Douglas Bates

Evaluation of devresid from an updated eta in GLMMs

1

In the "something to think about for the future" category, it seems to me that the basic loop in `glm` and `glmm` evaluations, `eta -> mu -> varfunc -> mueta...

Gradient of LMM objective through automatic differentiation

4

Copying here from Slack so that it doesn't disappear. I added a notebook to https://github.com/RePsychLing/ZiFPsychLing/ showing the forward mode and sketching the reverse-mode automatic differentiation of the objective for linear...

Finding your way around for R users

4

In private email Martin Maechler asked me several questions about using Julia and the MixedModels package. Because the answers to which may be of more general interest, I created this...

The Index tree interface

11

I am having difficulty getting my head around the indexed tree interface. I have a small package [RangeTrees.jl](https://github.com/dmbates/RangeTrees.jl) that creates interval trees in what I think is the indexed tree...

Preserve original expression when parsing a formula in terms2.0?

1

As discussed in https://github.com/JuliaInterop/RCall.jl/issues/306 I think it would be helpful to preserve a copy of the original expression passed to the `@formula` macro, either in the `FormulaTerm` type or perhaps...

Extend StatsBase.model_response methods with a Distribution argument

9

I have been thinking about conversion of a binary `PooledDataArray` or `CategoricalVector` to a 0/1 floating point vector in the `StatsBase.model_response` method. The trick is in determining what kind of...

Need for $(FLIBS)

1

With the "header only" version of Rcpp the `PKG_LIBS` definition In `src/Makevars` and `src/Makevars.win` can drop the call to `Rcpp::LdFlags()`. This is one of the big advantages of a header-only...

Positivity check in PDiagMat and ScalMat constructors?

1

At present there is no check for positivity of the arguments that will be on the diagonal of a `PDiagMat` or `ScalMat`. Probably a good idea to check that. ```julia...

Temporary duplication of capabilities in PDMats

1

I'm experimenting with using PDMats to represent covariance matrices for random-effects in the MixedModels package. Because I tend to use the factor more than the positive-definite matrix itself I will...

Using Arpack with MKL

14

```julia julia> versioninfo() Julia Version 0.7.0-beta.65 Commit e2de9b3d2e* (2018-06-28 03:45 UTC) Platform Info: OS: Linux (x86_64-linux-gnu) CPU: Intel(R) Core(TM) i5-3570 CPU @ 3.40GHz WORD_SIZE: 64 LIBM: libopenlibm LLVM: libLLVM-6.0.0 (ORCJIT,...