- Thread starter szm
- Start date
- Tags book regression sas time series

I have yet to find a good book on time series for someone without an advanced math background and I have spent a lot of years looking. I recently ordered the following book, but I have not actually worked with it. It might be useful.

http://support.sas.com/publishing/authors/extras/63980.pdf

I have large number of links to time series material - if you have a specific question I might be able to help.

This is of some valuewith ARIMA (Duke has a wonderful site for forecasting generally this is part of it http://people.duke.edu/~rnau/411home.htm).

http://people.duke.edu/~rnau/411arim.htm

This is for R but has an useful intro to time series.

http://a-little-book-of-r-for-time-series.readthedocs.org/en/latest/

Time series from an engineering perspective

http://www.itl.nist.gov/div898/handbook/pmc/section4/pmc4.htm

I just ran into this, it is supposed to be very useful for time series from a business perspective.

http://home.ubalt.edu/ntsbarsh/Business-stat/stat-data/Forecast.htm

An excellent on line book on forecasting

http://otexts.com/fpp/2/5/

I have not found a good SAS online book. You probably should start with PROC ESM which will generate ARIMA like results without having to do ARIMA (it uses ARIMA algorithms "quasi-Newton and exponential smoothing is essentially a special form of ARIMA in any case). It is as easy as you get for time series.

http://support.sas.com/documentation/cdl/en/etsug/63939/HTML/default/viewer.htm#esm_toc.htm

I am still in the beginning stages of learning to do regression with time series. There are a vast number of ways to do it all of which make different assumptions. My guess is that Proc AutoReg will be the way to go. You can find that through the link I sent for Proc ESM.

Best wishes. It is not an easy journey.

http://support.sas.com/publishing/authors/extras/63980.pdf

I have large number of links to time series material - if you have a specific question I might be able to help.

This is of some valuewith ARIMA (Duke has a wonderful site for forecasting generally this is part of it http://people.duke.edu/~rnau/411home.htm).

http://people.duke.edu/~rnau/411arim.htm

This is for R but has an useful intro to time series.

http://a-little-book-of-r-for-time-series.readthedocs.org/en/latest/

Time series from an engineering perspective

http://www.itl.nist.gov/div898/handbook/pmc/section4/pmc4.htm

I just ran into this, it is supposed to be very useful for time series from a business perspective.

http://home.ubalt.edu/ntsbarsh/Business-stat/stat-data/Forecast.htm

An excellent on line book on forecasting

http://otexts.com/fpp/2/5/

I have not found a good SAS online book. You probably should start with PROC ESM which will generate ARIMA like results without having to do ARIMA (it uses ARIMA algorithms "quasi-Newton and exponential smoothing is essentially a special form of ARIMA in any case). It is as easy as you get for time series.

http://support.sas.com/documentation/cdl/en/etsug/63939/HTML/default/viewer.htm#esm_toc.htm

I am still in the beginning stages of learning to do regression with time series. There are a vast number of ways to do it all of which make different assumptions. My guess is that Proc AutoReg will be the way to go. You can find that through the link I sent for Proc ESM.

Best wishes. It is not an easy journey.

Last edited: