3

auto.arima(ldeaths)

Here is the output I got from R, but I am not sure how to read ARIMA(1,0,0)(2,0,0)[12]. What does it mean? How to put ar1, sar1, and sar2 into a model?

Series: ldeaths 
ARIMA(1,0,0)(2,0,0)[12] with non-zero mean 

Coefficients:
         ar1    sar1    sar2  intercept
      0.4418  0.3098  0.5078  2058.2234
s.e.  0.1345  0.0973  0.0998   175.8665

Ok the data came from R. ldeaths...and I just analyzed it.

lusicat
  • 681
  • 1
  • 10
  • 20
  • 1
    Do you want the model equation? See some related posts like [this one](http://stats.stackexchange.com/questions/69407/how-do-i-write-a-mathematical-equation-for-arima-2-1-0-x-0-2-2-period-12?noredirect=1&lq=1). – Richard Hardy Nov 11 '16 at 09:06
  • I don't have routine access to R so could u please post the data in the requested format. – IrishStat Nov 11 '16 at 14:04
  • I got it! It is a seasonal ARIMA model! I am good. I also asked my PhD neighbour. Problem solved! – lusicat Nov 12 '16 at 02:28

1 Answers1

3

You have an implied loss of $12+12+1 =25$ starting values. This is indeed a very unusual model and sets a red flag for me. Why don't you post your data in a column oriented csv file. All ARIMA model can be expressed as a weighted average of the past which goes a long way (pun) to "explain" the model and it's implications for the future.

Rob Hyndman
  • 51,928
  • 23
  • 126
  • 178
IrishStat
  • 27,906
  • 5
  • 29
  • 55
  • I am motivated to further detail what an ARIMA model is and how it can be interpreted. Objective statistical analysis ( meaning time series analysis in this case ) should be used to determine how to weigh the past for inferential purposes. It is well known that an ARIMA model is a super-set of simple assumed moving averages as it empirically finds the optimal number of weights (N) to use and the optimal values of these weights rather than assuming the number of weights(N) and a set of weights that are uniform (1/N). Allow the data to speak ! . In the OP's model N=145 ... – IrishStat Nov 11 '16 at 13:59