Hanne Oberman

Agreed! Just here to leave my temporary solutions for others: ``` # load packages library(dplyr) library(ggplot2) # create some data categories

@johamunoz Unfortunately, the checks failed... Could you please try to solve the CMD check WARNING?

Hi Johanna, looks good! But would it be possible to add your function without so many dependencies? Currently, there are a hand full of packages added to the Imports part...

@johamunoz Unfortunately, one of the checks failed again. Could you please try to solve the error? Let me know if you need some help!

Hi @bbachilles, could you please share a [reprex](https://reprex.tidyverse.org/) for this issue?

This doesn't answer your question, but have you tried using the `mitml` package to pool the coefficients of your random effects model? See e.g. https://stefvanbuuren.name/fimd/sec-mlguidelines.html. A workflow where `imp` is...

Not a solution, but to circumvent the problem you could use the ggplot code that I've written for a shiny app here: [https://github.com/amices/shinyMice/blob/main/shinymice/R/utils_02_model.R](https://github.com/amices/shinyMice/blob/main/shinymice/R/utils_02_model.R)

@woodwards The visualization package [`ggmice`](https://amices.org/ggmice/index.html) now offers easily adjustable md pattern plots. You could use it from CRAN or look at the source code in [this repo](https://github.com/amices/ggmice/)?

This is a second attempt to include the IPD Heckman imputation function (see #485)

Check whether conditional import can be used?