Changelog
Source:NEWS.md
insight 0.19.8
Bug fixes
Fixed issue in
get_loglikelihood()
for glmmodels with binary outcome, where levels were defined in reversed order.Fixed issue in
find_formula()
for models of classglmmPQL
(package MASS).
insight 0.19.7
CRAN release: 20231126
General
Support for objects of class
ggcomparisons
fromggeffects::hypothesis_test()
.brms::gr()
is now supported, meaning that functions likeget_data()
orfind_predictors()
now also work for models with groupspecific random effects.Fix CRAN check issues due to the last fixest update.
Changes to functions

get_varcov()
for models of classpgmm
(package plm) now also supported robust variancecovariance matrices (i.e. argumentvcov
).
Bug fixes
Fixed issue in
find_predictors()
for survival models withstrata()
, containing more that one variable.Fixed issue in
model_info()
, where in some cases logistic regression models were erroneously considered as"bernoulli"
models.Fixed issue in
find_formula()
for models of classgamlss
when therandom()
function was used with namespace in the formula (i.e.... + gamlss::random()
).model_info()
now detects models with zeroinflation part from package glmmTMB when models have truncatedfamilies but noziformula
.
insight 0.19.6
CRAN release: 20231012
General
 Improved documentation for
get_predicted_ci()
.
Changes to functions
model_info()
now recognized ordered beta families.find_formula
andget_response
fornestedLogit
models gain adichotomies
argument, to return values for the dichotomies used to fit the model.
Bug fixes
find_transformation()
better detects powertransformation of the response variable.Corrected return value from
find_statistic
fornnet::multinom()
models.clean_parameters()
did not return the"clean_parameters"
class attributes for some object. This caused issued in upstream packages.Fixed issue in
model_info()
, which did not correctly detect “Bernoulli” property for some models classes (likeglmmTMB
orglmerMod
).
insight 0.19.5
CRAN release: 20230913
Bug fixes
 Fixed critical issue with
check_if_installed()
for old R releases.
insight 0.19.4
CRAN release: 20230910
Changes to functions
get_predicted()
now acceptspredict = "link"
for gaussian models with loglink (i.e.glm(..., family = gaussian("log"))
), to return predictions on the link scale.check_if_installed()
now automatically checks the package DESCRIPTION file to determine the correct minimum version required.
Bug fixes
Fixed issue with invalid multibyte strings in
trim_ws()
.Fixed issue in
find_statistic()
for models from package fixest.
insight 0.19.3
CRAN release: 20230629
Breaking changes

standardize_column_order()
has changed the position when reordering Bayes factors, ROPEs and ESS / Rhat (mainly relevant for Bayesian models).
Changes to functions
standardize_names()
andstandardize_column_order()
now also recognize the"response.level"
column name.get_data()
for lavaan models is now more stable at retrieving model data when this is not available in the environment.find_terms()
gets anas_term_labels
argument, to extract model terms from the formula’s"term.labels"
attribute. This is closer to the behaviour ofstats::terms()
, but may be insufficient, e.g. for mixed models.
Bug fixes
get_random()
now returns the same observations asget_data()
and correctly removes missing values from the data before returning it.find_parameters()
for marginal effects ignores the"s.value"
column (which was added in a recent update).Fixed issue in
get_response()
for brms models withtrunc()
function in the response variable.
insight 0.19.2
CRAN release: 20230523
Breaking changes
The minimum needed R version has been bumped to
3.6
.download_model()
no longer errors when a model object could not be downloaded, but instead returnsNULL
. This prevents test failures, and allows to skip tests when the return value ofdownload_model()
isNULL
.
General
 Improved support for
mclogit
models (package mclogit) andmipo
objects (package mice) for models with ordinal or categorical response.
Bug fixes
Fixed issue in
get_variance()
for glmmTMB models with rank deficient coefficients.Fixed issues in
get_weights()
forglm
models without weights andna.action
not set to default in the model call.clean_names()
now also removes therelevel()
pattern.Fixed issue in
model_info()
for models of classgamlss
.Fixed problems preventing
get_data()
from locating data defined in nonglobal environments.Fixed issue in
get_predicted()
for variables of class numeric matrix created byscale()
, which were correctly handled only whenget_data()
failed to find the data in the appropriate environment.Fixed issue in
model_info()
forgee
models frombinomial
families.
insight 0.19.1
CRAN release: 20230318
Changes to functions
Minor improvements to
get_data()
fort.test()
.format_value()
gets alead_zero
argument, to keep or drop the leading zero of a formatted value, as well as argumentsstyle_positive
andstyle_negative
to style positive or negative numbers.format_table()
now also formats columns namedSGPV
(second generation pvalues) as pvalues.Functions for models of class
clm
(likefind_formula()
,find_variables()
,get_data()
etc.) now also include variables that were defined asscale
ornominal
component.
Bug fixes
Fixed issue in
get_data()
for results fromkruskal.test()
.Fixed issue in
find_weights()
for models of classlme
andgls
.Fixed issue in
get_datagrid()
for models with multiple weight variables.
insight 0.19.0
CRAN release: 20230130
Breaking changes

