Not clustered: 23. Rory Duncan — only 12 of 21 metrics available (needs ≥ 60%); 26. Marty Hearne — only 12 of 21 metrics available (needs ≥ 60%); 31. Gary Herman — only 12 of 21 metrics available (needs ≥ 60%); 35. James McGinty — only 11 of 21 metrics available (needs ≥ 60%); 37. Peter Garrone — only 11 of 21 metrics available (needs ≥ 60%); 38. Peter Tolhurst — only 10 of 21 metrics available (needs ≥ 60%); 39. Andrew Berenyi — only 11 of 21 metrics available (needs ≥ 60%); 40. James Atkinson — only 5 of 21 metrics available (needs ≥ 60%); 42. Damian Hamilton — only 9 of 21 metrics available (needs ≥ 60%); 43. Wayne Johnston — only 6 of 21 metrics available (needs ≥ 60%); 44. Rennick Kerr — only 12 of 21 metrics available (needs ≥ 60%); 45. Tushar Pokle — only 9 of 21 metrics available (needs ≥ 60%); 46. Andrew Sutton — only 9 of 21 metrics available (needs ≥ 60%).
GlideComp groups the pilots by flying style, and not by score. It transforms the rank of every behavioural metric to a percentile inside the field. It then compares two pilots by the mean percentile gap over the metrics that both pilots have, and never fills in a missing value. Ward-linkage agglomeration forms the groups, and the best mean silhouette selects the number of groups. Each group carries the spread of the GAP ranks of its members, which shows where a style paid and where it did not.
k was searched from 2 to 6. The mean silhouette is 0.15 — a value near 0 means soft group boundaries, and a value near 1 means tight, well-separated groups.