Hello everyone,
Hope you all are doing great! I have been fitting arima models and
performing forecasts pretty straightforwardly in R.
However, I wanted to add a couple of regressors to the arima model to see if
it could improve the accuracy of the forecasts but have had a hard time
trying to do so.
I used the following R function:
arima(x, order = c(0, 0, 0),
seasonal = list(order = c(0, 0, 0), period = NA),
xreg = NULL, include.mean = TRUE,
transform.pars = TRUE,
fixed = NULL, init = NULL,
method = c("CSS-ML", "ML", "CSS"),
n.cond, optim.method = "BFGS",
optim.control = list(), kappa = 1e6)
Now, I know that you don´t need all the parameters in the function so I
basically fit the model using this sentence:
> var1.fit<-arima(response$cargotonnage, order=c(3,0,0), xreg=explanatory,
> include.mean=FALSE)
> var1.fit
Now the weird thing here is that R was actually able to fit the model,
however, when I wanted to make predictions (see below):
> var1.pred<-predict(var1.fit, n.ahead=12)
R popped the following error:
[b]Error in predict.Arima(var1.fit, n.ahead = 12) :
'xreg' and 'newxreg' have different numbers of columns
>
Which is weird beaucse 1. I made sure that my regressor matrix had the same
amount of rows as my univariate time series and
2. R was able to fit the model I was suggesting.
Has anyone done arima models including external regressors in R? Does anyone
has any idea of what could be happening?
Best regards,
Paul
--
View this message in context:
http://r.789695.n4.nabble.com/Time-Series-with-External-Regressors-in-R-Problems-with-XReg-tp4649500.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
