Why is the glmmLasso package failing to add random effects?

Question

I am trying to determine if a problem I'm having with the glmmLasso package in r is caused by my local machine or if it's a larger problem. When I run the examples give in the glmmLasso documentation, the random effect structure is not incorporated into the analysis correctly.

For example, running this code (copied directly from the documentation):

library(glmmLasso) 
lm2 <- glmmLasso(points~transfer.spendings + ave.unfair.score 
        + ball.possession + tackles + ave.attend 
        + sold.out, rnd = list(team=~1 + ave.attend), lambda=10, 
        data = soccer, control = list(index=c(1,2,3,4,NA,5), 
        method="REML",print.iter=TRUE))
summary(lm2)

produces the following output (notice the warning at the bottom):

Call:
glmmLasso.formula(fix = points ~ transfer.spendings + ave.unfair.score + 
    ball.possession + tackles + ave.attend + sold.out, rnd = list(team = ~1 + 
    ave.attend), lambda = 10, data = soccer, control = list(index = c(1, 
    2, 3, 4, NA, 5), method = "REML", print.iter = TRUE))

Fixed Effects:

Coefficients:
                   Estimate StdErr z.value p.value
(Intercept)         44.9576     NA      NA      NA
ave.attend           5.7944     NA      NA      NA
transfer.spendings   2.6151     NA      NA      NA
ave.unfair.score     0.0000     NA      NA      NA
ball.possession      0.0000     NA      NA      NA
tackles              0.0000     NA      NA      NA
sold.out             4.6687     NA      NA      NA

No random effects included!

This is with R version 3.2.2 and glmmLasso version 1.3.5.

Can someone please run the block of code above and let me know if you're seeing similar output? Or if possible, let me know how to correct this issue on my machine.

Answer 1

Thank you for making me aware of this. There simply was a small bug in the summary-function, which occured when the package was recently extended to fit also models without random effect components. The bug has been corrected and the corrected package has been submitted to CRAN again.