[Experimental] Use effects::allEffects() to estimate marginal predictions and return a tibble tidied in a way that it could be used by broom.helpers functions. See vignette("functions-supported-by-effects", package = "effects") for a list of supported models.

tidy_all_effects(x, conf.int = TRUE, conf.level = 0.95, ...)



a model


logical indicating whether or not to include a confidence interval in the tidied output


the confidence level to use for the confidence interval


additional parameters passed to effects::allEffects()


By default, effects::allEffects() estimate marginal predictions at the mean at the observed means for continuous variables and weighting modalities of categorical variables according to their observed distribution in the original dataset. Marginal predictions are therefore computed at a sort of averaged situation / typical values for the other variables fixed in the model.

For more information, see vignette("marginal_tidiers", "broom.helpers").


If the model contains interactions, effects::allEffects() will return marginal predictions for the different levels of the interactions.


if (FALSE) { # interactive()
df <- Titanic %>%
  dplyr::as_tibble() %>%
  tidyr::uncount(n) %>%
  dplyr::mutate(Survived = factor(Survived, c("No", "Yes")))
mod <- glm(
  Survived ~ Class + Age + Sex,
  data = df, family = binomial
tidy_plus_plus(mod, tidy_fun = tidy_all_effects)