Retractions as political statement
From Retraction Watch, a story about a retraction is really a story about Nature’s failure to publish a refutation:
#publication bias
12 posts
Related posts may also appear under #bias on the blog page.
- Read more → More from Meta-science →
-
Pressure to publish and the prevalence of positive results
Read more → More from Meta-science →This PLoS One study attempted to look at how pressure to publish might influence the prevalence of positive results. The author, Daniele Fanelli, made an odd choice by using ‘papers per capita by state’ as the measure of pressure to publish. The state seems way too macro a level to look at. I would expect pressure to vary strongly between schools and between departments within schools. There’s no reasoning for this given in the paper - I suspect that it was just simpler to use this measure, already provided by the NSF, then to come up with a method for looking at individual institutions.
-
Softer sciences publish more positive results
Read more → More from Meta-science →A colleague referenced this 2010 paper which measures proportion of positive results by scientific discipline.
-
Solutions: P-Curves
Read more → More from Meta-science →A paper and associated web-based tool have been proposed to detect publication bias and p-hacking in the literature. From the paper:
-
Power failure
Read more → More from Meta-science →There’s a new article out in Nature Reviews Neuroscience about the failure of scientific studies in general (and neuroscience and fMRI studies in particular) to adequately power their studies. The NRN paper isn’t open access, but you can email the authors for a pre-print. There’s a good write-up at National Geographic.
-
Trials with positive results published faster, more often than trials with negative results
Read more → More from Meta-science →A new PLoS one paper looked at the outcome of 1054 trials submitted to the ethics committee of a major Spanish hospital from 1997-2004. This flowchart captures the basic results:
-
Most medical research: true or false?
Read more → More from Meta-science →A friend forwarded me this paper, “Empirical estimates suggest most published medical research is true”, perhaps in an attempt to challenge my cynicism. I like to believe I am open to being challenged, and I do recognize that purposefully cataloging problems with research leaves me biased. But I don’t think this paper is the best counterpoint.
-
Bias in reporting efficacy and toxicity in breast cancer trials
Read more → More from Meta-science →A recent paper did an analysis of breast cancer studies published over the last 16 years. They evaluated 164 trials and looked at whether results re: the drug’s toxicity or overall survival rate was reported prominently in the abstract, within the article, or at all. They looked at who funded the work, the impact factor of the journal the work was published in, and most interestingly, whether the trial found positive or negative results.
-
False-Positive Psychology
Read more → More from Meta-science →Quoting my own write up:
-
"I don’t really believe about 95% of what gets published."
Read more → More from Meta-science →Vaughn Bell of Mind Hacks interviews researchers about the problems with fMRI:
-
Why Most Published Research Findings Are False
Read more → More from Meta-science →Why Most Published Research Findings Are False
-
The decline effect and the scientific method
Read more → More from Meta-science →The decline effect and the scientific method