Here's my data: https://pastebin.com/ZgWHcrTi
I booted up R today and suddenly I can't get p-values from my regression models. lme4 version 1.1.26
I can still get them with sjPlot::tab_model(data$dv1, p.val = "kr")
library(lme4)
summary(lmer(dv1 ~ group + (1|id),
data=data,
REML=T))
Linear mixed model fit by REML ['lmerMod']
Formula: dv1 ~ group + (1 | id)
Data: regression.data
REML criterion at convergence: 637.4
Scaled residuals:
Min 1Q Median 3Q Max
-3.3455 -0.5839 0.0699 0.6999 2.0728
Random effects:
Groups Name Variance Std.Dev.
id (Intercept) 2.189 1.479
Residual 62.981 7.936
Number of obs: 92, groups: id, 3
Fixed effects:
Estimate Std. Error t value
(Intercept) -7.749 1.412 -5.488
group1 -13.872 1.661 -8.351
Correlation of Fixed Effects:
(Intr)
group1 -0.537
Not printing p-values has been a "feature" of lme4
forever (see here and here ). I strongly suspect that you had the lmerTest
package loaded before (which wraps the lme4
functions and gives identical output except for including a p-value column) and that you have failed/forgotten to load it in your current session...
library(lme4)
coef(summary(m1 <- lmer(Reaction~Days + (Days|Subject), sleepstudy)))
## Estimate Std. Error t value
## (Intercept) 251.40510 6.824597 36.838090
## Days 10.46729 1.545790 6.771481
library(lmerTest)
coef(summary(m2 <- lmer(Reaction~Days + (Days|Subject), sleepstudy)))
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 251.40510 6.824597 16.99973 36.838090 1.171558e-17
## Days 10.46729 1.545790 16.99998 6.771481 3.263824e-06
If you've already fitted a model with lme4::lmer()
you can get the p-values by loading lmerTest
and converting the type: coef(summary(as(m1,"merModLmerTest")))
You may want to be careful with your specifications: the default denominator-df in lmerTest
is Satterthwaite, whereas your tab_model
is using Kenward-Roger. (You can use summary(., ddf="Kenward-Roger")
to get KR degrees of freedom/p-values from lmerTest
. Kenward-Roger is generally a little more accurate, but is slow to the point of infeasibility for large data sets, which is presumably why Satterthwaite is the default in lmerTest
.)
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.