Hi,
I have a dataset with approximately 1300 observations and I am interested in fitting a series of models using:
proc logistic
proc surveylogistic
proc genmod
Some of the included covariates have missing values and the missing values of the covariates belong to different observations. What I am trying to say is that for a single observations not all covariates included in the model are missing.
When I fit the models I get about 15% of the observations not used.
Is there an option to tell SAS to include the observations in the analysis which have at least one covariate with no missing data for the observation (to use available case analysis)?
Thank you,
Nikos
If the variables you are concerned with are CLASS variables you can use the option MISSING on the class statement to indicate that missing is considered a valid level in Logistic and Genmod. I don't see an equivalent for Surveylogistic though.
I don't believe there is another option if the predictor is not a class variable that might help directly.
Another option might be to impute values for the missing variables.
Thank you and best wishes,
nikos
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.