get_data()
was revised and now always tries to recover the data that was used to fit a model from the environment. If this fails, it falls back to recovering data from the model frame (the former default behaviour). Furthermore, thesource
argument can be used to explicitly force the old behaviour:source = "mf"
will try to recover data from the model frame first, then possibly falling back to look in the environment.
New functions

n_grouplevels()
, to return random effect groups and number of group levels for mixed models.
Changes to functions

get_datagrid()
preserves all factor levels for factors that are hold constant at their reference level. This is required to work together withget_modelmatrix()
when calculating standard errors forget_predicted()
.
Bug fixes
Fixed but in
get_modelmatrix()
handling of incomplete factors which sometimes had downstream implications for numerical results in the uncertainty estimates produced byget_predicted()
.Fixed minor issues for HTML tables in
export_table()
when model parameters were grouped.Fixed issue with incorrect backtransforming in
get_data()
for models with logtransformed variables.Fixes issue in
compact_list()
.has_single_value()
now returnsFALSE
when the object only hasNA
andna.rm = TRUE
.Fixed issue in
get_parameters()
for gammodels without smooth terms, or with only smooth terms and removed intercept.
insight 0.18.7
CRAN release: 20221118
General
Minor revisions to
get_predicted.glmmTMB()
due to changes in behaviour ofpredict.glmmTMB()
for truncatedfamily models since glmmTMB 1.1.5.New function
has_single_value()
that is equivalent tolength(unique()) == 1
(orn_unique() == 1
) but faster.
Changes to functions

ellipses_info()
now includes an attribute$is_binomial
, which isTRUE
for each model from binomial family.
Bug fixes
Fixed behaviour of the
at
argument inget_datagrid()
.Fixed issue for accessing model data in
get_datagrid()
for some edge cases.
insight 0.18.6
CRAN release: 20221023
New supported models
 Support the logitr package:
get_data()
,find_variables()
and more.
Bug fixes
Better detection of unicodesupport, to avoid failures when building vignettes.
get_predicted()
now correctly handles variables of class numeric matrix created byscale()
, which fixes a bug inperformance::check_model()
(easystats/performance#432).Fixed issue with
iterations
argument inget_predicted()
with brms models.
insight 0.18.5
CRAN release: 20221012
Breaking

get_df(type = "satterthwaite")
forlmerMod
objects now return degrees of freedom per parameter, and no longer per observation. Usedf_per_obs TRUE
to return degrees of freedom per observation.
New functions

safe_deparse_symbol()
to only deparses a substituted expressions when possible,which increases performance in case many calls todeparse(substitute())
.
Changes to functions
format_table()
gets ause_symbols
argument. IfTRUE
, column names that refer to particular effectsizes (like Phi, Omega or Epsilon) include the related unicodecharacter instead of the written name. This only works on Windows for R >= 4.2, and on OS X or Linux for R >= 4.0.The
stars
argument informat_table()
can now also be a character vector, naming the columns that should include stars for significant values. This is especially useful for Bayesian models, where we might have multiple columns with significant values, e.g."BF"
for the Bayes factor or"pd"
for the probability of direction.get_df()
gets moretype
options to return different type of degrees of freedom (namely,"wald"
and"normal"
, and for mixed models,"ml1"
,"betwithin"
,"satterthwaite"
and"kenwardroger"
).standardize_names()
now recognized more classes from package marginaleffects.Minor improvements to
find_parameters()
for models with nonlinear formula.Minor speed improvements.
Bug fixes
Fixed issue in
get_data()
for models of classplm
, which accidentally converted factors into character vectors.Fixed issue with column alignment in
export_table()
when the data frame to print contained unicodecharacters longer than 1 byte.Correctly extract predictors for
fixest::i(f1, i.f2)
interactions (#649 by @grantmcdermott).
insight 0.18.4
CRAN release: 20220920
Changes to functions

