Skip to main content
Fig. 17 | Journal of Big Data

Fig. 17

From: Cumulative deviation of a subpopulation from the full population

Fig. 17

Monarch (or milkweed) butterfly (Danaus plexippus), with scores being the probabilities; \(n =\) 1300; Kuiper’s statistic is \(0.01144 / \sigma = 2.857\), Kolmogorov’s and Smirnov’s is \(0.009057 / \sigma = 2.261\). Much like in Fig. 16, the deviation of the subpopulation below the full population that occurs for probabilities less than 0.1 is apparent only in the cumulative plot or in the very noisy reliability diagrams whose bins are roughly equispaced along the probabilities. The scalar summary statistics again detect somewhat significant deviation, though not as much as if the Kolmogorov-Smirnov and Kuiper metrics could better account for the steep drop that happens in the plot of cumulative differences

Back to article page