I'm far from the first person to say this, but as a field but our intuitions about confirmatory research (what it's for, and what should happen when we do it) are wildly off thanks to the last many decades of published work, and I don't really know how you fix s.t. like that
-
-
Replying to @melissaekline @djnavarro
Yes, I use preregistration to increase confidence of interpretation even when exploratory - the skeptical reader can know that I did not do a infinitely-broad fishing expedition, they see the scope of the project, be it exploratory or confirmatory.
1 reply 0 retweets 2 likes -
If you were unethical, you could do all the fishing expeditions and then just preregister the ones that worked.
2 replies 0 retweets 1 like -
If you were unethical, you could just go ahead and make up your data tho ;)
1 reply 0 retweets 0 likes -
Agree and ALSO, open notebook science is the only complete, or closest to nearly complete, solution to the file-drawer problem. This is not talked about as much as it should be https://en.wikipedia.org/wiki/Open-notebook_science …
0 replies 1 retweet 4 likes -
I use github plus psychopy to do it, making everything public as i go along.
@JeffRouder and others do that too but we need a tool to reconstruct a linear timeline0 replies 0 retweets 1 like -
Replying to @djnavarro @ceptional and
I do this already. Not for manuscripts though, code only. My LaTeX is on a git repo (
@overleaf) but I do not make that public.
1 reply 0 retweets 0 likes
The obvious problems are how do you detect force'ing and filter-branch'ing etc though? That is totally doable and changes history, right?
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.