model_info()
now includes information forhtest
objects fromshapiro.test()
andbartlett.test()
(will return$is_variancetest = TRUE
).
Bug fixes
Fixed issue in
get_data()
which did not correctly backtransform to original data when terms had logtransformations such aslog(1 + x)
orlog(x + 1)
.Fixed CRAN check issues.
insight 0.18.3
CRAN release: 20220918
New functions

format_alert()
,format_warning()
andformat_error()
, as convenient wrappers aroundmessage()
,warning()
orstop()
in combination withformat_message()
. You can use these funcionts to format messages, warnings or errors.
Changes to functions
get_predicted()
for models of classclm
now includes confidence intervals of predictions.format_message()
gets some additional formatting features. See ‘Details’ in?format_message
for more information and some current limitations.format_message()
gets anindent
argument, to specify indention string for subsequent lines.format_table()
now merges IC and IC weights columns into one column (e.g., former columns"AIC"
and"AIC_wt"
will now be printed as one column, named"AIC (weights)"
). Furthermore, anic_digits
argument was added to control the number of significant digits for the IC values.print_color()
andcolor_text()
now support bright variants of colors and background colors.get_datagrid()
gets more options forat
andrange
, to provide more control how to generate the reference grid.get_data()
for models of classgeeglm
andfixest
now more reliably retrieves the model data.
Bug fixes
Fixed issues with wrong attribute
adjusted_for
ininsight::get_datagrid()
.Fixed issue (resp. implemented workaround) in
get_data.iv_robust()
, which failed due to a bug in the estimatr package.Fixed issue where
get_predicted()
failed when data contains factors with only one or incomplete levels.Fixed issue in
get_predicted()
for models of classmlm
.Fixed issue where
get_predicted()
failed to compute confidence intervals of predictions when model contained matrixalike response columns, e.g. a response variable created withcbind()
.
insight 0.18.2
CRAN release: 20220810
New functions
format_percent()
as shortcut forformat_value(as_percent = TRUE)
.is_converged()
, to check whether a mixed model has converged or not.
Changes to functions
format_table()
gains anexact
argument, to either report exact or rounded Bayes factors.get_predicted()
gets a method for models of classgamlss
(and thereby,get_loglikelihood()
now also works for those model classes).get_predicted()
now better handles models of classpolr
,multinom
andrlm
.
insight 0.18.0
CRAN release: 20220705
Breaking changes
The
ci
argument inget_predicted()
now defaults toNULL
. One reason was to make the function faster if confidence intervals are not required, which was the case for many downstream usages of that function. Please setci
explicitly to compute confidence intervals for predictions.get_data()
no longer returns logical types for numeric variables that have been converted to logicals onthefly within formulas (likey ~ as.logical(x)
). Instead, for each numeric variable that was coerced to logical within a formula gets alogical
attribute (set toTRUE
), and the returned data frame gets alogicals
attribute including all names of affected variables.parameters_table()
, the alias forformat_table()
, was removed.
Changes to functions

find_transformation()
andget_transformation()
now also work for models where the response was transformed usinglog2()
orlog10()
.
Bug fixes
get_sigma()
for models from package VGAM returned wrong sigmaparameter.find_predictors()
for models from package fixest that contained interaction terms in the endogenous formula part did not correctly return all instruments.Fixed formatting of HTML table footers in
export_table()
.Several fixes to
get_predicted()
for models frommgcv::gam()
.The
component
argument infind_parameters()
forstanmvreg
models did not accept the"location"
value.null_model()
did not consider offsetterms if these were specified inside formulas.Argument
allow.new.levels
was not passed topredict()
forget_predicted.glmmTMB()
.clean_names()
now works correctly when several variables are specified ins()
(#573, @etiennebacher).
insight 0.17.1
CRAN release: 20220513
New supported model classes

