Table 2 |
|||||
|
The fraction of simulations (out of 1000, so the 95% confidence limit is approximately ± 0.03) in which the Page statistic (or the one-at-a-time statistic) exceeded its 2.5% false alarm threshold during the simulated outbreak for the baseline model, the baseline model with residuals modified by EWMA, the null model, and the null model with residuals modified by EWMA. |
|||||
|
Outbreak duration |
Test |
Baseline |
Baseline + EWMA |
Null |
Null + EWMA |
|
|
|||||
|
1–10 days |
Page |
0.46 |
0.21 |
0.28 |
0.17 |
|
1–10 days |
One-at-a-time |
0.37 |
0.31 |
0.17 |
0.31 |
|
>1 day |
Page |
0.42 |
0.20 |
0.30 |
0.14 |
|
>1 day |
One-at-a-time |
0.31 |
0.25 |
0.13 |
0.26 |
|
1 day |
Page |
0.44 |
0.36 |
0.30 |
0.45 |
|
1 day |
One-at-a-time |
0.71 |
0.70 |
0.47 |
0.68 |
|
|
|||||
|
Brillman et al. BMC Medical Informatics and Decision Making 2005 5:4 doi:10.1186/1472-6947-5-4 |
|||||