0
$\begingroup$

Let us say A- we have a binary classifier with labels 1 as healthy and 0 as sick. The precision we got is 100% and the recall is 70%.

Now let us say B-we flip the labels where 0 is healthy and 1 as sick.

Are Precision and recall get flipped in their values if you flip the labels? So in the new case, recall is 100% and precision is 70%?

Or the (70,100) values in the first case belonged to class 1 aka, healthy people and I should calculate the precision and recall for class 0?

My understanding was that we were able to recall 70% of sick people and out of every people who we detected as sick, no person was healthy (precision as 100%). But I am confused now

$\endgroup$
1
$\begingroup$

To begin with, I don't quite get it why you want to flip them. In the binary case, you flip Negatives and Positive, so True Negative becomes True Positive and so do FP/FN. Hence you flip specificity/true negative and sensitivity/recall values, so overall accuracy and F1 stay the same.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.