BookmarkSubscribeRSS Feed
Frances
Calcite | Level 5
Hello,

I've spent several hours searching for SAS code that will
calculate Bozdogan's Information Complexity Criterion (ICOMP) with no
luck. Am looking to compare several mulitple linear regression models.
Does anyone have such a beast they would be willing to share?

Thanks,
Frances
2 REPLIES 2
Cynthia_sas
SAS Super FREQ
Hi:
If you go to support.sas.com and look for the search box in the upper right hand corner, you can search for a term. For example, if you type
Bozdogan
into the search box, there are 40 hits on support.sas.com.

And if you type
compare linear regression models Bozdogan
into the search box, there are 13 hits.

Perhaps you will find what you need by searching support.sas.com or if you have already researched these references and not found what you wanted, you might consider contacting Tech Support for more help.

cynthia
Frances
Calcite | Level 5
Thank you Cynthia. I had searched sas.com using "ICOMP" and "Bozdogans" and came up with zero hits. I just needed the right magic words.

Unfortunately, all the search returns are referring to Bozdogan's CAIC value (called "Consistent Akaike's Information Criterion", or "Corrected Akaike's Information Criterion" at various places in the SAS manuals). The CAIC comes from a paper by Bozdogan in 1987. I think Bozdogan first introduced the Information Complexity (ICOMP) criterion in 1988, which he has since refined.

Regards,
Frances

SAS Innovate 2025: Save the Date

 SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!

Save the date!

What is Bayesian Analysis?

Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.

Find more tutorials on the SAS Users YouTube channel.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 2 replies
  • 919 views
  • 0 likes
  • 2 in conversation