Skip to main content

Table 4 Comparisons across models

From: Time series modelling to forecast prehospital EMS demand for diabetic emergencies

 

Model

MAE

MSE

MAPE

a)

SARIMA

37.75

1883.29

7.32%

b)

SARIMA + time trend

49.00

2792.45

9.11%

c)

ARIMA + seasonality

38.63

1581.40

7.23%

d)

Exponential smoothing

47.25

2384.75

8.78%

e)

Linear time trend + seasonality

43.22

2964.31

7.57%

  1. MAE (Mean Absolute Error), MSE (Mean Square Error), MAPE (Mean Absolute Percentage Error)
  2. Please note that measures of prediction accuracy across-model comparisons were generated using one-step forecasting