Table 4 Short-term forecasting performance in the context of the Ebola outbreak in DRC. For the ongoing Ebola outbreak in DRC, the sub-epidemic model consistently outperformed the other models in short-term forecasts based on all of the performance metrics. Values highlighted in italics correspond to the best performance metric at a given forecasting horizon
From: A novel sub-epidemic modeling framework for short-term forecasting epidemic waves
Model | Mean absolute error (MAE) | Mean squared error (MSE) | Mean interval score (MIS) | Percentage coverage of the 95% prediction interval |
|---|---|---|---|---|
2 weeks ahead | ||||
 Sub-epidemic wave | 9.3 | 131.9 | 67.4 | 86.1 |
 Richards | 11.0 | 205.0 | 172.4 | 63.9 |
 Logistic | 21.3 | 555.2 | 538.5 | 13.9 |
3 weeks ahead | ||||
 Sub-epidemic wave | 10.9 | 194.7 | 104.8 | 79.6 |
 Richards | 12.8 | 277.6 | 217.1 | 59.3 |
 Logistic | 23.8 | 689.0 | 658.4 | 9.26 |
4 weeks ahead | ||||
 Sub-epidemic wave | 12.3 | 258.5 | 153.1 | 75.0 |
 Richards | 14.8 | 368.1 | 275.7 | 51.4 |
 Logistic | 26.0 | 828.9 | 768.9 | 7.0 |
5 weeks ahead | ||||
 Sub-epidemic wave | 14.1 | 337.9 | 207.1 | 68.9 |
 Richards | 17.0 | 473.5 | 338.6 | 43.3 |
 Logistic | 28.1 | 975.4 | 874.3 | 5.6 |