Skip to main content
Fig. 5 | BMC Bioinformatics

Fig. 5

From: Improving network inference algorithms using resampling methods

Fig. 5

Bootstrapped Pearson correlation. Performance of Pearson and bootstrapped Pearson assessed on the full set of E. coli conditions (left) and on a realistically sized subset (right), both in terms of AUPR. In the right panel, bands indicate a 99% confidence interval constructed from the samples taken at each data fraction. The only significant difference (in the right panel, significance could not be assessed in the left due to sample size of 1) was for 5% subsampling fraction (p-value: 3.1E-3)

Back to article page