Research Article
Comparative Performance of Four Single Extreme Outlier Discordancy Tests from Monte Carlo Simulations
Table 1
Sample simulation and test outcome (modified after Hayes and Kinsella [
7]).
|
Discordancy test result | Contaminant ( replications) | Present ( 0, 0, > 1, or −1) | Absent ( = 0 or = 1) | Contaminant not used in a discordancy test ( type event) | Contaminant used in a discordancy test ( type event) |
| Not significant (TN ≤ CV99) | Spurious type II error probability () (Figure 3) | Nonspurious type II error probability () (Figures 5 and 7) | True negative probability () (Figures 3, 5, and 7) |
| Significant (TN > CV99) | Spurious power probability () (Figure 4) | Nonspurious power probability () (Figures 6 and 8) | Type I error probability () (Figures 4, 6, and 8) |
|
|
TN: calculated test statistic for a sample (TN2, TN8, TN14, or TN15); CV99: critical value for a given discordancy test at 99% confidence level.
|