Using autoregressive integrated moving average (ARIMA) models to predict and monitor the number of beds occupied during a SARS outbreak in a tertiary hospital in Singapore

Table 1 Parameters for the final ARIMA model

Variable	Coefficient	95 % CI	p-value
Constant	17.03	6.43, 27.62	0.002
Previous day's total admissions	-0.37	-0.63, -0.11	0.006
Previous day's probable case admissions	1.17	0.37, 1.97	0.004
ARMA Parameters
AR (1)	1.02	0.98, 1.06	<0.001
MA (1)	-1.34	-2.94, 0.27	0.102
MA (2)	-0.96	-1.80, -0.12	0.026
MA (3)	-0.95	-1.52, -0.38	0.001
Sigma	4.47	1.40, 7.53	0.004

ISSN: 1472-6963