As the first step in the decommissioning of sasCommunity.org the site has been converted to read-only mode.
Here are some tips for How to share your SAS knowledge with your professional network.
Beware Missing Values of Class Levels in PROC MEANS
Be aware of missing values in class variables when using PROC MEANS. By default any observation with a missing value for one of the class variables is removed from the analysis even if the results for the class variable with a missing value are not requested. For example:
data test; input c1 c2 y; datalines; 0 . 11 0 0 2 0 1 3 1 . 14 1 0 5 1 1 6 ; run; proc means data=test ; class c1 c2; types c1; var y; run;
yields the following result:
Analysis Variable : y N c1 Obs N Mean Std Dev Minimum Maximum 0 2 2 2.5000000 0.7071068 2.0000000 3.0000000 1 2 2 5.5000000 0.7071068 5.0000000 6.0000000
If you expect 3 observations for each level of c1, then either remove c2 from the class statement or add the missing option for the class statement as follows:
proc means data=test ; class c1 c2 / missing; types c1; var y; run;