BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
KekeK
Fluorite | Level 6

When running logistic regression with Enterprise Guide 5.1, how can I change the reference category within a parameter against which odds ratio estimates are presented? E.g. in below I would like to see how smoking occasionally (1) or daily (2) increases the odds of the health outcome as compared to smoking never (0) instead of comparisons 0 vs 2 and 1 vs 2. Odds Ratio Estimates Effect Point Estimate 95% Wald Confidence Limits Smoking 0 vs 2 0.878 0.189 4.075 Smoking 1 vs 2 0.291 0.040 2.123 Thanks!

1 ACCEPTED SOLUTION

Accepted Solutions
SteveDenham
Jade | Level 19

When building your model, save your code.  In proc logistic, change (PARAM=EFFECT) to (PARAM=REF REF='0').  Then re-run with this change.  That should give you what you are looking for.

Steve Denham

View solution in original post

6 REPLIES 6
SteveDenham
Jade | Level 19

When building your model, save your code.  In proc logistic, change (PARAM=EFFECT) to (PARAM=REF REF='0').  Then re-run with this change.  That should give you what you are looking for.

Steve Denham

ChrisHemedinger
Community Manager

You *might* be able to achieve it without hand-coding.  If your "dependent" var has 3 levels, then you can select "Ordered" or "Unordered" from the Model Response page, and then select the "Reference level" value.  I'm not sure if this gets you the content you're looking for, but maybe it will help.

logistic.png

Chris

SAS For Dummies 3rd Edition! Check out the new edition, covering SAS 9.4, SAS Viya, and all of the modern ways to use SAS!
Reeza
Super User

I think the OP is looking to change an independent variable not a dependent variable.

The model suggested would be a way of specifying a multinomial logistic regression instead of a logistic regression, from what I understand, though I'd have to check the code.

KekeK
Fluorite | Level 6

Thanks, I did not know how to do this either so useful to know for the future but in here I wanted to change independent variable as pointed out by Reeza.

KekeK
Fluorite | Level 6

Thank you! I was hoping this could be done without editing the codes, kind of odd that it cannot and hopefully something that will be fixed in future versions. A bit slower this way but otherwise works well.

Reeza
Super User

In general, if you're doing logistic or survival analysis, I found you very quickly need to step out of the EG GUI. 

hackathon24-white-horiz.png

The 2025 SAS Hackathon has begun!

It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.

Latest Updates

Creating Custom Steps in SAS Studio

Check out this tutorial series to learn how to build your own steps in SAS Studio.

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
  • 6 replies
  • 6290 views
  • 7 likes
  • 4 in conversation