although I'm guilty of this, I've put bars in my papers and line graphs 
-
-
Replying to @o_guest @robustgar
no need for bar guilt or shaming -- unless bars are inappropriate.
3 replies 0 retweets 4 likes -
Replying to @KriegeskorteLab @o_guest
we can't possibly know if bar plot not too bad unless scatterplot is used. Scatterplot = best default
1 reply 0 retweets 0 likes -
-
Replying to @o_guest @KriegeskorteLab
I don’t like violinplots for relatively small samples + people don’t appreciate KDE can go wrong
1 reply 0 retweets 2 likes -
Replying to @robustgar @KriegeskorteLab
Fair. I've used line plots in cases where others would use bar plots altho to be honest SD was essentially nil.
2 replies 0 retweets 0 likes -
I don't know about banning all bar plots though because like I just mentioned there are cases where sampling...
1 reply 0 retweets 0 likes -
is so high that SD is zero, and other cases, where they offer good visual overview. But obviously text of...
3 replies 0 retweets 0 likes -
What do you mean by sampling is so high that SD is zero? Do you mean SE? CI?
1 reply 0 retweets 0 likes -
Replying to @moritzkoerber @LuckyLutz and
if you sample tons SE can asymptotically approach zero.
2 replies 0 retweets 0 likes
or if there's little noise between model SD can be very low etc etc
-
-
Replying to @o_guest @LuckyLutz and
we're talking about a computational model not empirical sampling
0 replies 0 retweets 0 likesThanks. 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.
