"lmer 输出的方差分量的标准误差"

Question

I need to extract the standard error<\/code> of variance component from the output of lmer<\/code> .

library(lme4)
model <- lmer(Reaction ~ Days + (1|Subject), sleepstudy)

Answer 1

I think you are looking for the Wald standard error of the variance estimates. Please note that these (as often pointed out by Doug Bates) the Wald standard errors are often very poor<\/strong> estimates of the uncertainty of variances, because the likelihood profiles are often far from quadratic on the variance scale ... I'm assuming you know what you're doing and have some good use for these numbers ...

library(lme4)
library(merDeriv)
m1 <- lmer(Reaction ~ Days + (Days|Subject), sleepstudy)
sqrt(diag(vcov(m1, full = TRUE)))
vv <- vcov(m1, full = TRUE)
colnames(vv)
## [1] "(Intercept)"                  "Days"                        
## [3] "cov_Subject.(Intercept)"      "cov_Subject.Days.(Intercept)"
## [5] "cov_Subject.Days"             "residual"

Answer 2

I'm not really sure what you mean by "standard error of variance component". My best guess (based on your code) is that you want the standard error of the random effect. You can get this using package arm:

library(arm)
se.ranef(model)
#$Subject
#    (Intercept)
#308    9.475668
#309    9.475668
#310    9.475668
#330    9.475668
#331    9.475668
#332    9.475668
#333    9.475668
#334    9.475668
#335    9.475668
#337    9.475668
#349    9.475668
#350    9.475668
#351    9.475668
#352    9.475668
#369    9.475668
#370    9.475668
#371    9.475668
#372    9.475668

Answer 3

mn2=lmer(pun~ pre + (pre|pro), REML = TRUE, data = pro)
summary(mn2)
coe2=coef(mn2)
coe2

# Matriz de varianza-covarianza (covarianza)
as.data.frame(VarCorr(mn2))

# Extraer coeficientes fijos
fixef(mn2)

# Extraer desvios de a - alfa y b - beta
re=as.data.frame(ranef(mn2))