Dear All,
Why is it 1-specificity? Is it a hard and fast rule or there is an explanation behind it?
Thank you
With bets regards,
The ROC curve sensitivity against 1 -specificity as you change the threshold for classification. That allows you to not only assess overall accuracy (the AUC) but also try to select a best threshold/
With a very low threshold, everything will be detected but you'll have no specificity. With a very high threshold, you'll have perfect specificity but never classify anything as positive.
You could plot specificity on the X-axis and just reverse the direction so it goes from 1 to 0 instead of 0 to 1.
It's more intuitive with 1-specificity, which is the rate of false positives among all cases that should be negative (false positive + true negative). As you move along the ROC curve, you get more true positive but also more false positive.
Hi,
I totally agree with Maltenfort.An Extremely informative answer.
Dear Mitchell and Rihab,
Good day to you and thank you for your respective responses- much appreciated.
Thank you.
With best regards,
Arvinder
Great answer by Maltenfort!
I would add that if you actually plot specificity on the X-axis starting from 0 to 1, you will end up with a left facing curve. However, the special meaning of the area under the curve for sensitivity vs (1-specificity) will be lost.
Classification Assessment Methods
This paper introduces a detailed explanation with numerical examples many classification assessment methods or classification measures such as:
Accuracy, sensitivity, specificity, ROC curve, Precision-Recall curve, AUC score and many other metrics. In this paper, many details about the ROC curve, PR curve, and Detection Error Trade-off (DET) curve. Moreover, many details about some measures which are suitable for imbalanced data are explained.
Your comments are highly appreciated.
https://ac.els-cdn.com/S2210832718301546/1-s2.0-S2210832718301546-main.pdf?_tid=20353999-8c84-422a-8191-fd1059469272&acdnat=1536185805_03b19e159f0675a01f35512961973eb5
Presentation of the paper is here
https://www.researchgate.net/publication/327403649_Classification_assessment_methods_a_detailed_tutorial
- Badges
- Science topic
- Similar topics
- Biological Science
- Biochemistry
- Biomolecules
- Nucleic Acids
- RNA
- Small RNA
- microRNA