Hi all,
I have fitted an ARIMA model (1,1,1) to yearly disease incidence data (years 1973-2005). when i graph the observed and predicted values, the predicted values look like they would fit the data much better if they were shifted back one year (the predictions start at 1974 because of the 1st differencing). this makes sense to me since the "predict y, y" command gives me the back-differenced values. The problem is that STATA still assigns these values to year 1974 instead of year 1973. am i not writing this command correctly or once the predicted values are estimated, do you have to manually go in and shift all predicted values back one year (or however many years I have differenced the series)?
thanks,
joe
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
