Okay, kinda horrified by the "Nobody can possibly do studies that replicate reliably!" replies. Bigger samples, more diverse subjects... 1/2
-
-
Show this thread
-
...bigger effect sizes, simpler stats, check that others can carry out your methods, notice weirdness instead of chasing p-values. 2/2
Show this thread
End of conversation
New conversation -
-
-
...but also does not help as we fight the rise of obscurantism and superstition. Stop making excuses and check your damn results! (2/2)
-
They can't afford to, if everyone else isn't doing it too. No grant money for large sample sizes. Can't fall behind on CV and impact factor.
End of conversation
New conversation -
-
-
I think you mean "try harder", but realistically one should then get out of science, unless you changed the "publish or perish" system.
-
Publish or perish would change automatically, it's an equilibrium of too many people, too little funding, and too little at stake in quality
- End of conversation
New conversation -
-
-
Most likely just study safer topics less likely to surprise anyone, to the world's loss.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I'm not sure how "Try to escape from China" helps inform my experimental procedures.
-
Maybe ppl replicating your work pretend it is good because they need you to do the same back to them at a later stage?
End of conversation
New conversation -
-
-
Change careers.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Publish fake replications of other scientists' work to save their lives
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Tell wingsuit flyers about this exciting new opportunity. Don't know they'd make good scientists, but that's who you'd get.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Draw no conclusion, present the raw data. I'd be OK with that.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Does China do this? And if not, why is China a necessary part of this hypothetical?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I guess stop doing any work that is based on inductive logic then, which includes all empirical science.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Leave science, get into civil engineering.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
There's an obvious answer: start by getting the fuck out of China
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Drift over time to simpler tests meaning less variables to control for, e.g. Physics vs social science
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.