Skip to main content
Fig. 10 | Journal of Big Data

Fig. 10

From: Cumulative deviation of a subpopulation from the full population

Fig. 10

Eskimo Dog or Husky, with scores being the probabilities; \(n =\) 1300; Kuiper’s statistic is \(0.08082 / \sigma = 6.363\), Kolmogorov’s and Smirnov’s is \(0.06959 / \sigma = 5.478\). As in Fig. 9, none of the reliability diagrams with the same number of subpopulation scores per bin is able to smooth away the irrelevant variations while simultaneously capturing the severe deviation at the highest probabilities (however, the reliability diagram with 10 bins that are equispaced in probabilities captures everything nicely). The scalar summary statistics very successfully detect the statistically highly significant deviation of the subpopulation from the full population

Back to article page