Tamas K. Papp

better interface for matrix slices

1

Need a better interface when calculating the `inverse` of a (posterior) matrix by row, using a `TransformationTuple`.

Support `StaticVector` and possibly other `StaticArray`s. Two possible use cases: 1. map an `AbstractVector` to `StaticVector` elements when that is required by the transformation. Pro: more flexible interface. Con: transformations...

Rething API before tagging an initial release: - [ ] recognize both the callable and `transformation` as the primary transformation interface - [ ] remove `logjac`, `transformation_and_logjac` is more practical...

Possibly by a `TransformationNamedTuple`. Make sure it is smoothly wrapped by `TransformLogLikelihood`.

combine the stochastic volatility example into a single file

4

# TODO - [ ] write an introduction (is this indirect inference?) - [ ] document the motivation and how the model works (is it basically the one in the...

The documentation should have a section on making models run fast, in particular 1. paying attention to effective sample size, and model transformations 2. using a different AD framework (reverse...

```julia MultiColumn(pos, cell) = MultiColumn(1, pos, cell) ``` might make sense.

For local generation of docs, it is advised to run `] dev ..` from the `docs` directory to generate a correct manifest. This is not something that is easily done...