deltaMethod
(car),marginaleffects
,marginaleffects.summary
(marginaleffects)
General
get_predicted()
now supports models of classiv_robust
andivreg
.For
get_predicted()
, when bothtype
andpredict
are given,type
will overwritepredict
. Note that this will print a message, becausepredict
is the preferred argument.get_varcov()
gainsvcov
andvcov_args
arguments, to specify the variancecovariance matrix used to compute uncertainty estimates (e.g., for robust standard errors).get_loglikehood()
improved handling of models from package estimator.
Bug fixes
Fixed bug in
get_data()
for model objects whose data needs to be recovered from the environment, and where the data name was a reserved word (e.g., named like an R function).The matrix returned by
get_varcov()
for models of class bife now returns row and column names.find_offset()
did not find offsetterms formerMod
objects when the offset was specified asoffset
argument in the function call.
insight 0.17.0
CRAN release: 20220329
Breaking changes
 Arguments
vcov_estimation
andvcov_type
inget_predicted()
,get_predicted_se()
andget_predicted_ci()
are replaced byvcov
andvcov_args
, to have a more simplified and common interface to control robust covariance matrix estimation.
General
 Improved performance for various functions, in particular
get_data()
andmodel_info()
.
New functions
To check for names:
object_has_names()
andobject_has_rownames()
To work with lists:
is_empty_object()
andcompact_list()
To work with strings:
compact_character()
Further utility functions are
safe_deparse()
,trim_ws()
andn_unique()
.
Changes to functions
export_table()
now better checks for invalid values of caption and footer for tables in HTML format, and silently removes, e.g., ansicolour codes that only work for textformat.get_data.coxph()
returns the original data frame instead of data with type coercion.get_loglikelihood()
gets acheck_response
argument, to check if a model has a transformed response variable (likelog()
orsqrt()
transformation), and if so, returns a corrected loglikelihood.get_modelmatrix()
now supports BayesFactor models.get_loglikelihood()
andget_df()
now support more model classes.get_predicted()
was improved for multinomial models from brms.get_variance()
was improved to cover more edge cases of (more complex) random effect structures.get_data()
now includes variables in the returned data frame that were used in thesubset
argument of regression functions (likelm()
).In some edge cases, where
get_data()
is unable to retrieve the data that was used to fit the model, now a more informative error is printed.ellipses_info()
now also accepts a list of model objects, is more stable and returns more information about the provided models (like if all fixed or random effects are the same across models, if all models are mixed models or nullmodels, etc.)check_if_installed()
now works interactively and lets the user prompt whether to automatically update or install packages.
Bug fixes
Fixed incorrect column name conversion in
standardize_names()
for certain columns returned bybroom::glance()
.Fixed issue with correctly detecting Tweediemodels in
model_info()
.Fixed issue with
get_datagrid()
for brms models with monotonic factors.Fixed issue in
find_formula()
when argumentcorrelation
was defined outside oflme()
andgls()
(@etiennebacher, #525).Fixed issue with
get_data()
when backtransforming data from predictors that usedcos()
,sin()
ortan()
transformations.
insight 0.16.0
CRAN release: 20220216
New functions

get_datagrid()
, to generate a reference grid, usually used when computing adjusted predictions or marginal means from regression models.
Changes to functions
get_predicted()
get_predicted()
was revised. Beside the four core options for thepredict
argument, it is now also possible to use any value that is valid for the model’spredict()
method’stype
argument.get_predicted()
now supports more models (e.g., from packages like GLMMadaptive or survival).get_predicted()
is now more robust when calculating standard errors of predictions.
Other functions

get_statistic()
andfind_statistic()
now support htest objects.
insight 0.15.1
General
 Improved speed performance, especially for
get_data()
.
Changes to functions

get_data()
forcoxph
models now returns the original factor levels for variables transformed withstrata()
inside formulas.
insight 0.15.0
CRAN release: 20220107
Breaking changes
Data management functions (like
reshape_longer()
, ordata_match()
) have been moved to the datawizard package.get_data()
no longer returns factor types for numeric variables that have been converted to factors onthefly within formulas (likey ~ as.factor(x)
). Instead, for each numeric variable that was coerced to factor within a formula gets afactor
attribute (set toTRUE
), and the returned data frame gets afactors
attribute including all names of affected variables.
New functions
 New
standardize_column_order()
function can be used to standardize the column order in output dataframes.
General
Improved speed performance for some functions.
Improved handling of table captions and footers in
export_table()
. See also the new vignette on exporting data frames into human readable tables here: https://easystats.github.io/insight/articles/export.htmlRevised
width
argument inexport_table()
, which now allows to set different column widths across table columns. See examples in?export_table
.export_table()
gets atable_width
argument to split wide tables into two parts.get_varcov()
forMixMod
(package GLMMadaptive) was revised, and now allows to return a robust variancecovariance matrix.Added more
get_df()
methods.
Bug fixes
Fixed issues with manual sigma computation to handle dispersion models in
get_sigma()
.Fixed issue in
find_formula()
forBayesFactor::lmBF()
with multiple random effects.Fixed issue in
get_parameters.BFBayesFactor()
with wrong sign of difference estimate for ttests.Argument
width
informat_value()
was ignored when formatting integer values andprotect_integers
was set toTRUE
.
insight 0.14.5
CRAN release: 20211016
New functions

