ggeffects 0.3.4 2018-06-08

General

  • Prediction for glmmTMB-objects now compute proper confidence intervals, due to fix in package glmmTMB 0.2.1
  • If terms in ggpredict() is missing or NULL, marginal effects for each model term are calculated. ggpredict() then returns a list of data frames, which can also be plotted with plot().

Changes to functions

  • The jitter-argument from plot() now accepts a numeric value between 0 and 1, to control the width of the random variation in data points.
  • ggpredict() and ggeffect() can now predict transformed values, which is useful, for instance, to exponentiate predictions for log(term) on the original scale of the variable. See package vignette, section Marginal effects at specific values or levels for examples.

Bug fixes

  • Multivariate response models in brms with variable names with underscores and dots were not correctly plotted.

ggeffects 0.3.3 2018-05-03

General

  • Better support for multivariate-response-models from brms.
  • Support for cumulative-link-models from brms.
  • ggpredict() now supports linear multivariate response models, i.e. lm() with multiple outcomes.

Changes to functions

  • ggpredict() gets a pretty-argument to reduce and “prettify” the value range from variables in terms for predictions. This applies to all variables in terms with more than 25 unique values.

Bug fixes

  • Recognize negative binomial family from brmsfit-models.

ggeffects 0.3.2 2018-03-21

General

  • ggpredict(), ggeffect() and gginteraction() get a x.as.factor-argument to preserve factor-class for the x-column in the returned data frame.
  • The terms-argument now also allows the specification of a range of numeric values in square brackets, e.g. terms = "age [30:50]".

Bug fixes

  • Give proper warning that clm-models don’t support full.data-argument.
  • emm() did not work properly for some random effects models.

ggeffects 0.3.1 2018-01-15

General

  • Use convert_case() from sjlabelled, in preparation for the latest snakecase-package update.

Bug fixes

  • Model weights are now correctly taken into account.

ggeffects 0.3.0 2017-11-27

General

  • Support for brmsfit-models from the brms-package.
  • Support for clm-models from the ordinal-package.
  • Support for multinom-models from the nnet-package.
  • Posterior predictive distributions (see argument ppd) now compute uncertainty intervals also for non-gaussian models.
  • Use functions from package sjstats (link inverse, model frame etc.).
  • If the regression model used weights, ggpredict() now computes the weighted mean as typical value for predictors that are held constant.
  • Use select-helpers from package tidyselect, instead of dplyr.

New functions

  • New summary() function, to provide information on predictions by grouping variables, and on constant values from adjustments.

Changes to functions

  • plot() gets a show.legend-argument to show or hide the legend of plots.

Bug fixes

  • Fixed issues with gam- and vgam-models.

ggeffects 0.2.2 2017-09-19

Changes to functions

  • plot() gets a dot.alpha-argument, to specify a different alpha-values for data points when plotting raw data.
  • plot() gets a jitter-argument, to add a small amount of random variation to the location of data points when plotting raw data.
  • plot() and getter-functions (like get_title() or get_x_labels()) get a case-argument, to convert labels into any case, using the snakecase-package.
  • Confidence intervals are now also computed for hurdle, zeroinfl, truncreg and betareg-models. Note, however, that due to some uncertainty, the intervals may not be “smooth”.

Bug fixes

  • Confidence intervals for generalized mixed effects models are now computed properly.
  • Different levels for confidence intervals (argument ci.lvl) were not always recognized.
  • Fixed issues with glmmTMB-models.
  • Fixed issues with lme-models.
  • Fixed issue when plotting data returned from ggeffect(), if the term in question was categorical.

ggeffects 0.2.1 2017-08-22

General

  • Support for stanreg models (pkg rstanarm).
  • Fixed issue with latest tidyr-update on CRAN.

Bug fixes

  • Plotting raw data with plot() did not work for predictions at specific values (i.e. when certain levels of predictor where selected in square brackets).
  • Computing predictions for mermod-objects did not work when model had only one fixed effects term.

ggeffects 0.2.0 2017-07-24

General

  • Updated package imports and dependencies.
  • Support for polr models (pkg MASS).
  • Support for hurdle and zeroinfl models (pkg pscl).
  • Support for betareg models (pkg betareg).
  • Support for truncreg models (pkg truncreg).
  • Support for coxph models (pkg survival).

New functions

  • emm() as convenient shortcut to compute the estimate marginal mean of the model’s response value.

Changes to functions

  • plot() gets a use.theme-argument, to use the default ggeffects-theme, or to use the default ggplot-theme.

Bug fixes

  • Fixed issues with columns resp. column names for models that used special functions in formula (e.g. s() for gam-models, or bs() for splines).
  • Fixed issue for wrong legend values when grouping term was a non-labelled factor with non-ordered numeric levels.

ggeffects 0.1.1 2017-05-17

Changes to functions

  • ggpredict() computes proper confidence intervals for merMod- and lme-objects.
  • Improved plot()-method, to better plot raw data.

Bug fixes

  • Confidence intervals were not properly calculated for glm’s.
  • For plot(), argument rawdata did not work for models with discrete binary response.
  • Fixed issues with models of class lme and glmmTMB.
  • Fixed issues with model-classes that preserved NA-values in model-frame.

ggeffects 0.1.0 2017-04-26

General

  • initial release