Bug: estimate_contrasts failing with basic example

[dfalster]

Hi team, thanks for the great work. I love how your packages make it easier to process the outputs of models. I use these teaching a large 2nd year university course with 170 students. :)

I'm encountering a strange error and not sure how to solve or diagnose this. When I run estimate_contrasts with the basic example I get a cryptic error. I'm running the latest version on max OSX, R and packages. Moreover it used to work, so this behaviour has appeared in the last few days. Not sure how or why.

I've also included the stack call below. I'm a reasonably advanced user and a bit perplexed

The below was run in a clean R session. It occurs whether running in rstduio or terminal,

> library(modelbased)
>   model <- lm(Sepal.Width ~ Species, data = iris)
>    estimate_contrasts(model)
We selected `contrast=c("Species")`.
Error: Sorry, calculating marginal contrasts failed with following error:
Assertion failed. One of the following must apply: * checkmate::check_character(hypothesis): Must be of type
  'character', not 'formula' * checkmate::check_choice(hypothesis): Must be element of set
  {'pairwise','reference','sequential','meandev','meanotherdev','revpairwise','revreference','revsequential'}, but is * not atomic scalar * checkmate::check_numeric(hypothesis): Must
  be of type 'numeric', not 'formula' * checkmate::check_matrix(hypothesis): Must be of type 'matrix', not 'formula' * checkmate::check_function(hypothesis): Must be a function, not
  'formula' * checkmate::check_null(hypothesis): Must be NULL

> sessionInfo()
R version 4.4.2 (2024-10-31)
Platform: aarch64-apple-darwin20
Running under: macOS Sequoia 15.3.1

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0

locale:
[1] en_US.UTF-8/en_AU.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

time zone: Australia/Sydney
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices datasets  utils     methods   base

other attached packages:
[1] modelbased_0.9.0 datapasta_3.1.0

loaded via a namespace (and not attached):
 [1] marginaleffects_0.20.1 compiler_4.4.2         backports_1.5.0        generics_0.1.3         cli_3.6.3.9002         datawizard_1.0.0       Rcpp_1.0.14            crayon_1.5.3.9000
 [9] data.table_1.16.4      checkmate_2.3.2        insight_1.0.2          rlang_1.1.5            rdoc_0.1.0.9000

Stack

> options(error=recover)
> estimate_contrasts(model)
We selected `contrast=c("Species")`.
Error: Sorry, calculating marginal contrasts failed with following error:
Assertion failed. One of the following must apply: * checkmate::check_character(hypothesis): Must be of type
  'character', not 'formula' * checkmate::check_choice(hypothesis): Must be element of set
  {'pairwise','reference','sequential','meandev','meanotherdev','revpairwise','revreference','revsequential'}, but is * not atomic scalar * checkmate::check_numeric(hypothesis): Must
  be of type 'numeric', not 'formula' * checkmate::check_matrix(hypothesis): Must be of type 'matrix', not 'formula' * checkmate::check_function(hypothesis): Must be a function, not
  'formula' * checkmate::check_null(hypothesis): Must be NULL

Enter a frame number, or 0 to exit

1: estimate_contrasts(model)
2: estimate_contrasts.default(model)
3: get_marginalcontrasts(model, contrast = contrast, by = by, predict = predict, comparison = comparison, p_adjust = p_adjust, ci = ci, estimate = estimate, transform = transform, verbose = verbose,
4: estimate_means(model = model, by = unique(c(my_args$contrast, my_args$by)), ci = ci, hypothesis = my_args$comparison, predict = predict, backend = "marginaleffects", estimate = estimate, transfor
5: get_marginalmeans(model, by = by, predict = predict, ci = ci, estimate = estimate, transform = transform, verbose = verbose, ...)
6: .call_marginaleffects(fun_args)
7: insight::format_error(msg)
8: format_alert(..., type = "error")

[strengejacke]

We should check is the correct version of marginaleffects is installed. In your case, you need to update to version 0.20.5, then it should work.

[strengejacke]

No, sorry, you need marginaleffects 0.25.0
Anyway, I recommend updating packages, and after that, run easystats::install_latest().

[dfalster]

Thanks for the rapid response. confirming that updating to marginaleffects 0.25.0 fixed it!