Skip to contents

Changelog

Source: NEWS.md

performance 0.14.0

Breaking Changes

  • The "Increased SE" column in the output of check_collinearity() was renamed into "adj. VIF" (=adjusted VIF). Furthermore, the computation of the adjusted VIF now correctly accounts for the numbers of levels (i.e. degrees of freedom) for factors.

New functions

Changes

  • Singularity checks with check_singularity() are now more efficient and also include the random effects for the dispersion component (from package glmmTMB). Furthermore, a check argument allows to check for general singularity (for the full model), or can return singularity checks for each random effects term separately.

Bug fixes

  • Fixed issue with wrong computation of pseudo-R2 for some models where the base-model (null model) was updated using the original data, which could include missing values. Now the model frame is used, ensuring the correct number of observations in the returned base-model, thus calculating the correct log-likelihood and returning the correct pseudo-R2.

  • Fixed examples in check_outliers().

performance 0.13.0

CRAN release: 2025-01-15

Breaking changes

  • check_outliers() with method = "optics" now returns a further refined cluster selection, by passing the optics_xi argument to dbscan::extractXi().

  • Deprecated arguments and alias-function-names have been removed.

  • Argument names in check_model() that refer to plot-aesthetics (like dot_size) are now harmonized across easystats packages, meaning that these have been renamed. They now follow the pattern aesthetic_type, e.g. size_dot (instead of dot_size).

Changes

Bug fixes

  • check_outliers() did not warn that no numeric variables were found when only the response variable was numeric, but all relevant predictors were not.

  • check_collinearity() did not work for glmmTMB models when zero-inflation component was set to ~0.

performance 0.12.4

CRAN release: 2024-10-18

Changes

  • check_dag() now also checks for colliders, and suggests removing it in the printed output.

  • Minor revisions to the printed output of check_dag().

Bug fixes

  • Fixed failing tests that broke due to changes in latest glmmTMB update.

performance 0.12.3

CRAN release: 2024-09-02

New functions

  • check_dag(), to check DAGs for correct adjustment sets.

Changes

  • check_heterogeneity_bias() gets a nested argument. Furthermore, by can specify more than one variable, meaning that nested or cross-classified model designs can also be tested for heterogeneity bias.

performance 0.12.2

CRAN release: 2024-07-18

Patch release, to ensure that performance runs with older version of datawizard on Mac OSX with R (old-release).

performance 0.12.1

CRAN release: 2024-07-15

General

  • icc() and r2_nakagawa() get a null_model argument. This can be useful when computing R2 or ICC for mixed models, where the internal computation of the null model fails, or when you already have fit the null model and want to save time.

  • icc() and r2_nakagawa() get a approximation argument indicating the approximation method for the distribution-specific (residual) variance. See Nakagawa et al. 2017 for details.

  • icc() and r2_nakagawa() get a model_component argument indicating the component for zero-inflation or hurdle models.

  • performance_rmse() (resp. rmse()) can now compute analytical and bootstrapped confidence intervals. The function gains following new arguments: ci, ci_method and iterations.

  • New function r2_ferrari() to compute Ferrari & Cribari-Neto’s R2 for generalized linear models, in particular beta-regression.

  • Improved documentation of some functions.

Bug fixes

  • Fixed issue in check_model() when model contained a transformed response variable that was named like a valid R function name (e.g., lm(log(lapply) ~ x), when data contained a variable named lapply).

  • Fixed issue in check_predictions() for linear models when response was transformed as ratio (e.g. lm(succes/trials ~ x)).

  • Fixed issue in r2_bayes() for mixed models from rstanarm.

performance 0.12.0

CRAN release: 2024-06-08

Breaking

  • Aliases posterior_predictive_check() and check_posterior_predictions() for check_predictions() are deprecated.

  • Arguments named group or group_by will be deprecated in a future release. Please use by instead. This affects check_heterogeneity_bias() in performance.

General

  • Improved documentation and new vignettes added.

  • check_model() gets a base_size argument, to set the base font size for plots.

  • check_predictions() for stanreg and brmsfit models now returns plots in the usual style as for other models and no longer returns plots from bayesplot::pp_check().

