ARIMA (p,d,q) in laymen's terms

[podarum]

I need to investigate how to build an ARIMA model, but can anyone describe for me the meaning of (p,d,q) in layman's terms... when and how to use them, and the difference between different scenarios?  Thanks

[udo_sas · Accepted solution]

AR: p = order of the autoregressive part

I: d = degree of first differencing involved

MA: q = order of the moving average part

I guess this is not the answer you were hoping for - the good news is that there is a vast amount of literature out there providing more detailed and also applied answers to your question.

My personal favourites include:

• Forecasting: Methods and Applications - Makridakis, Wheelwright, and Hyndman
• Time-Series Forecasting: Chatfield
• Forecasting and Time Series: An Applied Approach - Bowerman and O'Connell

This list is by no means complete and other subscribers of this discussion forum will have their own preferences for sure.

For a more SAS specific forecasting book, with lots of examples, I can highly recommend: https://support.sas.com/pubscat/bookdetails.jsp?catid=1&pc=57275 by Brocklebank and Dickey.

Furthermore you might want to consult the ever-growing amount of public statistical forecasting web pages, for example: http://home.ubalt.edu/ntsbarsh/stat-data/forecast.htm

Hyndman and Athanasopoulos are also working on a new online text­book on forecasting: http://robjhyndman.com/fpp/ - however, the chapter on ARIMA is still missing.

Again, this list is by no means complete and others might want to chime in as well.

And of course, there is always the option to attend training classes offered by SAS education, which I can also highly recommend: http://support.sas.com/training/us/paths/for.html

Thanks,

Udo