topic Re: PROC GLM - class statement in SAS Programming

PROC GLM - class statement

ralphbenno — Thu, 28 Mar 2019 03:16:57 GMT

I want to test rate of "t" between age 4 and 5

proc means data=project mean ;
class sex age ;
var rate ;

where age in (4 5) & sex in ("t" );
run;

"this code shows me the mean for "t" for age 4 and age 5

then I use the ttest then I get error did not run

proc ttest data = Project;
class age & sex ;
var rate age;
where age in (4 5) & sex in ("t");
run;
quit;

run;

help help

Re: PROC GLM - class statement

ralphbenno — Thu, 28 Mar 2019 03:21:01 GMT

sorry the code I used is this

proc means data=project mean ;
class sex age ;
var rate ;

where age in (4 5) & sex in ("t" );
run;
proc ttest data = Project;
class sex age;
var rate ;
where age in (4 5) & sex in ("t");
run;
quit;

the ttest did not work prob with "sex" in class

run;

Re: PROC GLM - class statement

Reeza — Thu, 28 Mar 2019 03:42:05 GMT

Your title says PROC GLM but you're running PROC TTEST. Which type of test are you trying to run?

If you have a single CLASS variable either procedure gives you the same result. PROC GLM can handle multiple CLASS variables, but unfortunately PROC TTEST cannot. If you need two iterations, you'll have to run it twice.

@ralphbenno wrote:

sorry the code I used is this

proc means data=project mean ;
class sex age ;
var rate ;

where age in (4 5) & sex in ("t" );
run;
proc ttest data = Project;
class sex age;
var rate ;
where age in (4 5) & sex in ("t");
run;
quit;

the ttest did not work prob with "sex" in class

run;

Re: PROC GLM - class statement

ralphbenno — Thu, 28 Mar 2019 12:42:02 GMT

sorry for the confusion

I want to do a t test using multiple class for the column and row

do I use

proc glm

class column, row

var data

is it right?

Re: PROC GLM - class statement

PaigeMiller — Thu, 28 Mar 2019 12:58:04 GMT

It would be very helpful if you provided (a portion of) your data via SAS data step code, and not in any other format.

In any event, the general outline of what you want to do is:

proc glm data=whatever;
    class x1 x2;
    model y = x1 x2 /* the interaction is optional */ x1*x2;
run;
quit;