Hello, I have a logistic regression model with a binary outcome and for two of my categorical variables, I want to estimate contrasts for each pair of the levels (within each variable-one variable has three levels, the other variable has 4 levels). How may I do that without using LSMESTIMATE? Thanks!
Use the LSMEANS command in PROC SURVEYLOGISTIC, with the LINES and LINESTABLE options.
Use the LSMEANS command in PROC SURVEYLOGISTIC, with the LINES and LINESTABLE options.
Thank you @PaigeMiller May you please give me an example or document that I can learn how to do this? Thanks1
You would be helping yourself in the long run by learning to find and use the actual SAS documentation for PROC SURVEYLOGISTIC and look at the LSMEANS commend.
In general, you can do an internet search via typing the following command
proc surveylogistic site:documentation.sas.com
Another helpful link is this one, which shows all SAS PROCs in alphabetical order
Thank you @PaigeMiller . Your suggestion for using LSMEANS worked very well
SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.