More than one random effect for nonparametricbootstrap

[joseah]

Dear Phillip,

First of all, many thanks for all the work you've put into this package so far!
Following this issue from theMixedModels.jl library, I've tried out using the nonparametricbootstrap method. However, I've run into the following error when trying to use two random effects in the model. For example:

sleepstudy = MixedModels.dataset(:sleepstudy)
m1 = fit(MixedModel, @formula(reaction ~ (1 | days) + (1 | subj)), sleepstudy; progress=false)
non = nonparametricbootstrap(MersenneTwister(42), 1000, m1)

ERROR: MethodError: no method matching lmul!(::Matrix{Float64}, ::Matrix{Float64})

I'm not sure if this is an error or a limitation in the current implementation.

Cheers,
Jose

• Julia v1.10.3
• MixedModels v4.22.5
• [647c4018] MixedModelsPermutations v0.2.0