search

aaronpeikert / bayes-prereg

https://aaronpeikert.github.io/bayes-prereg/#2
Creative Commons Zero v1.0 Universal
6 stars 6 forks source link

preregistration is appropriate for any type of empirical study? #43

Open brandmaier opened 2 years ago

brandmaier commented 2 years ago

Preregistration effectively reduces uncertainty about theorethical risk, which increases the persuasiveness of evidence, and hence is appropriate for any type of empirical study. (quoted from my modified branch)

This last sentence in the abstract is very broad and sounds like a free ride ticket. Taken literaly, anybody can just pregister something (whatever it is) and then do something else and it is OK. I am sure that this is not what you mean. So, I think we need some qualifications to this statement "...as long as the preregistration maximizes transparency, comprehensibility, and replicability"? But maybe you have a different view, @aaronpeikert ?

aaronpeikert commented 2 years ago

Good point!

We of course need to qualify under what conditions it "effectively reduces uncertainty".

aaronpeikert commented 2 years ago

That is transparency.