BookmarkSubscribeRSS Feed
Rucstat_huadli
Fluorite | Level 6
In a logistic model, the explanatory variable treatment has four levels.I want to test the first versus the fourth level of treatment, we usually use this contrast statement below

contrast '1 vs 4' treatment 1 0 0 -1;

but,I read the SAS help about The LOGISTIC Procedure contrast statement,they use

contrast '1 vs 4' treatment 2 1 1;

Both have different results,Why?
2 REPLIES 2
Olivier
Pyrite | Level 9
I guess it depends on the way your variables are coded : check the PARAM option in the CLASS statement.
If you typed CLASS treatment / PARAM = GLM ; then your coefficients 1 0 0 -1 are correct. If you simply used CLASS treatement ; without options, or with PARAM=EFFECT, then the coefficients would be 2 1 1 as the help says.

Both lead to the same results :
[pre]
ODS SELECT contrastTest (PERSIST) ;
PROC LOGISTIC DATA = sashelp.class ;
WHERE age IN (12,13,14,15) ;
CLASS age ;
MODEL sex = age ;
CONTRAST "test 12 vs 15" age 2 1 1 ;
RUN ;
PROC LOGISTIC DATA = sashelp.class ;
WHERE age IN (12,13,14,15) ;
CLASS age / PARAM = GLM ;
MODEL sex = age ;
CONTRAST "test 12 vs 15" age 1 0 0 -1 ;
RUN ;
ODS SELECT ALL ;
[/pre]

sas-innovate-2024.png

Don't miss out on SAS Innovate - Register now for the FREE Livestream!

Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.

 

Register now!

New Learning Events in April

 

Join us for two new fee-based courses: Administrative Healthcare Data and SAS via Live Web Monday-Thursday, April 24-27 from 1:00 to 4:30 PM ET each day. And Administrative Healthcare Data and SAS: Hands-On Programming Workshop via Live Web on Friday, April 28 from 9:00 AM to 5:00 PM ET.

LEARN MORE

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