Table 2.
Multivariate seasonal autoregressive integrated moving average (SARIMA) models of malaria incidence in four administrative areas in Swaziland
| SARIMA modela | Coefficients | SE | AIC | AIC difference |
|---|---|---|---|---|
| Hhohho | ||||
| Malaria only | 9.6 | – | ||
| Malaria + MEI (lag = 2) | −0.067 | 0.049 | 11.67 | 2.07 |
| Malaria + TMAX (lag = 0) | 0.0137 | 0.0152 | 10.97 | 1.37 |
| Malaria + TMIN (lag = 3) | 0.0124 | 0.0089 | 12.58 | 2.98 |
| Malaria + precipitation (lag = 3) | 0.02 | 0.0066 | 5.43 b | −4.17 |
| Lubombo | ||||
| Malaria only | 92.34 | – | ||
| Malaria + MEI (lag = 1) | −0.2039 | 0.05 | 89.46 | −2.88 |
| Malaria + TMAX (lag = 3) | 0.0449 | 0.0775 | 88.88 | −3.46 |
| Malaria + TMIN (lag = 1) | 0.0135 | 0.0092 | 92.22 | −0.12 |
| Malaria + precipitation (lag = 2) | 0.0224 | 0.0007 | 86.59 b | −5.75 |
| Manzini | ||||
| Malaria only | −474.99 b | – | ||
| Malaria + MEI (lag = 3) | 0.0054 | 0.0085 | −471.65 | 3.34 |
| Malaria + TMAX (lag = 3) | 0.7475 | 0.3119 | −471.83 | 3.16 |
| Malaria + TMIN (lag = 2) | 0.0004 | 0.0024 | −471.27 | 3.72 |
| Malaria + precipitation (lag = 1) | 0.0054 | 0.0025 | −471.12 | 3.87 |
| Shiselweni | ||||
| Malaria only | −396.8 b | – | ||
| Malaria + MEI (lag = 7) | 0.0156 | 0.0139 | −375.52 | 21.28 |
| Malaria + TMAX (lag = 4) | 0.009 | 0.004 | −389.54 | 7.26 |
| Malaria + TMIN (lag = 2) | 0.0039 | 0.0023 | −393.72 | 3.08 |
| Malaria + precipitation (lag = 3) | 0.006 | 0.0032 | −390.88 | 5.92 |
aThe lag is selected using a cross-correlation function
bThe model with the lowest AIC value is indicated in italic type