  • Updated the trained model that is used to prediction distributions in check_distribution().

Bug fixes

  • check_model() now falls back on normal Q-Q plots when a model is not supported by the DHARMa package and simulated residuals cannot be calculated.

performance 0.11.0

CRAN release: 2024-03-22

New supported models

  • Rudimentary support for models of class serp from package serp.

New functions

General

Bug fixes

performance 0.10.9

CRAN release: 2024-02-17

Changes

  • r2() for models of class glmmTMB without random effects now returns the correct r-squared value for non-mixed models.

  • check_itemscale() now also accepts data frames as input. In this case, factor_index must be specified, which must be a numeric vector of same length as number of columns in x, where each element is the index of the factor to which the respective column in x.

  • check_itemscale() gets a print_html() method.

  • Clarification in the documentation of the estimator argument for performance_aic().

  • Improved plots for overdispersion-checks for negative-binomial models from package glmmTMB (affects check_overdispersion() and check_model()).

  • Improved detection rates for singularity in check_singularity() for models from package glmmTMB.

  • For model of class glmmTMB, deviance residuals are now used in the check_model() plot.

  • Improved (better to understand) error messages for check_model(), check_collinearity() and check_outliers() for models with non-numeric response variables.

  • r2_kullback() now gives an informative error for non-supported models.

Bug fixes

  • Fixed issue in binned_residuals() for models with binary outcome, where in rare occasions empty bins could occur.

  • performance_score() should no longer fail for models where scoring rules can’t be calculated. Instead, an informative message is returned.

  • check_outliers() now properly accept the percentage_central argument when using the "mcd" method.

  • Fixed edge cases in check_collinearity() and check_outliers() for models with response variables of classes Date, POSIXct, POSIXlt or difftime.

  • Fixed issue with check_model() for models of package quantreg.

performance 0.10.8

CRAN release: 2023-10-30

Changes

  • Changed behaviour of check_predictions() for models from binomial family, to get comparable plots for different ways of outcome specification. Now, if the outcome is a proportion, or defined as matrix of trials and successes, the produced plots are the same (because the models should be the same, too).

Bug fixes

  • Fixed CRAN check errors.

  • Fixed issue with binned_residuals() for models with binomial family, where the outcome was a proportion.

performance 0.10.7

CRAN release: 2023-10-27

Breaking changes

  • binned_residuals() gains a few new arguments to control the residuals used for the test, as well as different options to calculate confidence intervals (namely, ci_type, residuals, ci and iterations). The default values to compute binned residuals have changed. Default residuals are now “deviance” residuals (and no longer “response” residuals). Default confidence intervals are now “exact” intervals (and no longer based on Gaussian approximation). Use ci_type = "gaussian" and residuals = "response" to get the old defaults.

Changes to functions

  • binned_residuals() - like check_model() - gains a show_dots argument to show or hide data points that lie inside error bounds. This is particular useful for models with many observations, where generating the plot would be very slow.

performance 0.10.6

General

  • Support for nestedLogit models.

Changes to functions

  • check_outliers() for method "ics" now detects number of available cores for parallel computing via the "mc.cores" option. This is more robust than the previous method, which used parallel::detectCores(). Now you should set the number of cores via options(mc.cores = 4).

Bug fixes

  • Fixed issues is check_model() for models that used data sets with variables of class "haven_labelled".

performance 0.10.5

CRAN release: 2023-09-12

Changes to functions

  • More informative message for test_*() functions that “nesting” only refers to fixed effects parameters and currently ignores random effects when detecting nested models.

  • check_outliers() for "ICS" method is now more stable and less likely to fail.

  • check_convergence() now works for parsnip _glm models.

Bug fixes

  • check_collinearity() did not work for hurdle- or zero-inflated models of package pscl when model had no explicitly defined formula for the zero-inflation model.

performance 0.10.4

CRAN release: 2023-06-02

Changes to functions

  • icc() and r2_nakagawa() gain a ci_method argument, to either calculate confidence intervals using boot::boot() (instead of lmer::bootMer()) when ci_method = "boot" or analytical confidence intervals (ci_method = "analytical"). Use ci_method = "boot" when the default method fails to compute confidence intervals and use ci_method = "analytical" if bootstrapped intervals cannot be calculated at all. Note that the default computation method is preferred.