find_transformation()
andget_transformation()
to find or get any function that was used to transform the response variable in a regression model.
General
Improved support for models of class
sampleSelection
.Improved documentation.
get_modelmatrix()
now supports:rms::lrm
get_predicted()
supports:MASS::polr
,MASS::rlm
,rms::lrm
,fixest
,bife::bife
,ordinal::clm
.get_predicted()
standard errors are often much faster to compute.get_predicted()
supports models with “grouped” or “level” outcomes (e.g., multinomial logit).get_predicted()
handles factors better.Improved documentation
Changes to functions
check_if_installed()
gains aquietly
argument, if neither stopping nor a warning message for noninstalled packages is requested.get_predicted()
’spredict
argument now accepts these values: “link”, “expectation”, “prediction”, “classification”, or NULL.get_predicted()
acceptspredict=NULL
, which allows users to push atype
argument through the...
ellipsis, forward to thepredict()
method of the modelling package.
Bug fixes
Fixed issue with parameter names from emmeans objects in
get_parameters()
.Fixed issues with unknown arguments in
get_predicted()
.
insight 0.14.3
CRAN release: 20210817
Changes to functions
get_predicted()
gains a new option,predict = "response"
for binomial models.Improved stability of
get_variance()
when computing randomslopeintercept correlation with categorical random slopes.Improved
get_priors()
for brms models.
Bug fixes
Fixed issue in
get_data()
for brms models with auxiliary parameters.Fixed issue in
find_formula()
for brms models with auxiliary parameters.Fixed issue where
get_data()
for htest objects did not always preserve factors.Fixed issue in
format_table()
for cilevels with longer fractional part.
insight 0.14.2
CRAN release: 20210622
Changes to functions
check_if_installed()
gains aminimum_version
argument, to check if an installed package is not older than the specified version number.The
package
argument incheck_if_installed()
is now vectorized, so you can check for multiple packages in one function call.Value formatting functions (like
format_value()
orformat_ci()
) can now round to significant digits usingdigits = "signif"
.
Bug fixes
Fixed issue in
model_info()
withstan_polr()
models.Fixed issue in
find_parameters()
for brms when model contained parameters for the priors on sigma.Fixed issue in
n_obs()
forstats4::mle()
models.Fixed failing tests due to latest fixest update.
Fixed issues due to latest epiR update.
insight 0.14.1
CRAN release: 20210528
New functions
 Added several data management and preparation functions:
data_to_long()
,data_match()
,data_relocate()
,data_restoretype()
,force_numeric()
.
Bug fixes
Stability improvements to
get_predicted()
.Fixed issues when accessing information from an
afex_aov
model with an emptyaov
slot (in anticipation for afex v.1.0.0).Fixed issue in
model_info()
for stanreg object with nonstandard modelfamily specification.
insight 0.14.0
CRAN release: 20210507
General
 Better support for accessing auxiliary parameters (via
get_sigma()
andget_auxiliary()
, as well asget_parameters(component = "all")
) forbrmsfit
models.
New functions
get_modelmatrix()
as a robust alternative tomodel.matrix()
for different model classes.format_message()
to format warnings and messages by adjusting the maximum line_length, possibly to the width of the console window.format_string()
to shorten a string to a maximum length.check_if_installed()
to see if the needed package is installed.
New supported model classes
 Support for
mvord
(mvord),SemiParBIV
(GJRM),selection
(sampleSelection)
Changes to functions
find_formula()
now warns when data name is present in formula, since this can result in unexpected behaviour in other package functions.model_info()
returnsis_bernoulli = TRUE
for Bernoulli models.Add
get_statistic()
for lavaan models.get_df()
supports more models/objects.get_sigma()
supports more models/objects.get_sigma()
andget_deviance()
forlrm
models (package rms) now only return one value, sigma or deviance for the model with intercept and predictors.get_deviance()
now works forglmerMod
,MixMod
andglmmTMB
models.The behaviour and documentation of the
effects
andcomponent
arguments, in particular forbrmsfit
models, were revised to be more consistent.export_table()
now correctly prints the footer if the input was a list of data frames.
Bug fixes
Fixed issue (warning) in
get_loglikelihood()
for binomial models with nonnumeric response variables.find_statistic()
correctly distinguishes t and zstatistic for emmGrid objects.Fixed issue in
model_info()
forBGGM
andmgcv::gam()
.Fixed issue in
find_formula()
forgamlss
models withrandom()
function in formula.Fixed issue with
find_parameters()
for brmsfit models when auxiliary parameters are directly modelled.Fixed issue with
get_parameters()
andfind_parameters()
for multigroup blavaan models.Fixed issue in
ellipsis_info()
when detecting nested models with polyterms.Fixed issue in
find_response()
for brmsfit models that used theresp_thres()
function in the model formula.Fixed issue in
get_predicted_ci()
for models with rankdeficient model matrix.Argument
zap_small
informat_value()
did not work properly over vectorized vectors.
insight 0.13.2
CRAN release: 20210401
General
get_predicted()
has be revamped with a new API and a stable output form (a vector). In the course of this revision, a new functionget_predicted_ci()
to calculate uncertainty intervals for model predictions.Improved support for
orm
(rms).
New supported model classes
 Support for
svy_vglm
(svyVGAM),mjoint
(joineRML),mhurdle
(mhurdle),sarlm
(spatialreg),model_fit
(tidymodels)
New functions

