RM ANOVA (proc glm, proc mixed)

 

DATA wide;
  INPUT sub group dv1 dv2 dv3 dv4;
CARDS;
1 1  3  4  7  3
2 1  6  8 12  9
3 1  7 13 11 11
4 1  0  3  6  6
5 2  5  6 11  7
6 2 10 12 18 15
7 2 10 15 15 14
8 2  5  7 11  9
;
RUN;
 

PROC PRINT DATA=wide ;  RUN; 

PROC GLM DATA=wide;
  CLASS group;
  MODEL dv1-dv4 = group / NOUNI ;
  REPEATED trial 4;  /* level of trial -> DV1-DV4 => 1-4 trial * group
RUN; 
quit;

 

 

DATA long ; SET Wide;

dv = dv1; trial = 1; OUTPUT;

dv = dv2; trial = 2; OUTPUT;

dv = dv3; trial = 3; OUTPUT;

dv = dv4; trial = 4; OUTPUT;

DROP dv1 - dv4 ;

RUN;

 

PROC PRINT DATA=long ; RUN;

 

 

PROC MIXED DATA=long;

CLASS sub group trial;

MODEL dv = group trial group*trial;

REPEATED trial / SUBJECT=sub TYPE=CS;

run;

 

 

 

 

 

참조

https://webpages.uidaho.edu/CALS-StatProg/sas/workshops/mixed/ANOVA.pdf

http://hosting03.snu.ac.kr/~hokim/seminar/repeat.pdf

https://support.sas.com/resources/papers/proceedings/pdfs/sgf2008/374-2008.pdf (random or fixed)

Proc Mixed - Right Options to get Right Output (사용법설명)

https://www.lexjansen.com/nesug/nesug11/sa/sa03.pdf

 

https://www.pharmasug.org/proceedings/2016/PO/PharmaSUG-2016-PO06.pdf

 

PROC MIXED DATA = Indat ;

  CLASS Usubjid Sequence Period Trt ;

  MODEL LCMAX = Sequence Period Trt / SOLUTION DDFM = KR ;

REPEATED TRT / SUBJECT = Usubjid TYPE = UN ;

  ESTIMATE "B VS A" Trt -1 1 0 / CL ALPHA = 0.10 ;

  ESTIMATE "C VS A" Trt -1 0 1 / CL ALPHA = 0.10 ;

  ESTIMATE "C VS B" Trt 0 -1 1 / CL ALPHA = 0.10 ;

  LSMEANS Trt/ CL ALPHA = 0.10 ;

ODS OUTPUT TESTS3 = Tests3 ESTIMATES = Estimates LSMEANS = Lsmeans ;

RUN ;

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

주의점

 

 

PROC MIXED allows missing values. In contrast, PROC GLM with REPEATED statement does not allow missing values, that is, if there is a missing value in one subject, all observations in this subject will be ignored.

 

Mixed model incorporates a random term whereas PROC ANOVA uses only fixed effects.

 

PROC MIXED uses Maximum Likelihood Estimation, while PROC ANOVA uses Least Squares.