match_FP_and_FN_counts_to_smaller_of_the_two | R Documentation |
Usually, the number of TNs and TPs will be unbalanced (i.e., there will usually be far more absences (TNs) than presences (TPs). Therefore, there will be far more opportunities to inject FPs than FNs or vice versa. Consequently, even if the FP and FN rates are set to the same value, there are likely to be far more FPs than FNs or vice versa in the apparent matrix. In many ecological cases, this would yield an unreasonable number of False Positives since False Positives are generally much less likely than False Negatives in field studies.
match_FP_and_FN_counts_to_smaller_of_the_two( num_TPs, num_TNs, FP_const_rate, FN_const_rate )
num_TPs |
integer |
num_TNs |
integer |
FP_const_rate |
numeric |
FN_const_rate |
numeric |
So, this routine will adjust the error rate of the dominant value to yield the same _count_ as the other, e.g., if TNs are dominant, then the adjusted_P(FP) = num_FNs / num_TNs
Returns FP_FN_const_rate_pair list
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.