topic Re: Different N obs between proc means and proc npar1way in SAS Programming

Different N obs between proc means and proc npar1way

Melk — Fri, 26 Jan 2018 18:19:10 GMT

I am running a 2 sample wilcoxon and also supplementing my p-value with with medians using proc means. However, the number of obs in each are different: proc means reports I have 3 in my class variable whereas npar1way reports I have 2. What can be the reason for this?

proc means data=x median;
   where group = "A";
   class sub;
   var change;
run;

proc npar1way data=x wilcoxon;
   where group = "A";
   class sub;
   var change;
   exact;
run;

Re: Different N obs between proc means and proc npar1way

svh — Fri, 26 Jan 2018 18:56:36 GMT

You can add 'nmiss' to your PROC MEANS statement to try to examine missingness of the continuous variables at the class level.

Or, have you tried running a PROC FREQ to examine the categorical variables and their frequencies. That might help.

Such as

PROC FREQ DATA=X;

TABLES SUB;

TABLES GROUP;

TABLES SUB*GROUP;

RUN;

Re: Different N obs between proc means and proc npar1way

Rick_SAS — Fri, 26 Jan 2018 19:05:25 GMT

In PROC MEANS, "NObs" is the total number of observations in each group. It includes missing and nonmissing. To see the number of observations that are used in the analysis, put N and NMISS on the PROC MEANS statement:

proc means data=x N NMISS median ;
    where group = "A";
    class sub;
    var change;
run;

The "N" column should match the "N" column in NPAR1WAy.