Effects of Pooling Samples on the Performance of Classification Algorithms: A Comparative Study
Figure 5
Performance of classifiers based on the animal scenario (sample size = 180). Performance of classifiers for datasets of individual samples and pool sizes of 2, 3, and 5 are compared when numbers of markers = 10 and sample size = 90 samples per class as performed in human scenario. The height of bars indicates 95% confidence interval from 300 replications.