Joshua Lambert

Possibility to generalise probability distribution interface?

3

I've been taking a look through #504 and I really like the way distributions are specified and enable nesting for parameter uncertainty. I think this could be a nice interface...

Document how to handle grouped line list columns

5

It is unclear from the current {incidence2} documentation whether the package, specifically `incidence2::incidence()`, can handle grouped columns. An example of such a line list with a grouped column is the...

This PR enhances the plotting method for `` and `` objects by using {ggplot2}, {ggdist} and {gridExtras} R packages. The previous plotting methods used base R functionality. The new methods...

Could you add a comment explaining why we prefer returning NA than errorring (during input checking) here? _Originally posted by @Bisaloo in https://github.com/epiverse-trace/epiparameter/pull/259#discussion_r1539134071_

Enhance, delete or leave `<multi_epidist>`

10

The `` class in {epiparameter} only has one purpose: improve printing when there are a large number of `` entries returned by `epidist_db()`. From #197 there was some difference of...

{epiparameter} Shiny App or Quarto Dashboard

2

A dashboard to explore the parameter library and easier visualise the distributions would be a useful supplementary tool.

Can we make it so that `identical(stats::family(x$prob_dist), "truncated")` work for all cases? I.e., remove edge cases and provide a more consistent structure for all epidist objects. _Originally posted by @Bisaloo...

`aggregate.epidist` S3 method

1

An issue to discuss development of an `aggregate` method for ``. Initial work started by @Bisaloo, Anne Cori, Sangeeta Bhatia, Patrick Doohan, Christian Morgenstern, and Finlay Campbell in #270.

Please include a brief description of the issue and any proposed solutions you may have.

This way of specifying uncertainty implies that the uncertainty in parameters is uncorrelated, which it normally won't be - if that's how uncertainty is reported then obviously there is nothing...