is_gam_model()
as a small helper to check if a model is a generalized additive model with smooth terms.
Changes to functions
Added
iterations
argument toget_predicted()
to control the number of draws returned for Bayesian models.model_info()
now returns$is_gam
if model is generalized additive model with smooth terms.format_table()
andexport_table()
now check for valid input (e.g., nonempty data frame) and give an informative message.Improved support for
MixMod
(GLMMadaptive) inget_variance()
.Improved
print_parameters()
, to allow more flexibility and better cope with different output formats.get_parameters()
,find_parameters()
andclean_parameters()
for emmGrid and emm_list objects were revised and now better match the actual parameter names (also for contrasts).
Bug fixes
Fixed issue in
get_variance()
for models without intercept.Fixed labelling issue in
get_parameters()
andclean_parameters()
forblavaan
models.clean_parameters()
for MCMCglmm objects did not include random parameters.Fixed minor issue with unintended subtitles for
print_html()
.Fixed issue in
get_prior()
forrstanarm::R2()
priors.
insight 0.13.1
CRAN release: 20210222
Changes to functions
get_residuals(..., weighted = TRUE)
doesn’t throw warnings if weights are 1 (no weights specified).n_parameters()
gains aonly_estimable
argument, to remove nonestimable parameters from counting the number of parameters for models with rankdeficient model matrix.format_ci()
also gains azap_small
argument.
Bug fixed
Fix or disable failing tests on Mac OS.
Fixed issues in
get_variance()
with noncorrelated randomslopeintercepts for lme4 models.
insight 0.13.0
CRAN release: 20210215
New supported model classes
 Support for
crr
(cmprsk),ergm
(ergm),btergm
(btergm),Rchoice
(Rchoice),garch
(tseries)
Changes to functions
Slightly improved handling of different CIcolumns in
format_table()
.model_info()
now returns$is_leventest
if model is an object returned bycar::leveneTest()
.get_parameters()
supportshtest
objects.
Bug fixes
get_varcov()
did not properly removeNA
from rankdeficient models.Fixed issue/warning in
get_data()
for some htest objects, where the environment was not properly evaluated.Fixed issue in
format_table()
with pvalue formatting, when input data frame contained a column named"p"
, which was not numeric.(Hopefully) fixed issue with failing CRAN checks.
insight 0.12.0
CRAN release: 20210114
Breaking changes

