Creation date: 05/12/98
Authored by: Rich Herrington
How do I perform simple main effects analysis using SAS or SPSS?
Answer:
In SAS release 6.11 or higher:
PROC GLM ;
CLASS A B ;
MODEL Y = A B A*B ;
LSMEANS A*B / SLICE=B ;
Additional
Example:
/*An example of a
three-way ANOVA using the slice option to get simple effects. The
following */
/*data set is
simulated using the random number generator function, RANNOR. */
data a; do a= 1 to 3; do b= 1 to 2; do c = 1 to 2; do rep=1 to 20; int=rannor(123); y=int+(3*a)+(6*b)+(1.5*c)+(4.2*a*b)+(3.1*a*c)+(1.8*b*c)+(4.01*a*b*c)+ rannor(456); output; end; end; end; end; proc print; run; proc glm data=a; class a b c; model y= a|b|c ; lsmeans a*b /slice=b; /*A within the levels of B*/ lsmeans a*c /slice=c; /*A within the levels of C*/ lsmeans a*b*c/slice=b*c pdiff; /* A within the levels of B*C*/ lsmeans a*b*c/slice=c pdiff; /* A*B within the levels of C*/ run;
In SPSS, you can use the MANOVA procedure:
MANOVA Y BY A(1,2) B(1,2)
/DESIGN = A WITHIN B(1) A WITHIN B(2).
See also:
How to Test Contrasts in Repeated Measures
Designs
How to Test Contrasts in Simple Mixed Models (One Within Subjects and One Between Subjects Effect) (Under Construction)
Last updated: 01/18/06 by Craig Henderson