  • check_predictions() accepts a bandwidth argument (smoothing bandwidth), which is passed down to the plot() methods density-estimation.

  • check_predictions() gains a type argument, which is passed down to the plot() method to change plot-type (density or discrete dots/intervals). By default, type is set to "default" for models without discrete outcomes, and else type = "discrete_interval".

  • performance_accuracy() now includes confidence intervals, and reports those by default (the standard error is no longer reported, but still included).

Bug fixes

  • Fixed issue in check_collinearity() for fixest models that used i() to create interactions in formulas.

performance 0.10.3

CRAN release: 2023-04-07

New functions

Support for new models

Changes to functions

  • test_*() functions now automatically fit a null-model when only one model objects was provided for testing multiple models.

  • Warnings in model_performance() for unsupported objects of class BFBayesFactor can now be suppressed with verbose = FALSE.

  • check_predictions() no longer fails with issues when re_formula = NULL for mixed models, but instead gives a warning and tries to compute posterior predictive checks with re_formuka = NA.

  • check_outliers() now also works for meta-analysis models from packages metafor and meta.

  • plot() for performance::check_model() no longer produces a normal QQ plot for GLMs. Instead, it now shows a half-normal QQ plot of the absolute value of the standardized deviance residuals.

Bug fixes

performance 0.10.2

CRAN release: 2023-01-12

General

Changes to functions

Bug fixes

  • Fixed issue in item_difficulty() with detecting the maximum values of an item set. Furthermore, item_difficulty() gets a maximum_value argument in case no item contains the maximum value due to missings.

performance 0.10.1

CRAN release: 2022-11-25

General

  • Minor improvements to the documentation.

Changes to functions

  • icc() and r2_nakagawa() get ci and iterations arguments, to compute confidence intervals for the ICC resp. R2, based on bootstrapped sampling.

  • r2() gets ci, to compute (analytical) confidence intervals for the R2.

  • The model underlying check_distribution() was now also trained to detect cauchy, half-cauchy and inverse-gamma distributions.

  • model_performance() now allows to include the ICC for Bayesian models.

Bug fixes

  • verbose didn’t work for r2_bayes() with BFBayesFactor objects.

  • Fixed issues in check_model() for models with convergence issues that lead to NA values in residuals.

  • Fixed bug in check_outliers whereby passing multiple elements to the threshold list generated an error (#496).

  • test_wald() now warns the user about inappropriate F test and calls test_likelihoodratio() for binomial models.

  • Fixed edge case for usage of parellel::detectCores() in check_outliers().

performance 0.10.0

CRAN release: 2022-10-03

Breaking Change

New functions

Changes to functions

  • check_normality(), check_homogeneity() and check_symmetry() now works for htest objects.

  • Print method for check_outliers() changed significantly: now states the methods, thresholds, and variables used, reports outliers per variable (for univariate methods) as well as any observation flagged for several variables/methods. Includes a new optional ID argument to add along the row number in the output (@rempsyc #443).

  • check_outliers() now uses more conventional outlier thresholds. The IQR and confidence interval methods now gain improved distance scores that are continuous instead of discrete.

Bug Fixes

performance 0.9.2

CRAN release: 2022-08-10

General

  • print() methods for model_performance() and compare_performance() get a layout argument, which can be "horizontal" (default) or "vertical", to switch the layout of the printed table.

  • Improved speed performance for check_model() and some other performance_*() functions.

  • Improved support for models of class geeglm.

Changes to functions

  • check_model() gains a show_dots argument, to show or hide data points. This is particular useful for models with many observations, where generating the plot would be very slow.

Bug Fixes

performance 0.9.1

CRAN release: 2022-06-20

Breaking

  • The formerly “conditional” ICC in icc() is now named “unadjusted” ICC.

New functions

Support for new models

  • Added support for models from package estimator.

