robably everyone has done it: signing Captain Zlog, Perditia McNihilation,
Biff Sproing, Finnegan Zwake, Miss Quoted, or Bucephalus O'McFinkelsteinson on
a sign-up sheet or entering “Not since Thursday” to a question
about their sex. Then there are those surveys claiming that some enormous
percentage of the American people drink bleach to prevent Covid. But how often
does it really happen? Well, Science™ has now investigated this burning
question.
Bleach
We all remember when the news media started claiming that President Trump recommended that people inject bleach to protect against Covid. Well, it turns out that the news media aren't the only ones who make stuff up. People taking surveys do it too.
A recent preprint on MedrXiv [1] says that 87% of all reports of drinking/gargling household cleaner, soapy water, or diluted bleach were made by the same “problematic respondents.” They write:
Problematic respondents can create the illusion that almost anything occurs in the population, no matter how implausible. We also observed that 3% of respondents reported that they have never used the Internet, 5.8% reported having “suffered a fatal heart attack,” and 7% reported “Eating concrete for its high iron content.”
The scientists concluded that a percentage of respondents in a survey will answer “Yes” to almost any question. This poses a big problem for using surveys to detect rare events. They break it down into mischievous, inattentive, and careless respondents.
Once inattentive, mischievous, and careless responses are taken out of the analytic sample, we find no evidence that people intentionally ingest household cleansers for protection against Covid-19 infection. . . . We did not find a single respondent who provided any reasonable or compelling open-ended description of cleanser ingestion.
The researchers reported that those who claimed to drink bleach were the same population who claimed to weigh 1900 pounds, eat concrete for its iron content, and have recently had a fatal heart attack. They were baffled by one respondent who entered their height as “100” without specifying the units: whether they are 100 inches or 100 centimeters, they are far outside the normal range for a human.
Then again, these same people may have said they were dogs, in which case it might make sense.
Conclusions: (1) Survey-takers should always include a few implausible questions to correct for mischievous respondents. Even so, it isn't possible to eliminate them entirely. And (2) No, people are not drinking bleach to protect themselves against COVID.
Just in case some Official Internet Fact Chucker wants to flag this page: No, The Science is clear that drinking bleach is harmful and will not protect you from Wuhan Coronavirus or any other disease. However, we must admit that it could prevent you from dying from it.
1. Litman L, Rosen Z, Rosenzweig C, Weinberger-Litman S, Moss A, Robinson J (2020). Did people really drink bleach to prevent COVID-19? A tale of problematic respondents and a guide for measuring rare events in survey data medRxiv preprint doi: https://doi.org/10.1101/2020.12.11.20246694 December 11, 2020
dec 14 2020, 5:52 am
