Dissident Veteran For Peace

I complain about the routine dishonesty of mainstream and Left media outlets because they are my main sources of news and commentary. However, I have zero illusions about the routine accuracy and integrity of Right media outlets.

A case in point is a recent article by Jordan Davidson on the site of The Federalist titled: "Major Study Finds Masks Don't Reduce COVID-19 Infection Rates". In the body of Davidson's article it is claimed: "A high-quality, large-scale Danish study finds no evidence that wearing a face mask significantly minimizes people's risk of contracting COVID-19." 

However, right in the Danish article's abstract the authors, Bundgaard et al., state: "Although the difference observed was not statistically significant, the 95% CIs are compatible with a 46% reduction to a 23% increase in infection."

Davidson writes: 

After a month, 42 of the mask-wearers in the study (1.8 percent) were infected with the virus while 53 of the non-mask-wearers (2.1. percent) were infected with the virus. Statistically, this is not a significant difference between the two groups, suggesting these infection differences were a product of chance, say the study authors.

Echoing similar misinformation from the New York Times, Davidson again misleads her readers by misrepresenting the meaning and importance of a lack of statistical significance.* In fact, Bundgaard et al. use the word "chance" exactly nowhere in their article. They actually describe their findings as "inconclusive" rather than attributable to mere "chance".

In the "Discussion" section of the Bundgaard et al. article it says:

The findings ... should not be used to conclude that a recommendation for everyone to wear masks in the community would not be effective in reducing SARS-CoV-2 infections, because the trial did not test the role of masks in source control of SARS-CoV-2 infection. [emphasis added]

In other words, Davidson did exactly what the authors said she shouldn't do based on their work.

In the "Discussion" the authors again note that one of several limitations of their study was that it made "no assessment of whether masks could decrease disease transmission from mask wearers to others." In other words, the study offers no evidence about whether masks do or don't prevent COVID-19 infected mask wearers from infecting other people.

Moreover, as Bundgaard et al. indicate in their "Intervention" section, they were testing the effects of "no mask recommendation" versus "a recommendation to wear a mask". They were not testing masks or mask wearing per se. Also, only "46% of participants wore the mask as recommended" but Bundgaard et al. did not exclude from their results people in the mask recommendation group who were "predominantly" but not fully compliant with the mask recommendation. Only the 7% whose compliance was characterized as "not as recommended" were excluded.

In short, the Danish study says what pretty much any sensible person already realized—masks alone are not a silver bullet but there is evidence that they do help reduce the spread of COVID-19 from infected people to non-infected mask wearers.

Liar, manipulators, and incompetents working in the media depend upon the fact that most people will never question their reporting or never question it enough to do their own research. It also bears remembering that reporters and editors are also fallible humans—not every error or falsehood reported is deliberate. In any case, when it comes to important matters never blindly trust a media outlet (or a politician) to be accurate or honest.

###

* A note on "statistical significance": Davidson is not alone in botching the reporting on "statistical significance" the Danish authors do it, too. In 2019's, "Moving to a World Beyond 'p < 0.05' " the editors of the journal of the American Statistical Association write:

... it is time to stop using the term "statistically significant" entirely. Nor should variants such as "significantly different," "p < 0.05," and "nonsignificant" survive, whether expressed in words, by asterisks in a table, or in some other way.

Regardless of whether it was ever useful, a declaration of "statistical significance" has today become meaningless. Made broadly known by Fisher's use of the phrase (1925), Edgeworth's (1885) original intention for statistical significance was simply as a tool to indicate when a result warrants further scrutiny. But that idea has been irretrievably lost. Statistical significance was never meant to imply scientific importance, and the confusion of the two was decried soon after its widespread use (Boring 1919). Yet a full century later the confusion persists.

They also offer this guidance:

• Don't base your conclusions solely on whether an association or effect was found to be "statistically significant" (i.e., the p-value passed some arbitrary threshold such as p < 0.05).
• Don't believe that an association or effect exists just because it was statistically significant.
• Don't believe that an association or effect is absent just because it was not statistically significant.
• Don't believe that your p-value gives the probability that chance alone produced the observed association or effect or the probability that your test hypothesis is true.
• Don't conclude anything about scientific or practical importance based on statistical significance (or lack thereof).

Labels: COVID-19, critical thinking, health, media, science, statistics

# posted by VFPDissident @ 11/18/2020 10:10:00 PM