y*****w 发帖数: 1350 | 1 假设下面一个crossover design:
subject, random effect
renal site, fixed effect
drug treatment, fixed effect
SAS linear mixed model is as follows (no interaction effect of site and drug
):
proc mixed data=tmp cl;
class subject site drug;
model diff=site drug / ddfm=kr cl;
random subject;
run;
在crossover design的情况下,作linear mixed model后,如何计算inter-subject
and intra-subject coefficient of variation? 我看到下面这个blog提到intra-
subject coefficient of variation的计算:
http://onbiostatistics.blogspot.com/2014/03/intra-subject-coeff
但是找不到如何算inter-subject coefficient of variation。我看到有人直接用
square root of between-subject variance divided by the overall mean作为inter
-subject coefficient of variation,这个在crossover design的上下文里面对吗?
如果这个对,那么intra-subject coefficient of variation是不是也可以用同样的方
法计算呢?在SAS PROC MIXED output里面,between-subject variance和within-
subject variance是不是就是“Covariance Parameter Estimates”下面的Estimates
,其中“Subject”对应between-subject variance,“Residual”对应within-
subject variance?可是我试着用这个“Residual”值算了一下,和上面的blog里面提
供的公式算出来的不一样。 |
|