The changing relationship between Cholera and interannual climate variables in Kolkata over the past century

Table 1 - Results of SARIMA analysis

Time Interval	Regressor	Model Description	AIC (%change from Null)
Historical	Null	ARIMA(1,0,0)(1,1,0) [11]	962.26
	ONI (lag = 2)	ARIMA(1,0,2)(0,0,1) [11]	834.79 (-13.2%)
	DMI (lag = 8)	ARIMA(1,1,1)(0,0,1) [11]	959.79 (-0.25%)
Recent	Null	ARIMA(1,0,0)(0,1,1) [11]	637.24
	ONI (lag = 12*)	ARIMA(1,0,0)(0,1,1) [11]	639.08 (+ 0.29%)
	DMI (lag = 4*)	ARIMA(1,0,0)(0,1,1) [11]	637.93 (+ 0.1%)

*Indicates not statistically significant at CCF. Null refers to the univariate cholera model. Model description describes the selected SARIMA model parameters in the form ARIMA (p,d,q) (P,D,Q) [m]. Where p refers to the order of the autoregressive terms, d the degree of differencing and q the order of the moving-average model. P,D, and Q describe the equivalent terms for the seasonal part of the model. m refers to the number of time steps in a single seasonal period

ISSN: 1757-4749