggests that similar issues could be present in other mainstream scientific journals. The discussion highlights broader issues in the handling of statistics within scientific publishing, emphasizing the need for improved accuracy and scrutiny in research reporting.
Monique
Staff Emeritus
Science Advisor
Gold Member
Messages
4,211
Reaction score
68
http://www.newscientist.com/news/news.jsp?id=ns99995051"

Two of the world's top scientific journals, Nature and the British Medical Journal, have been found guilty of routinely publishing figures that do not add up.

The evidence comes from Spanish researchers who found a surprisingly large number of statistical errors in the two journals. They warn that the same may well be true of other mainstream journals.

The analysis revealed that at least one error appeared in 38 per cent of the Nature papers and 25 per cent of the BMJ papers looked at. Furthermore, the study estimates that four per cent of results reported to be statistically "significant" may not be significant after all. :eek:

http://www.newscientist.com/news/news.jsp?id=ns99995051"
Rounding numbers seems to be a difficult task for some..
 
Last edited by a moderator:
Biology news on Phys.org
I am not surprised. Statistics and probability seem to be reduced to folklore theorems and rules of thumb even in branches of quantitative science.
 
Well that isn't very encouraging. Then again I have witnessed papers get rejected from other journals where the editor had requested "additional information" that was in the paper already.
 
I've been reading a bunch of articles in this month's Scientific American on Alzheimer's and ran across this article in a web feed that I subscribe to. The SA articles that I've read so far have touched on issues with the blood-brain barrier but this appears to be a novel approach to the problem - fix the exit ramp and the brain clears out the plaques. https://www.sciencealert.com/new-alzheimers-treatment-clears-plaques-from-brains-of-mice-within-hours The original paper: Rapid amyloid-β...
https://www.discovermagazine.com/the-deadliest-spider-in-the-world-ends-lives-in-hours-but-its-venom-may-inspire-medical-miracles-48107 https://en.wikipedia.org/wiki/Versutoxin#Mechanism_behind_Neurotoxic_Properties https://www.sciencedirect.com/science/article/abs/pii/S0028390817301557 (subscription or purchase requred) The structure of versutoxin (δ-atracotoxin-Hv1) provides insights into the binding of site 3 neurotoxins to the voltage-gated sodium channel...
Back
Top