0
$\begingroup$

Recently I crossed a paper, which authors presented their ROC curve results in the following way:

44,7,0,19,18,74,15,8,27,24,2,0,0,0,2,0,0,0,0,0,0,0, 0,0,0,183,42,36,46,59,25,6,2,2,15,330,81,59,86,1 04,14,2,2,2,8,16,4,2,2,8,317,97,67,67,86,287,89,5 9,59,80,359,104,67,86,102,16,4,2,2,8,16,4,2,2,8,1 78,62,31,40,45,336,98,65,84,89,31,23,8,0,0,2,2,0, 0,0,0,0,0,0,0,0,0,3,13,324,0,114,0,0,7,0,0,0,0,0,0, 265,0,0,0,0,0,0,12,0,57,21,0,0,156,121,6,361,0

How can understand the performance over the used dataset? I checked this post and post but still I don't get it how it can be represented instead of scores by above numbers?

$\endgroup$
4
  • $\begingroup$ I'll state the obvious and point out that this is a dump of numbers and not ROC curves. I was going to suggest to get in touch with the authors before I noticed that the email for contact is [email protected]. $\endgroup$
    – dipetkov
    Commented Jul 13, 2022 at 20:24
  • 1
    $\begingroup$ @dipetkov many researchers in China use email addresses in the 163.com domain. They are all numbers, this one looks fairly legit. $\endgroup$
    – Calimo
    Commented Jul 13, 2022 at 20:32
  • $\begingroup$ @Calimo Thanks. Then the author might appreciate to learn that something went wrong with Figure 4 of his paper because this doesn't look like a legit ROC curve. $\endgroup$
    – dipetkov
    Commented Jul 13, 2022 at 20:36
  • 1
    $\begingroup$ Absolutely. And I would also take the rest of the paper with a grain of salt, as something obviously went very wrong in the peer review process... $\endgroup$
    – Calimo
    Commented Jul 14, 2022 at 7:09

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.