`model_performance()`

and`r2()`

now support*rma*-objects from package*metafor*,*mlm*and*bife*models.

`compare_performance()`

gets a`bayesfactor`

argument, to include or exclude the Bayes factor for model comparisons in the output.- Added
`r2.aov()`

.

- Fixed issue in
`performance_aic()`

for models from package*survey*, which returned three different AIC values. Now only the AIC value is returned. - Fixed issue in
`check_collinearity()`

for*glmmTMB*models when zero-inflated formula only had one predictor. - Fixed issue in
`check_model()`

for*lme*models. - Fixed issue in
`check_distribution()`

for*brmsfit*models. - Fixed issue in
`check_heteroscedasticity()`

for*aov*objects. - Fixed issues for
*lmrob*and*glmrob*objects.

- Removed
`logLik.felm()`

, because this method is now implemented in the*lfe*package. - Support for
`DirichletRegModel`

models.

`check_itemscale()`

to describe various measures of internal consistencies for scales which were built from several items from a PCA, using`parameters::principal_components()`

.`r2_efron()`

to compute Efron’s pseudo R2.

- Fixed issue in documentation of
`performance_score()`

.

- Support for
`mixor`

,`cpglm`

and`cpglmm`

models.

`performance_aic()`

as a small wrapper that returns the AIC. It is a generic function that also works for some models that don’t have a AIC method (like Tweedie models).`performance_lrt()`

as a small wrapper around`anova()`

to perform a Likelihood-Ratio-Test for model comparison.

- Fix issues with CRAN checks.

`model_performance()`

now calculates AIC for Tweedie models.

- Support for
`bracl`

,`brmultinom`

,`fixest`

,`glmx`

,`glmmadmb`

,`mclogit`

,`mmclogit`

,`vgam`

and`vglm`

models. `model_performance()`

now supports*plm*models.`r2()`

now supports*complmrob*models.`compare_performance()`

now gets a`plot()`

-method (requires package**see**).

`compare_performance()`

gets a`rank`

-argument, to rank models according to their overall model performance.`compare_performance()`

has a nicer`print()`

-method now.- Verbosity for
`compare_performance()`

was slightly adjusted. `model_performance()`

-methods for different objects now also have a`verbose`

-argument.

`check_collinearity()`

now no longer returns backticks in row- and column names.

- Fixed issue in
`r2()`

for`wbm`

-models with cross-level interactions. `plot()`

-methods for`check_heteroscedasticity()`

and`check_homogeneity()`

now work without requiring to load package*see*before.- Fixed issues with models of class
`rlmerMod`

.

`performance()`

is an alias for`model_performance()`

.

`principal_components()`

was removed and re-implemented in the**parameters**-package. Please use`parameters::principal_components()`

now.

`check_outliers()`

now also works on data frames.- Added more methods to
`check_outliers()`

. `performance_score()`

now also works on`stan_lmer()`

and`stan_glmer()`

objects.`check_singularity()`

now works with models of class*clmm*.`r2()`

now works with models of class*clmm*,*bigglm*and*biglm*.`check_overdispersion()`

for mixed models now checks that model family is Poisson.

- Fixed bug in
`compare_performance()`

that toggled a warning although models were fit from same data. - Fixed bug in
`check_model()`

for*glmmTMB*models that occurred when checking for outliers.

- Many
`check_*()`

-methods now get a`plot()`

-method. Package**see**is required for plotting. `model_performance()`

gets a preliminary`print()`

-method.

- The attribute for the standard error of the Bayesian R2 (
`r2_bayes()`

) was renamed from`std.error`

to`SE`

to be in line with the naming convention of other easystats-packages. `compare_performance()`

now shows the Bayes factor when all compared models are fit from the same data. Previous behaviour was that the BF was shown when models were of same class.

`model_performance()`

now also works for*lavaan*-objects.`check_outliers()`

gets a`method`

-argument to choose the method for detecting outliers. Furthermore, two new methods (Mahalanobis Distance and Invariant Coordinate Selection) were implemented.`check_model()`

now performs more checks for GLM(M)s and other model objects.`check_model()`

gets a`check`

-argument to plot selected checks only.`r2_nakagawa()`

now returns r-squared for models with singular fit, where no random effect variances could be computed. The r-squared then does not take random effect variances into account. This behaviour was changed to be in line with`MuMIn::r.squaredGLMM()`

, which returned a value for models with singular fit.`check_distribution()`

now detects negative binomial and zero-inflated distributions. Furthermore, attempt to improve accuracy.`check_distribution()`

now also accepts a numeric vector as input.`compare_performance()`

warns if models were not fit from same data.

`check_homogeneity()`

to check models for homogeneity of variances.

- Fixed issues with
`compare_performance()`

and row-ordering. - Fixed issue in
`check_collinearity()`

for zero-inflated models, where the zero-inflation component had not enough model terms to calculate multicollinearity. - Fixed issue in some
`check_*()`

and`performance_*()`

functions for models with binary outcome, when outcome variable was a factor.

`r2()`

now works for more regression models.`r2_bayes()`

now works for multivariate response models.`model_performance()`

now works for more regression models, and also includes the log-loss, proper scoring rules and percentage of correct predictions as new metric for models with binary outcome.

`performance_accuracy()`

, which calculates the predictive accuracy of linear or logistic regression models.`performance_logloss()`

to compute the log-loss of models with binary outcome. The log-loss is a proper scoring function comparable to the`rmse()`

.`performance_score()`

to compute the logarithmic, quadratic and spherical proper scoring rules.`performance_pcp()`

to calculate the percentage of correct predictions for models with binary outcome.`performance_roc()`

, to calculate ROC-curves.`performance_aicc()`

, to calculate the second-order AIC (AICc).

`check_collinearity()`

to calculate the variance inflation factor and check model predictors for multicollinearity.`check_outliers()`

to check models for influential observations.`check_heteroscedasticity()`

to check models for (non-)constant error variance.`check_normality()`

to check models for (non-)normality of residuals.`check_autocorrelation()`

to check models for auto-correlated residuals.`check_distribution()`

to classify the distribution of a model-family using machine learning.

`r2_mckelvey()`

to compute McKelvey and Zavoinas R2 value.`r2_zeroinflated()`

to compute R2 for zero-inflated (non-mixed) models.`r2_xu()`

as a crude R2 measure for linear (mixed) models.

`model_performance.stanreg()`

and`model_performance.brmsfit()`

now only return one R2-value and its standard error, instead of different (robust) R2 measures and credible intervals.`error_rate()`

is now integrated in the`performance_pcp()`

-function.

`model_performance.stanreg()`

and`model_performance.brmsfit()`

now also return the*WAIC*(widely applicable information criterion).`r2_nakagawa()`

now calculates the full R2 for mixed models with zero-inflation.`icc()`

now returns`NULL`

and no longer stops when no mixed model is provided.`compare_performance()`

now shows the Bayes factor when all compared models are of same class.- Some functions get a
`verbose`

-argument to show or suppress warnings.

- Renamed
`r2_coxnell()`

to`r2_coxsnell()`

. - Fix issues in
`r2_bayes()`

and`model_performance()`

for ordinal models resp. models with cumulative link (#48). `compare_performance()`

did not sort the`name`

-column properly, if the columns`class`

and`name`

were not in the same alphabetical order (#51).