At high prior probability (set as 0.1) all statistically significant findings demonstrated a low probability for false positive results.
Experiment 8 was compared with all other 13 experiments and the total number of identified probe sets as well as true and false positives was counted.
In real applications, if the threshold is set as ε 3, the false alarm probability is 0.01, and the existing target in a single pulse can be detected if its power is comparable to the clutter-and-noise power.
A general P-value cut-off of p < 0.1 was set as a reasonable compromise between false-positives and false-negatives.
For protein identification, all criteria were set as follows: the comparison of the false discovery rate is 1%.
However, when the prediction probability was set as more than 0.99995 to reduce false positive, they were filtered out with a result of no overlap between homology search and SVM-model candidates.
GC content normalization was enabled for all of the analyses, along with the noisyData option set as TRUE in order to avoid false-positive predictions due to non-uniform capture in exome sequencing data.
Two metrics are computed—"Sensitivity" (Sn) is defined as common items divided by total items in truth set; "Purity" (Pu) is defined as common items divided by total items in the test set as can be used to infer false-positive discovery.