Changes to functions

Bug fixes

  • check_predictions() did not work for GLMs with matrix-response.

  • check_predictions() did not work for logistic regression models (i.e. models with binary response) from package glmmTMB

  • item_split_half() did not work when the input data frame or matrix only contained two columns.

  • Fixed wrong computation of BIC in model_performance() when models had transformed response values.

  • Fixed issues in check_model() for GLMs with matrix-response.

performance 0.9.0

CRAN release: 2022-03-30

New functions

  • check_concurvity(), which returns GAM concurvity measures (comparable to collinearity checks).

Changes to functions

Check functions

Test functions

Model performance functions

  • performance_aic() now corrects the AIC value for models with transformed response variables. This also means that comparing models using compare_performance() allows comparisons of AIC values for models with and without transformed response variables.

  • Also, model_performance() now corrects both AIC and BIC values for models with transformed response variables.

Plotting and printing

  • The print() method for binned_residuals() now prints a short summary of the results (and no longer generates a plot). A plot() method was added to generate plots.

  • The plot() output for check_model() was revised:

    • For binomial models, the constant variance plot was omitted, and a binned residuals plot included.

    • The density-plot that showed normality of residuals was replaced by the posterior predictive check plot.

Bug fixes

performance 0.8.0

CRAN release: 2021-10-01

Breaking Changes

  • The ci-level in r2() for Bayesian models now defaults to 0.95, to be in line with the latest changes in the bayestestR package.

  • S3-method dispatch for pp_check() was revised, to avoid problems with the bayesplot package, where the generic is located.

General

  • Minor revisions to wording for messages from some of the check-functions.

  • posterior_predictive_check() and check_predictions() were added as aliases for pp_check().

New functions

Changes to functions

  • r2() for linear models can now compute confidence intervals, via the ci argument.

Bug fixes

  • Fixed issues in check_model() for Bayesian models.

  • Fixed issue in pp_check() for models with transformed response variables, so now predictions and observed response values are on the same (transformed) scale.

performance 0.7.3

CRAN release: 2021-07-21

Changes to functions

performance 0.7.2

CRAN release: 2021-05-17

New functions

Bug fixes

  • Fixed issue with "data length differs from size of matrix" warnings in examples in forthcoming R 4.2.

  • Fixed issue in check_normality() for models with sample size larger than

5.000 observations.

  • Fixed issue in check_model() for glmmTMB models.

  • Fixed issue in check_collinearity() for glmmTMB models with zero-inflation, where the zero-inflated model was an intercept-only model.

performance 0.7.1

CRAN release: 2021-04-09

New supported models

  • Add support for model_fit (tidymodels).

  • model_performance supports kmeans models.

General

  • Give more informative warning when r2_bayes() for BFBayesFactor objects can’t be calculated.

  • Several check_*() functions now return informative messages for invalid model types as input.

  • r2() supports mhurdle (mhurdle) models.

  • Added print() methods for more classes of r2().

  • The performance_roc() and performance_accuracy() functions unfortunately had spelling mistakes in the output columns: Sensitivity was called Sensivity and Specificity was called Specifity. We think these are understandable mistakes :-)

Changes to functions

check_model()

model_performance()

Other functions

  • The default-method for r2() now tries to compute an r-squared for all models that have no specific r2()-method yet, by using following formula: 1-sum((y-y_hat)^2)/sum((y-y_bar)^2))

  • The column name Parameter in check_collinearity() is now more appropriately named Term.

Bug fixes

  • test_likelihoodratio() now correctly sorts models with identical fixed effects part, but different other model parts (like zero-inflation).

  • Fixed incorrect computation of models from inverse-Gaussian families, or Gaussian families fitted with glm().

  • Fixed issue in performance_roc() for models where outcome was not 0/1 coded.

  • Fixed issue in performance_accuracy() for logistic regression models when method = "boot".

  • cronbachs_alpha() did not work for matrix-objects, as stated in the docs. It now does.

performance 0.7.0

CRAN release: 2021-02-03

General

  • Roll-back R dependency to R >= 3.4.

Breaking Changes

New functions to test or compare models

Changes to functions

performance_lrt()

  • performance_lrt() get an alias test_likelihoodratio().

