Phillip Alday
Phillip Alday
@andreasnoack see also https://github.com/JuliaStats/MixedModels.jl/issues/312
I don't think that the by-`row` random effect is in the SAS model. I didn't see it in my reading of it, but I've pinged @ararslan who's actually worked with...
1. I think you need to set the residual standard deviation to make that trick work -- the `σ` kwarg to `fit` will handle that. 2. I think it would...
I'm generally onboard with this, but we should probably do something like a pkgeval to see if we would actually break anything. But we're also not so near the bottom...
I'm closing this as stale, but I'm happy to re-open @MaxMenzies if you're still having problems.
I don't think there is a `==` method defined, so it falls back to `===`: ```julia julia> @code_lowered reval("1") == reval("1") CodeInfo( 1 ─ %1 = x === y └──...
Although lme4 and MixedModels.jl share a common intellectual heritage, they differ in a key way (beyond the choice of implementation language 😉) that makes a MixedModels.jl analogue of [`lmerMultiMember`](https://github.com/jvparidon/lmerMultiMember) a...
Packages we need to check (feel free to edit/add to) - [ ] MixedModels.jl https://github.com/JuliaStats/MixedModels.jl/pull/664 - [ ] Effects.jl - [x] GLM.jl https://github.com/JuliaStats/GLM.jl/pull/512 - [ ] RegressionFormulae.jl - [ ]...
> The question is if there is a need for very large er very quick Loess computations where the uncertainty calculation is just a nuisance. Sorry for the delay in...
potentially relevant xref: #3514