Question

我希望在因变量DV上运行线性混合模型，该模型是在三个不同Condition的两个不同Timepoint下收集的。数据结构如下：

   ## dput(head(RawData,5))
    structure(list(Participant = structure(c(2L, 2L, 2L, 2L, 4L), 
  .Label = c("Jessie", "James", "Gus", "Hudson", "Flossy", 
 "Bobby", "Thomas", "Alfie", "Charles", "Will", "Mat", "Paul", "Tim", 
  "John", "Toby", "Blair"), class = "factor"), 
 xVarCondition = c(1, 1, 0, 0, 1), 
 Measure = structure(c(1L, 2L, 3L, 4L, 1L), 
.Label = c("1", "2", "3", "4", "5", "6", "7", "8", 
"9", "10", "11", "12"), class = "factor"), 
Sample = structure(c(1L, 2L, 1L, 2L, 1L), 
.Label = c("1", "2"), class = "factor"), 
 Condition = structure(c(2L, 2L, 1L, 1L, 2L),
 .Label = c("AM", "PM"), class = "factor"),
 Timepoint = structure(c(2L, 2L, 2L, 2L, 1L), 
.Label = c("Baseline", "Mid", "Post"), class = "factor"),
 DV = c(83.6381348645853, 86.9813802115179, 69.2691666620429, 
 71.3949807856125, 87.8931998204771)), 
.Names = c("Participant", "xVarCondition", "Measure", 
   "Sample", "Condition", "Timepoint", "DV"), 
 row.names = c(NA, 5L), class = "data.frame")

每个Participant每Condition次Timepoint执行两次试验，如Measure所示;但是，缺少数据，因此每个参与者不一定有12个级别。列xVarCondition只是一个虚拟变量，它包含条件中AM的每个条目的1。列Sample指的是Condition每个Timepoint的2个试验。

我是R用户，但统计员是SAS用户，他认为该模型的代码应为：

proc mixed data=RawData covtest cl alpha=&alpha;
class Participant Condition Timepoint Measure Sample;
model &dep=Condition Timepoint/s ddfm=sat outp=pred residual noint;
random int xVarCondition xVarCondition*TimePoint*Sample 
          TimePoint/subject=Participant s;

以上SAS代码给出了明智的答案，并且工作正常。我们认为上述模型的结果lme4语法为：

TestModel = lmer(DV ~ Condition + Timepoint + 
              (1 | Participant/Timepoint) +
              (0 + xVarCondition | Participant) +
              (1 | Participant:xVarCondition:Measure), data = RawData)

但是，运行此模型时出现以下错误：

Error: number of levels of each grouping factor must be < number of observations

是否正确指定了随机效果？

Answer 1

我无法从您的说明中说出来，但很可能您的Participant:xVarCondition:Measure术语构建了一个分组变量，在每个分类级别中只有一个以上的观察值，这将使{{1带有剩余误差项的术语冗余，它始终包含在(1|Participant:xVarCondition:Measure)模型中。如果你真的想通过包含

，你可以覆盖错误

lmer

在您的函数调用中，但（如果我已正确诊断出问题），这将导致残差方差和control=lmerControl(check.nobs.vs.nlev = "ignore")方差无法识别。这种不可识别性通常不会导致模型的其他部分出现任何问题，但我对可识别的模型更为满意（这种不可识别性总会导致数值问题）。

有一个类似的例子here。

您可以按如下方式检查我的猜想：

Participant:xVarCondition:Measure

如何在SAS中复制lme4中的随机效应？

1 个答案: