Table 4.

Percentage reduction in the out-of-sample mean absolute forecast error of the model compared with the baseline forecast

		1 week ahead	2 weeks ahead	3 weeks ahead
Weather covariates included	Ae. aegypti	− 10.0% (p < 0.001)	6.5% (p < 0.001)	10.7% (p < 0.001)
	Ae. albopictus	− 18.5% (p < 0.001)	7.8% (p < 0.001)	10.3% (p < 0.001)
Weather covariates not included	Ae. aegypti	0.3% (p = 0.764)	8.3% (p < 0.001)	10.8% (p < 0.001)
	Ae. albopictus	− 4.9% (p < 0.001)	9.8% (p < 0.001)	11.0% (p < 0.001)

The mean absolute forecast error was derived by averaging the absolute forecast errors across all sites and baseline time points. The p-values were obtained based on a two-sided paired t-test