Open amvillegas opened 6 years ago
At the moment the cohort effect of the model follows an arima model that needs to be specified by the user.
It would be good to have the option of having gc.method="iarima" so that one can choose the best model according ot auto.arima
gc.method="iarima"
APC <- apc(link = "logit") wxt_esp <- genWeightMat(ages = c(0:99), years = c(1975:2006), clip = 3, zeroCohorts = 1886) APCfit <- fit(APC, Dxt = Dxt_esp, Ext = Ext_esp, ages = c(0:99), years = c(1975:2014), ages.fit = c(0:99), years.fit = c(1975:2006), wxt = wxt_esp) APCfor <- forecast(APCfit, h= 8, kt.method= "iarima", gc.method="iarima")
At the moment the cohort effect of the model follows an arima model that needs to be specified by the user.
It would be good to have the option of having
gc.method="iarima"
so that one can choose the best model according ot auto.arima