Table 8.
Anderson-Darling test results, for parallax (ϖ) distribution, between each pair of subclusters [i, j].
Subclusters | N° members | ϖ |
---|---|---|
[i, j] | [ni, nj] | Significance |
[A,B] | [418,33] | – |
[A,C] | [418,7] | < 1% |
[A,D] | [418,9] | < 1% |
[A,E] | [418,14] | – |
[A,F] | [418,7] | – |
[B,C] | [33,7] | < 1% |
[B,D] | [33,9] | < 1% |
[B,E] | [33,14] | – |
[B,F] | [33,7] | – |
[C,D] | [7,9] | – |
[C,E] | [7,14] | < 1% |
[C,F] | [7,7] | 2.5–5% |
[D,E] | [9,14] | < 1% |
[D,F] | [9,7] | 1–2.5% |
[E,F] | [14,7] | – |
Notes. The number of members per subcluster, [ni, nj], is also given to assess the significance.
The cases where the differences are not statistically significant are marked with “–”. The populations are statistically different if the significance level is < 1%. Note that we do not consider the G extend population in this comparison due to its large standard deviations.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.