April 24, 2017
Briefly
- The Herald (from the Daily Mail) recommends drinking beetroot juice, based on a study of brain waves: “This finding could help people who are at-risk of brain deterioration to remain functionally independent, such as those with a family history of dementia“. The NHS Choices blog commented on a similar study by the same research group in 2010; their comments still apply.
- Testimonials and motivational speakers tell you “I did this and look how it turned out”. As XKCD illustrates, results may not be typical
- “Data made available for reanalysis, a journal that promptly responded to the outcomes of that reanalysis, and a finding that could save lives.” (from Stat). Another moral to the story: don’t edit data by copy-and-paste.
- “The company says it has studies that back up its claims, but refused to release them on the grounds that they are commercial-in-confidence.” It appears that Johnson & Johnson would rather pull their ad than let people look at the evidence. (from The Age)
- “it’s not acceptable if you’ve got the information readily available to leave it to the last minute for release, that’s not what the Act says you can do” The Chief Ombudsman interviewed by Newsroom about the Official Information Act.
And finally
I ended a recent #SciComm talk with this slide of questions scientists should answer even if they’re not asked: pic.twitter.com/N88LuuSBoM
— Rachel Feltman (@RachelFeltman) April 11, 2017
Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »