Hi All,
I'm fitting an arima with xreg:
arima(temp_ts, order = c(1,1,1), seasonal = list(order = c(0,1,0), period = 12),
xreg = temp_xreg, method="CSS")
and it reported error:
Error in optim(init[mask], armaCSS, method = optim.method, hessian = TRUE, :
non-finite value supplied by optim
I tried adding :
arima(temp_ts, order = c(1,1,1), seasonal = list(order = c(0,1,0), period = 12),
xreg = temp_xreg, method="CSS", optim.method = "L-BFGS-B"))
and
arima(temp_ts, order = c(1,1,1), seasonal = list(order = c(0,1,0), period = 12),
xreg = temp_xreg, method="CSS", optim.method = "Nelder-Mead"))
But nothing works. always the same error!
I even tried to add a
"hessian = FALSE"
But it returned the same error with an extra warning:
unused argument (hessian = FALSE)
Help!
I think this problem related to nonstationarity, did you try
auto.arima function?
You set order = c(p, d, q) = c(1,1,1). Since d =1, the model uses the differenced series assuming your original series is most probably I(1). I think the problem is originating from your xreg = temp_xreg argument. There is high possibility that the regressors are collinear. Hence, the design matrix does not seem to be full rank matrix. Does xreg include several exogenous variables? Is xreg a set of dummies? Could you share what is in the temp_xreg object?
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R