the following code implements the analyses suggested at the lower right corner of page 10 (i.e., page 312) of this paper for genetic predictors. 
PROC
MIXED DATA
= dataset_name;
  class
subjid  SEX  visit;
  MODEL
change = baseline SEX genotype VISIT genotype *VISIT /DDFM
= KR S;
  REPEATED
VISIT /SUBJECT = SUBJID TYPE
= UN;
  contrast ‘effect of one
additional good genotype at the 5th visit after baseline’ genotype 1
genotype*visit 0 0 0 0 1;
run;
PROC
MIXED DATA
= dataset_name;
  class
subjid SEX visit genotype;
  MODEL
change = baseline SEX genotype VISIT genotype *VISIT /DDFM
= KR S;
  REPEATED
VISIT /SUBJECT = SUBJID TYPE
= UN;
  lsmeans
genotype*visit /alpha = 0.05
CL pdiff slice
= visit;
run;
 
No comments:
Post a Comment