| Outlier y |
n = 5 | n = 10 | n = 15 | |||
|---|---|---|---|---|---|---|
| F | T | F | T | F | T | |
| 0.010 | 0.80 | 0.63 | 0.90 | 0.79 | 0.93 | 0.86 |
| 0.025 | 0.81 | 0.68 | 0.90 | 0.83 | 0.94 | 0.88 |
| 0.050 | 0.81 | 0.73 | 0.91 | 0.85 | 0.94 | 0.90 |
| 0.100 | 0.82 | 0.77 | 0.91 | 0.88 | 0.94 | 0.92 |
| 10 | 2.80 | 2.87 | 1.90 | 2.06 | 1.60 | 1.74 |
| 20 | 4.80 | 4.70 | 2.90 | 3.26 | 2.27 | 2.67 |
| 50 | 10.8 | 9.05 | 5.90 | 6.38 | 4.27 | 5.25 |
| 80 | 16.8 | 12.49 | 8.90 | 8.92 | 6.27 | 7.47 |
| 90 | 18.8 | 13.52 | 9.90 | 9.68 | 6.93 | 8.14 |
| 100 | 20.8 | 14.51 | 10.9 | 10.41 | 7.60 | 8.79 |
Note: Bold indicates the points at which y becomes large enough, relative to n, to render the Trnqvist index better than the Fisher for approximating the mean = 1 in the presence of a high outlier.