format_table()
is an alias forparameters_table()
, and is no longer referring toexport_table()
.
New supported model classes
 Support for
coxr
(coxrobust),coeftest
(lmtest),ivFixed
(ivFixed),ivprobit
(ivprobit),riskRegression
(riskRegression).summary.lm
,lmodel2
(lmodel2), improved support forbamlss
(bamlss).
New functions
Added
get_deviance()
function that returns the model deviance as a robust alternative tostats::deviance()
.Added
model_name()
function that returns the model’s “name”.Added
format()
method forfind_formula()
output to flatten it.Added
null_as_ones = TRUE
argument toget_weights()
to return vector of 1s instead ofNULL
.Added
get_intercept()
as a helper function to easily retrieve the value at the intercept.Added
get_df()
as a robust alternative tostats::df.residuals()
.Added
get_predicted()
as a robust alternative tostats::fitted()
.Added
get_loglikelihood()
(and its aliasloglikelihood()
) function as a robust alternative tostats::logLik()
.Added
get_residuals()
as a robust alternative extract model residuals.Added
ellipsis_info()
to specify the nature of ellipsis (...
) inputs.Added
is_nested_models()
to check if multiple regression models are nested (decreasing or increasing).Added generic
print_html()
, to allow other packages to create tables in HTML format (viaexport_table()
) when not printing the output to console.Added
is_mixed_model()
, to safely check if a model is a mixed effects model. This function also works for multivariate response models.n_parameters()
was moved from parameters to insight.
Changes to functions
find_formula()
,find_predictor()
,find_random()
and related functions now also return names of random effects from generalized additive mixed models (gamm
,gamm4
,stan_gamm4
).Added support for more BFBayesFactor objects.
model_info()
now returns$is_xtab
forchisq.test()
andBayesFactor::contingencyTableBF()
. Furthermore, the$family
element for those objects is set to"categorical"
.n_obs()
now handles number of observations from models with binomial family correctly when these have matrixcolumns as response variable.
Bug fixes
Fixed issue in
find_statistic()
for fixest models, which did not return the correct value"tstatistic"
forfeols()
.Fixes inconsistencies in
get_priors()
for (linear)BFBayesFactor
models.
insight 0.11.1
CRAN release: 20201208
General
 Warnings that formerly were printed using
print_color()
now usewarning()
, to better suppress warning messages if required.
New functions

find_smooth()
, to return in particular smooth terms used in a model.
Changes to functions
get_variance()
andget_variance_random()
gain atolerance
argument, to set the tolerance level for singularity checks when computing random effect variances.parameters_table()
formats more objects from the easystats packages, like ROPErange orp_rope()
.find_statistic()
now supports models of class scam.get_data()
now also supportshtest
object, where possible.
Bug fixes
Fix CRAN check issues.
find_formula()
forstan_gamm4()
now correctly includes random effects.
insight 0.11.0
CRAN release: 20201124
Breaking changes
model_info()
now also detects models fromoneway.test()
,binom.test()
chisq.test()
,mcnemar.test()
andprop.test()
. Furthermore,model_info()
better deals with objects fromBFBayesFactor
, and censored regression models no longer returnTRUE
for$is_linear
.format_table()
is going to be renamed in a future update. Please use its aliasexport_table()
.
New supported model classes
 Support for
scam
(scam),meta_random
andmeta_fixed
(metaBMA),Glm
(rms),ridgelm
(MASS),mediate
(mediation). Partial support formcmc.list
(e.g. bayesGARCH)
New function
parameters_table()
, which was moved from package parameters to insight. Note that this function is going to be renamed intoformat_table()
in a future update.find_offset()
, to find the name of offsetterms.Added generics for
display()
andprint_md()
, to allow other packages to create tables in other formats when not printing the output to console.
Changes to functions
standardize_names()
tries to be as loyal to the broomnaming conventions as possible.The function of the
brackets
argument informat_ci()
was changed. It is now also possible to provide a lengthtwo character vector, to define own brackets that encompass the CIvalues.Related to the change in
format_ci()
, the function of thebrackets
argument inparameters_table()
was changed accordingly. Furthermore,parameters_table()
gains apreserve_attributes
argument, to preserve any attributes from the input data frame.export_table()
gains several new arguments that allows to create tables in markdownformat.print_parameters()
gains akeep_parameter_column
argument, to keep (default) both the"Cleaned_Parameter"
and"Parameter"
columns, or  ifFALSE
 use"Cleaned_Parameter"
as new"Parameter"
column.
Bug fixes
get_data()
Fixed issue in
get_data()
forMixMod
objects, which were caused due to internal changes in GLMMadaptive.get_data()
for zeroinflated models from pscl did not include the offsetterm in cases where the offset was defined as argument, not inside the model formula.Fixed issue in
get_data()
forcoxph
models with survivalobjects withevent
argument as response.Fixed edge case in
get_data()
for column name of response values that were logtransformed usinglog(x+1)
.
insight 0.10.0
CRAN release: 20201022
New function
get_sigma()
to return the residual standard deviation.standardize_names()
, which was moved from package parameters to insight.
New supported model classes
 Support for
maov
(stats),HLfit
(spaMM), preliminary support formargins
(margins),merModList
(merTools).
General
Better support for (weighted) multivariate response models of class
mlm
for functions likeget_varcov()
orclean_parameters()
.Make
find_formula()
work with ttests from BayesFactor.Improved handling for mira objects.
Changes to functions
format_bf()
gains ana_reference
argument, to set the “reference” for Bayes factor values that areNA
, and anexact
argument for returning scientific formatted extreme values.format_value()
gains azap_small
argument, to prevent scientific printing of numbers if these have more decimal places than indicated bydigits
.get_weights()
now also returnsNULL
when all weights were 1.get_parameters()
for BFBayesFactor objects gets averbose
argument.get_parameters()
for emmGrid and emm_list objects gets asummary
argument, to either return the full posterior samples or the summarized centrality indices for Bayesian models.find_formula()
forMuMIn::model.avg()
now tries to retrieve the random effects part of a formula, when present.get_weights()
gains ana_rm
argument to remove possible missing values.
Bug fixes
Fix issues with onesample Bayesian ttests ( https://github.com/easystats/parameters/issues/297 ).
Fix issue in
format_value()
that printed"100%"
as"1e+02%"
.Removed unnecessary whitespaces in
format_ci()
when upper or lower interval was larger than 1e+5.has_intercept()
did not work correctly when intercept was removed from formula using1
.find_terms()
now shows removal of intercept formula using1
as term"1"
.Fix issues with
get_statistic()
for vgam models.
insight 0.9.6
CRAN release: 20200920
Changes to functions
get_data()
now works for models fromafex_aov()
.get_parameters()
returns a more informative message forBFBayesFactor
objects when not the first model is indexed.clean_names()
now also removesexp()
pattern.clean_names()
for characterobjects now works with “interaction patterns” (likeclean_names("scale(a):scale(b)")
).format_bf()
gains aprotect_ratio
argument, to print numbers smaller than 1 as ratios.
Bug fixes
Fix issues in CRAN checks.
get_priors()
now works for more complexBFBayesFactor
objects that have multiple custom priors.
insight 0.9.5
CRAN release: 20200907
Breaking changes

