# GLMM ERROR: UndefVarError: emηᵢ not defined

**URL:** https://discourse.julialang.org/t/glmm-error-undefvarerror-em-not-defined/82672
**Category:** Statistics
**Tags:** question
**Created:** [June 13, 2022, 10:17am UTC](https://discourse.julialang.org/t/glmm-error-undefvarerror-em-not-defined/82672 "2022-06-13T10:17:18Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![Shuya\_Fan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/shuya_fan/32/37008_2.png) [@Shuya\_Fan](https://discourse.julialang.org/u/Shuya_Fan)
#### Post date: [June 13, 2022, 10:17am UTC](https://discourse.julialang.org/t/glmm-error-undefvarerror-em-not-defined/82672/1 "2022-06-13T10:17:18Z")

</div>

Hi,  
I’m new to Julia and it’s an awesome language. But I got some errors while running the GLMM. Looking forward to your help.  
In my data, ‘species’ and ‘newOBJIDsic’ are the random effect, ‘bio\_pd\_mpd\_mean’ is the fixed effect and the fixed effect has been scaled. Besides, there are no NAs in the data. The codes I used are as follows:

```julia
using DataFrames, DataFramesMeta, CSV, MixedModels, StatsModels, GLM, BenchmarkTools 
dfAll = CSV.read("df.all.naomit.scaled.bio_pd_mpd_mean.csv",DataFrame) 
dfAllform = @formula(ys ~ 1 + bio_pd_mpd_mean + (1|species)+ (1|newOBJIDsic)) 
gm1 = fit(MixedModel, dfAllform, dfAll, Binomial(), CloglogLink()) 
print(gm1)

```

but got the following error:

`ERROR: UndefVarError: emηᵢ not defined`

Then, I try to add `fast = true` in the code, as:

```julia
gm1 = fit(MixedModel, dfAllform, dfAll, Binomial(), CloglogLink(), fast = true)

```

then I got the following error:

```julia
ERROR: PosDefException: matrix is not positive definite; Cholesky factorization failed.

```

The data can be get from: [data](https://drive.google.com/file/d/1j6n0-ggxTBL-gP1dQ6PsXJJF9agPl6MR/view?usp=sharing).

Thanks so much in advance.