Bug in Error Calculation
Closed this issue · 3 comments
saurabhsharma1993 commented
Hi,
Wanted to point out a bug in your error calculation. The errors for all actions are simply averaged, without regard to the number of data points in each action. It should be a weighted mean. This yields slightly higher numbers.
weigq commented
@ssfootball04
Good point, the weights are usually not taken into account when calculating the errors under protocol #1/2, since the results under these protocols are the average error among actions.
saurabhsharma1993 commented
I don't think that's right, from all the papers I've come across. Can you give a reference ?
weigq commented
I saw you have submitted the same issue on the original repo, so I closed now.