Oh my favourite subject! LanX you could add to the list AstraZeneca's efforts to re-invent statistical testing and when messing things up using un-scientific, super-natural explanations.

Two full doses of the vaccine appeared to be only 62% effective at preventing disease, while a half dose, followed by a full dose, was about 90% effective. That latter analysis was conducted on a small subset of the study participants, only 2,741.

And not counting the age signatures of the groups, I must add.

STEM: perhaps add Economics in there too?

Yes, AstraZeneca was the most recent example I had in mind.

Back in universities I earned money helping teaching math as student assistant.

Biology was a desaster area.

Engineers would try to cheat and BA would try to bargain to get their points.

But Biologist would ask for the right excel sheet to do their stats pushing data around till it fits.

Cheers Rolf
_{(addicted to the Perl Programming Language :)
Wikisyntax for the Monastery}

I am OT here but there is a site for watching scientific publications being retracted (most because of false data): https://www.reactionwatch.com and here you can see one of these falsifications https://pubpeer.com/storage/image-1517672284260.png but there are others more "advanced" using ... photoshop's mirror-image. Basically they get past data="western blots" (it is used to "measure" protein expression by means of visual examination!) and claim is for a new study as long as it shows what they want. For a long time, I used to believe that contradictory biological findings were due to the complexities of living organisms but the other factor of course is falsification of experimental results. And then the pandemic hit...

Procrustes? Surely a Biologist.

Disclaimer: not all biologists are like that: https://forbetterscience.com, just a ~ 5-10%. No affiliation with any websites.

bw, bliako