Figure 2 in The maximum likelihood identification method applied to insect morphometric data
Figure 2. Classification based on landmarks (and semilandmarks). Values in percent are the proportions of correct assignments averaged over the complete set of data, mixing the various species, but restricted to the landmark-based method (including here the combination of landmarks and semilandmarks). Each value is shown with an error bar which is its standard deviation. The left part shows the results from the maximum likelihood method applied to the centroid size and to the shape variables. The right part shows the average scores obtained with the Mahalanobis classification. Abbreviation: first PC—the shape variables used were the few first PC of shape variables that the MLi classification selected as the most discriminant set of PC; all PC—the maximum number of PC that could be used by the Mahalanobis classification.
ShareScore
40/100
Overall dataset sharing score
Score breakdown
These five areas show where the dataset supports — or may limit — practical reuse.
- Stewardship
- 8
- Harmonization
- 4
- Access
- 20
- Reuse readiness
- 8
- Engagement
- 0