Originally, the story was “Only reports of success are reported in the paper, not reports of failure, so there is a bias toward assuming success.

I’ve seen all sorts of things related to this concept./mitoujr/nishio.icon

  • It is easy to talk about in-house products, but difficult to talk about outsourced development.
  • Only successful people’s tweets get buzzed and communicated to a wide audience.
    • @nishio: even if the success rate is 0.1%, if 1000 people try it, maybe 1 person will say “I tried this and it worked in one shot!” and it gets a lot of buzz. I tried it 10 times and all succeeded! and then the success rate will finally reach 50%.

  • The vindictiveness of “I got a PhD but can’t find a job” is easily tweeted, but “I got a job easily, didn’t I?” However, people who think, “I got a job easily, didn’t I?

from /mitoujr/publication-bias.

publication bias


This page is auto-translated from /nishio/パブリケーションバイアス using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.