A quick story about replication: When I was working on my PhD, I decided to do some modelling of affective priming data. I chose a (1/13)
examples to that where utterly bad experiments can still be explained because one sees what went wrong. Maybe I've misunderstood you tho?
-
-
I agree if "one sees what went wrong" can include "what went wrong is there's no prior reason to have expected that manipulation to work"
-
The (stupid) example I keep thinking of is trying to turn on the lights by cracking eggs into a bowl
-
I'm having trouble with your specific point. It's quite late so I'm probably very out of it, my fault! I'll try and sleep and reread soon.

-
Actually, as soon as typed I don't get, I got it. And yes, I agree. Obviously trying random stuff that goes against priors can be rejected
-
before even running the experiment. You'd hope nobody published a paper on the null results from the eggs & the light switches experiment.
-
Not all null results are valuable.

-
Is there a PPNull in some near future of ours?
-
What's a ppnull? Google says it's a type of mouse.

- 1 more reply
New conversation -
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.

