I've been told this too, when pressed there was no persuasive reasoning behind ithttps://twitter.com/pdakean/status/835608567549988869 …
-
-
Replying to @hardsci
The one field I do trust is psychophysics. Measurements usually at kilotrial level.
1 reply 0 retweets 5 likes -
Replying to @EJWagenmakers @hardsci
ah, but v small Ns, often expert Ss, so generalisability can be an issue
2 replies 0 retweets 2 likes -
psychophys used to do stats *per S*. When *each* S needs p<.05 ability to generalise is good.
1 reply 0 retweets 1 like -
but increasingly seeing small N and then standard group-level stats which does seem bad combo
1 reply 0 retweets 2 likes -
FWIW I'm aware some people in dev sci do meta analyses http://bootphon.blogspot.co.uk/2016/01/getting-handle-on-variation-in-infant.html?m=1 …
1 reply 0 retweets 0 likes
I've also witnessed some pretty bad/questionable research practices in quite a few dev sci labs
1:56 PM - 2 Mar 2017
0 replies
0 retweets
0 likes
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.