BookmarkSubscribeRSS Feed
AndreyMyslivets
Obsidian | Level 7

Hello all!

 

Could you please help me with the following question:

I need to create the following table (this is example from CDISC😞

 

 image.png

Following SAS code presented in the document:

 

PROC PHREG DATA=ADTTE;

MODEL AVAL*CNSR (1 2 3) = TRTPN AGEGR1N SEXN
/ ALPHA=0.05;
RUN;

 

I can't find event rate information at the output, could you please help me with it?

Which SAS-code should be used for Event Rate evaluation at day 168 (I higlite it using red color in the table)?

 

Thanks in advance,

Best Regards,

Andrey

3 REPLIES 3
Reeza
Super User
Depending on context you're likely looking for the survival or failure rate at a specific time that you should be able to get from the output. Try an OUTPUT statement and see the output data will have what you want.

https://documentation.sas.com/?docsetId=statug&docsetVersion=14.3&docsetTarget=statug_phreg_syntax18...

However, if you want to account for the other variables you'll likely want a baseline survival given certain conditions. See the example in the docs titled 'Survival Curves' which has an example you can follow.
AndreyMyslivets
Obsidian | Level 7

Thank you, Reeza!

 

Now I realize, that the event rate in the table is the output from PROC LIFETEST with statement "survival" and not from PROC PGREG procedure. 

The line with method = "Cox Regression Model" mislead me, now I see the footnote "Based on the Kaplan-Meier estimates".

 

Andrey

 

Reeza
Super User

KM doesn't account for covariates.

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
  • 3 replies
  • 2222 views
  • 0 likes
  • 2 in conversation