Hello Mark, Thank you for your timely reply. All I want to know is if the xreg argument must contain the same amount of historical observations as the dependent variable and if newxreg has to have a forecast of the exogenous variable equal to the number of periods to be forecasted.
Best regards and thanks again, Paul 2014-12-03 22:30 GMT-06:00 Mark Leeds <marklee...@gmail.com>: > hi paul: I don't have time to answer all of your questions but below > should help. > there'sa better one that actually how arima is better for forecasting > than gls > but I can't find it right now. if I find it, I'll send it. > > > http://stats.stackexchange.com/questions/6469/simple-linear-model-with-autocorrelated-errors-in-r > > > On Wed, Dec 3, 2014 at 11:12 PM, Paul Bernal <paulberna...@gmail.com> > wrote: > >> Hello everyone, >> >> I am just trying to understand how the Arimax function works, so my >> questions are: >> >> 1. If I have a univariate time series of sales and sales are dependent >> upon, say inflation rates, then my xreg would be inflation rates right? >> >> 2. Now is I have historial data on sales (from january 2000 to december >> 2010) then my xreg argument would be a historical time series of inflation >> rates on the same time frame? (from january 2000 to december 2010?) >> >> 3. If I want to predit, say 5 years of monthly data (60 periods) using the >> exogenous variable (in this particular case inflation rates) then that >> means I would have to have a a 60 period forecast of inflation rates and >> that would be my newxreg argument? >> >> Any guidance will be greatly appreciated, >> >> Best regards, >> >> Paul >> >> [[alternative HTML version deleted]] >> >> ______________________________________________ >> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see >> 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. >> > > [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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.