Skip to main content

Table 1 Accuracy of the statistical models without covariates at various forecast horizons

From: Assessing dengue forecasting methods: a comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil

Week

AR(1)

MA(1)

ARIMA

ETS

MAE

MAPE (%)

RMSE

MAE

MAPE (%)

RMSE

MAE

MAPE (%)

RMSE

MAE

MAPE (%)

RMSE

1

83.28

19.93

127.03

82.72

19.49

124.61

78.26

18.25

124.33

78.66

19.17

126.71

2

114.99

26.59

176.96

114.62

26.03

175.04

114.61

25.05

179.33

118.36

26.52

185.13

3

139.51

33.02

211.01

144.65

32.90

216.32

143.84

31.39

221.81

146.24

36.07

223.62

4

178.87

39.48

269.14

182.26

39.85

274.49

175.38

36.07

277.48

186.66

44.12

292.18

8

314.44

62.00

457.62

323.80

62.68

465.38

308.92

56.32

461.73

392.21

89.16

578.60

12

432.34

81.05

608.53

436.55

81.86

612.83

396.91

64.95

583.04

649.15

150.31

917.47

  1. Bold indicates the method with the best performance for each of the measures