Table 2 Comparison of log-likelihood, AIC, BIC, autocorrelation, moving average, and Sigma coefficients of different models for selecting the best-fitted model in forecasting census numbers
From: Time series analysis for forecasting neonatal intensive care unit census and neonatal mortality
Log likelihood | AR (SE) | MA (SE) | Seasonal | Sigma (SE) | AIC | BIC | ||
|---|---|---|---|---|---|---|---|---|
AR (SE) | MA (SE) | |||||||
D2.ln. smooth census number = ARIMA (1,2,1) SARIMA (1,0,1,4) | 69.65 | 0.939 (0.172) | -0.829 (0.229) | 0.116 (0.149) | -0.799 (0.195) | 0.101 (0.006) | -140.49 | -93.54 |
D2.ln.smooth census number = ARIMA(4,2,1)SARIMA(1,0,1,4) | 65.25 | -0.885 (0.142) | 0.999 (0.109) | -0.921 (0.129) | 0.771 (0 0.233 | 0.096 (0.931) | -105.54 | -95.33824 |
D2.ln.smooth census number = ARIMA(1,2,1)SARIMA(4,0,1,4) | 60.19 | 0.908 (0.205) | -0.032 (0.0693) | 0.099 (0.007) | 0.498 (0 0.663) | 0.108 (0.693) | -107.38 | -95.83 |
D2.ln.smooth census number ARIMA(1,2,4) SARIMA(1,0,1,4) | 67.25 | − 0.489 (0.565) | -0.756 (0.289) | -0.917 (0 0.149) | 0.779 (0 0.301) | 0.099 (0.025) | -118.35 | -99.50 |