Table 2
p values (of unimodality) of Hartigan’s dip tests on MSP samples (with the sample size denoted as Nsample) obtained with various parallax significances, ϖ/σϖ.
| ϖ/σϖ | >3 | >4 | >5 | >6 | >7 |
|---|---|---|---|---|---|
| Nsample | 64 | 53 | 45 | 38 | 30 |
| Hartigan’s dip tests on v1 | |||||
| p value | 0.91 | 0.89 | 0.81 | 0.77 | 0.92 |
| N0.9 | ≈490 | ≈360 | ≈220 | ≈150 | ≈200 |
| N0.95 | ≈610 | ≈450 | ≈270 | ≈180 | ≈250 |
| Hartigan’s dip tests on |v1| | |||||
| p value | 0.64 | 0.57 | 0.43 | 0.42 | 0.33 |
| N0.9 | ≈240 | ≈160 | ≈110 | ≈90 | ≈60 |
| N0.95 | ≈300 | ≈200 | ≈130 | ≈110 | ≈70 |
Notes. N0.9 and N0.95 refers to the total number of measurements (including the Nsample measurements) needed to rule out uni-modality of the v1 (or |v1|) samples at 90% and 95% confidence, respectively, assuming the v1 sample truly follow the multi-modal distribution used in the visualisation (see Section 2).
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.