Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Whenever I see a study like this I assume that the researchers won the p<0.05 lottery


If you've tried 20 things, you've probably won that lottery. It's an easy lottery to win.


I think that's more than likely here as "placebo" was literally this peppermint cordial [1].

They say it doesn't have peppermint oil in it... but it does list "flavorings" and I don't know how you make something taste like peppermint without using peppermint (or why you wouldn't).

The other possible explanation is 1 group is basically drinking an extra 200ml of water with a microscopic amount of peppermint oil, and the other group is drinking an extra 200ml of sugar water. The researchers may have literally just stumbled on the fact that more water and less soda has positive health impacts.

[1] https://www.tesco.com/shop/en-GB/products/254854798


Classic xkcd on this topic https://xkcd.com/882/


Very likely. If they really wanted to make the results a bit stronger, they could at least have switched the two groups after 20 days.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: