The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
Shaded area around AUC in PerformanceVector ??
Maven
Hi,
I wonder what the meaning is of the shaded area around the ROC curve of a PerformanceVector ?
I found http://rapid-i.com/rapidforum/index.php/topic,418.0.html, which explained that the +/- after specificity indicates the standard deviation.
So has the shaded area around the ROC also something to do with the standard deviation ?
But why is the width of the shading different for different values of the x-axis (1-specificity) ?
Many thanks,
Axel
I wonder what the meaning is of the shaded area around the ROC curve of a PerformanceVector ?
I found http://rapid-i.com/rapidforum/index.php/topic,418.0.html, which explained that the +/- after specificity indicates the standard deviation.
So has the shaded area around the ROC also something to do with the standard deviation ?
But why is the width of the shading different for different values of the x-axis (1-specificity) ?
Many thanks,
Axel
0
Answers
if you are performing a cross-validation, you have different folds, for example 10, where each fold contains roughly the same number of examples. If you now build the ROC curve for each fold, you have 10 examples at every point. The average value of the examples is marked with the thick red line, while the standard deviation is marked with the shaded area.
It gives you a visual impression of how robust the learner was depending on the different data in the folds.
Greetings,
Sebastian