Table 2. Comparison of province-level prediction accuracy between full-data and real-time predictions, by prediction horizon.

These calculations assume that both the full-data and real-time multi-step predictions began at the same time. The table shows the 5th percentile (Q₅), 25th percentile (Q₂₅), median (Q₅₀), 75th percentile (Q₇₅), and 95th percentile (Q₉₅) value of the relative MAE from each province at the given horizon. The relative MAEs were calculated as the MAE from the real-time predictions divided by the MAE from the full-data predictions, i.e. values larger than 1 indicate that the real-time models showed more absolute error on average than the full-data models.

horizon	Relative MAE (real-time vs. baseline scores)
	Q 5	Q 25	Q50 (median)	Q 75	Q 95
1	0.78	0.90	1.00	1.06	1.20
2	0.74	0.87	0.95	1.02	1.17
3	0.77	0.90	0.97	1.03	1.11
4	0.82	0.95	1.02	1.08	1.19
5	0.83	0.96	1.04	1.13	1.29
6	0.87	1.02	1.08	1.21	1.45
7	0.88	1.01	1.13	1.28	1.71
8	0.88	1.00	1.15	1.35	1.97
9	0.90	1.01	1.16	1.38	2.22
10	0.88	1.01	1.19	1.42	2.45