Zoom Logo

BARUG ROC Day - Shared screen with speaker view
Nina Zumel
33:40
Joseph Egan, I believe
Ljubomir Buturovic
59:28
The one-vs-one AUC is implemented by R package called "HandTill2001"
Ljubomir Buturovic
59:41
https://cran.r-project.org/web/packages/HandTill2001/HandTill2001.pdf
Simone Thair
01:00:23
Thank you Ljubomir!
Michael Lane
01:01:19
That's ok :D I love multiple charts so multiple ROCs is ok for me :D
Michael Lane
01:03:00
Do you have to have a probability for ROC? (Sorry for this a dumb question, but I been trying to figure out the proper way to do ROC when my predictor is ordinal)
rhorton
01:03:32
You don't need probability, but you do need to be able to sort the cases by the score.
Michael Lane
01:04:38
:O ? really? Then why does in always complain about needing a probability when I try SVM or (in the case of my question) ordinal logistic regression.
Michael Lane
01:06:07
\o/ \o/
Mario E. Inchiosa
01:08:15
Thanks Ljubomir for the link to the "HandTill2001" R package for one-vs-one AUC!
Kenneth Tay
01:08:37
could be due to software? it’s theoretically possible to construct ROC as long as you have ordered scores
Michael Lane
01:11:37
logo is still a thing in minecraft
Michael Lane
01:11:53
the computer in Minecraft do logo
Stephen McInerney
01:13:10
The terms Mario mentioned ‘One-vs-Rest and ‘One-vs-One’ are also known as ‘One-Against-All’/’OAA’ and ‘One-Against-One’/’OAO’
Michael Lane
01:13:42
@Kenneth let me watch and try to understand
Michael Lane
01:22:28
Man this awesome.
pavitra chakravarty
01:26:48
`that turtle animation has really made this come alive..i am able to relate to this so much better after having seen that
Kenneth Tay
01:28:00
+1
Michael Chen
01:33:34
+1
Michael Lane
01:42:10
+10
Michael Lane
01:44:40
Interesting do you have the code for some these more advanced ROC curves? :D
Mark Ferrari
01:49:05
You can also think of each orange box as a little ROC plot. The line is diagonal because in that subpopulation we have no information—all the scores are the same.
Joseph Rickert
01:53:25
Brilliant!
Harish Ramadas
01:53:31
+1!!
Kenneth Tay
01:56:41
btw, the wilcoxon interpretation is the basis for the delong test, which is used to test the hypothesis that two AUCs are equal
Michael Lane
01:57:23
OPTIMAL :O
Michael Lane
02:05:53
python is evil! (jokes)
Michael Lane
02:10:49
What is Zella?
Nina Zumel
02:11:00
zeallot
Nina Zumel
02:11:17
package for multiple assignment
Stephen McInerney
02:18:34
@JohnMount: don’t understand why false_negative_value = 0 isn’t good enough?
Don Hejna
02:27:04
Im not seeing the screen
Michael Lane
02:27:24
?-?
Yehudit Hasin
02:27:32
I can see
Jeff
02:27:41
working for me
Reed Davis
02:28:08
Looks fine to me.
Michael Lane
02:28:22
please continue
Reed Davis
02:28:33
No sound from Nina.
Rudy M
02:30:25
Can some explain prevalence?
Rudy M
02:30:48
Prevalence threshold
Kenneth Tay
02:31:07
prevalence is the proportion of the population that is positive