  • Does not return AIC/BIC now (as they are not related to LRT per se and can be easily obtained with other functions).

  • Now contains a column with the difference in degrees of freedom between models.

  • Fixed column names for consistency.

model_performance()

  • Added more diagnostics to models of class ivreg.

Other functions

Bug fixes

performance 0.6.1

CRAN release: 2020-12-09

General

Bug fixes

  • Fixed examples, now using suggested packages only conditionally.

performance 0.6.0

CRAN release: 2020-12-01

General

New functions

  • r2_somers(), to compute Somers’ Dxy rank-correlation as R2-measure for logistic regression models.

  • display(), to print output from package-functions into different formats. print_md() is an alias for display(format = "markdown").

Changes to functions

model_performance()

  • model_performance() is now more robust and doesn’t fail if an index could not be computed. Instead, it returns all indices that were possible to calculate.

  • model_performance() gains a default-method that catches all model objects not previously supported. If model object is also not supported by the default-method, a warning is given.

  • model_performance() for metafor-models now includes the degrees of freedom for Cochran’s Q.

Other functions

  • performance_mse() and performance_rmse() now always try to return the (R)MSE on the response scale.

  • performance_accuracy() now accepts all types of linear or logistic regression models, even if these are not of class lm or glm.

  • performance_roc() now accepts all types of logistic regression models, even if these are not of class glm.

  • r2() for mixed models and r2_nakagawa() gain a tolerance-argument, to set the tolerance level for singularity checks when computing random effect variances for the conditional r-squared.

Bug fixes

  • Fixed issue in icc() introduced in the last update that make lme-models fail.

  • Fixed issue in performance_roc() for models with factors as response.

performance 0.5.1

CRAN release: 2020-10-29

Breaking changes

  • Column names for model_performance() and compare_performance() were changed to be in line with the easystats naming convention: LOGLOSS is now Log_loss, SCORE_LOG is Score_log and SCORE_SPHERICAL is now Score_spherical.

New functions

  • r2_posterior() for Bayesian models to obtain posterior distributions of R-squared.

Changes to functions

Bug fixes

  • Fix bug in compare_performance() when ... arguments were function calls to regression objects, instead of direct function calls.

performance 0.5.0

CRAN release: 2020-09-12

General

New functions

  • pp_check() to compute posterior predictive checks for frequentist models.

Bug fixes

performance 0.4.8

CRAN release: 2020-07-27

General

  • Removed suggested packages that have been removed from CRAN.

Changes to functions

  • icc() now also computes a “classical” ICC for brmsfit models. The former way of calculating an “ICC” for brmsfit models is now available as new function called variance_decomposition().

Bug fixes

  • Fix issue with new version of bigutilsr for check_outliers().

  • Fix issue with model order in performance_lrt().

performance 0.4.7

CRAN release: 2020-06-14

General

  • Support for models from package mfx.

Changes to functions

  • model_performance.rma() now includes results from heterogeneity test for meta-analysis objects.

  • check_normality() now also works for mixed models (with the limitation that studentized residuals are used).

  • check_normality() gets an effects-argument for mixed models, to check random effects for normality.

Bug fixes

performance 0.4.6

CRAN release: 2020-05-03

General

  • Minor revisions to model_performance() to meet changes in mlogit package.

  • Support for bayesx models.

Changes to functions

  • icc() gains a by_group argument, to compute ICCs per different group factors in mixed models with multiple levels or cross-classified design.

  • r2_nakagawa() gains a by_group argument, to compute explained variance at different levels (following the variance-reduction approach by Hox 2010).

  • performance_lrt() now works on lavaan objects.

Bug fixes

  • Fix issues in some functions for models with logical dependent variable.

  • Fix bug in check_itemscale(), which caused multiple computations of skewness statistics.

  • Fix issues in r2() for gam models.

performance 0.4.5

CRAN release: 2020-03-28

General

Changes to functions

  • compare_performance() gets a bayesfactor argument, to include or exclude the Bayes factor for model comparisons in the output.

  • Added r2.aov().

Bug fixes