BookmarkSubscribeRSS Feed
DanielQuay
Quartz | Level 8

I'm having a problem running a model using proc surveylogistic.

 

proc surveylogistic data = source order=formatted;

class ACTIV (param=ordinal) TV_HRS(param=ordinal);

model BMIc = ACTIV|TV_HRS ;

format BMIc BMIc. ACTIV ACTIV. TV_HRS TV_HRS.;

weight WTANAL;

strata Stratumcr4;

run;

 

The problem I'm having is that it is not running the Proportional Odds Assumption test.

I've tried running it without the interaction variable and I still don't get this as part of my printout.

Any idea why it's not running this test?  After looking for a reason all day yesterday I'm stumped.

5 REPLIES 5
raghidazamzam
Calcite | Level 5

I have the same problem. Did you figure it out?

DanielQuay
Quartz | Level 8

I believe I fixed it by using the </ solution> option in the model statement.

raghidazamzam
Calcite | Level 5

Thank you for the reply /solution is for surveyreg but it does not work with surveylogistic. 

DanielQuay
Quartz | Level 8

Apologies, you are quite correct.  That was the last problem I had tackled.

Regarding this one, I never did figure it out.  I had to test it outside survey logistic.

I believe I graphed it, and found out that it violated the assumption so I had to change the link= option.

raghidazamzam
Calcite | Level 5

Thank you

Ready to join fellow brilliant minds for the SAS Hackathon?

Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.

Register today!
What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 5 replies
  • 1505 views
  • 0 likes
  • 2 in conversation