Is there a way to create a 3-way table in PROC FREQ where the 3 variables are all in one table? I know this can be done in PROC TABULATE.
In PROC FREQ, when I cross the 3 variables (e.g., tables var1*var2*var3), I get bivariate analyses for var2 and var3 for each level of var1 in a separate table.
In proc freq the option LIST will place all of the variable on one row with the count and percent similar to a one-way table:
Tables var1*var2*var3*var4 / list ;
IF you might have missing values for any of the variables you likely will want to add the MISSING option as well, otherwise combinations of variables that include missing values will not be shown.
Register Today!
Join us for SAS Innovate 2025, our biggest and most exciting global event of the year, in Orlando, FL, from May 6-9.
Early bird rate extended! Save $200 when you sign up by March 31.