brms.mmrm
brms.mmrm copied to clipboard
openpharma
R package to run Bayesian MMRMs using {brms}
This PR fixes #102. @andrew-bean, @chstock, and @yonicd, would you be willing to have a look? There is a new `brm_formula_sigma()` function to flexibly model residual variances. ```r set.seed(0) data...
This pull request lays the groundwork for informative prior archetypes. It fixes #96 and #99, and adds a citation for https://opensource.nibr.com/bamdd/src/02h_mmrm.html. @andrew-bean, @chstock, and @yonicd, would you please have a...
The `model.Rmd` vignette could be more approachable and less cryptic, and it could align with the notation in `brms` more closely. I will wrap this into #105.
The package has undergone many changes since I last ran the pipeline for https://openpharma.github.io/brms.mmrm/articles/sbc.html. In particular, the package now supports different correlation structures and different [distributional parameter](https://cran.r-project.org/web/packages/brms/vignettes/brms_distreg.html) structures for `sigma`....
The interface could be `brm_formula(..., variance = "heterogeneous_group")`. (Homogeneous group-specific variances would be an odd choice, and I see no reason for it.) Then in `brm_marginal_draws()`, the calculation of effect...
cell means, treatment effects, and average over time. Planning to implement this after we are aligned on #100 and it is merged.
It is easy to create a rank-deficient model in R: ```r data(fev_data, package = "mmrm") formula [1] 10 ``` As part of #96, I would like to add a new...
Following up on #93, we could have different end-to-end workflows for specific informative prior use cases, such as successive differences (e.g. #92). We could begin with `brm_data()`, have specific functions...
Currently I don't think it is possible to add `y | weights(weight) ~ ...` in the brm_formula as it is constructed right now. I tried adding it through `...` but...