get_data()
did not always “backtransform” logtransformed or scaled variables to return the original values. Now this bug has been fixed, andget_data()
should return all variables on the original scale (as if these variables were not transformed), as stated in the docs.
Bug fixes
get_data()
now returns the correct original data for “empty” polynomials (i.e.poly(x, 1)
).Fix CRAN check issues due to latest estimatr update.
insight 0.9.1
CRAN release: 20200826
New supported model classes
 Support for
mipo
(mice),lqmm
andlqm
(lqmm). Preliminary support forsemLME
(smicd),mle
(stats4) andmle2
(bbmle).
Changes to functions
model_info()
returns$is_meta = TRUE
for brmsmetaanalysis models.Make
find_statistic()
work withmgcv::bam()
.get_variance()
now also supporttruncated_nbinom2()
family from glmmTMB.
Bug fixes
Fixed issue with correctly detecting sigmaparameters in
find_parameters()
for multipleresponsebrmsfit
models.Fixed issue with
find_formula()
for models fromstan_nlmer()
.Fixed issues with
find_terms()
when response variable included a namespace, likesurvival::Surv()
.Fixed issues with
get_priors()
for stanreg models, probably caused by the latest update to rstanarm 2.21.2.Fixed issues in
get_variance()
for brmsfit models.Fixed some issues around
crq
objects (package quantreg).
insight 0.9.0
CRAN release: 20200720
New supported model classes

BGGM
(BGGM),metaplus
(metaplus),glht
(multcomp),glmm
(glmm), improved support formanova
(stats)
New functions
 Value formatting functions
format_bf()
,format_pd()
,format_p()
,format_rope()
andformat_number()
were moved from package parameters to insight.
Changes to functions
get_variance()
now also returns the correlation among random slopes.get_variance()
now also (partially) supportsbrmsfit
models.get_parameters()
for models that return (posterior or simulated) samples of model parameters gains asummary
argument, which  ifTRUE
 returns a pointestimate (mean of samples) instead of the full samples.format_p()
returns"> .999"
for pvalues equal to or greater than 0.999.
Bug fixes
Fixed issue in
find_formula()
that did not properly work for models with random effects in formula (in lme4 notation), when random effects were in between fixed effects parts.get_variance()
did not return variance components for random effects for nullmodels with random slopes.Fixed issue with
get_variance()
forlme
models with categorical random slope.Fixed issue that occurred since R 4.0.0 in
find_weights()
when function call had noweights
argument.Fixed issue in
get_data()
for models withcbind()
response variables and matrixlike variables in the model frame (e.g. when usingpoly()
).Fixed issues with
PROreg::BBmm()
, due to changes in latest package update.