MIDAS problem

[James071375]

Dear all, 

I need to conduct regressions with high frequency data as dependent variable and low frequency data as independent and control variables. The literature states that MIDAS (mixed data sampling) regression models can help to deal with the problem. Does SAS provide such procedure or program to complete the requirement? After implementing preliminary Google search, I couldn't find any useful information. If you have any idea, please let me know. Thank you for your advice in advance. 

[JosvanderVelden]

Have you seen this paper? https://unsworks.unsw.edu.au/fapi/datastream/unsworks:47589/binf1f90643-b526-407d-bbe9-659ad94259a9?...
Doc on NLPNRA call:
https://documentation.sas.com/doc/en/pgmsascdc/v_022/imlug/imlug_langref_sect294.htm

[James071375]

Thank you for your recommendation. 

Differing from the paper, my dependent variable has higher frequency (i.e., monthly data) and the main independent variable is monthly as well. However, control variables have lower frequency (i.e., quarterly or yearly data). In other words, it's a reverse MIDAS model. Does SAS offer any procedure or program to deal with the situation? Thanks. Look forward to hearing you.