992
Matched EDA prediction rows
Eight provinces · 2023–2025 evaluation
Complexity did not beat persistence
| Method | MAE / episodes |
|---|
| Persistence / last observed week | 45.088 |
| Trailing four-week mean | 46.673 |
| Random Forest + climate | 50.294 |
| Random Forest without climate | 52.763 |
| Previous-year same week | 71.954 |
Lower is better. A four-week-ahead target is one future week's count, not a four-week cumulative total. Training: 2019–2022.
+5.206
Climate forest minus persistence MAE
Uncertainty limits the conclusion
Approximate 95% cluster-bootstrap interval:
−0.474 to +13.349 episodes
5,000 resamples of 24 province-year sequences. The interval crosses zero; it is not an equivalence test or a prediction interval for future patients.
The evaluation years were inspected during development. Provinces and years may be correlated. No operational forecasting advantage has been demonstrated.