diff --git a/DESCRIPTION b/DESCRIPTION
index 2b7fe815a..abac13053 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: performance
 Title: Assessment of Regression Models Performance
-Version: 0.12.4.1
+Version: 0.12.4.2
 Authors@R:
     c(person(given = "Daniel",
              family = "Lüdecke",
@@ -95,7 +95,7 @@ Suggests:
     cplm,
     dagitty,
     dbscan,
-    DHARMa,
+    DHARMa (>= 0.4.7),
     estimatr,
     fixest,
     flextable,
@@ -129,7 +129,7 @@ Suggests:
     nonnest2,
     ordinal,
     parallel,
-    parameters (>= 0.21.6),
+    parameters (>= 0.22.0),
     patchwork,
     pscl,
     psych,
diff --git a/NAMESPACE b/NAMESPACE
index 08f6bcc15..d35d82547 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -566,7 +566,6 @@ export(check_multimodal)
 export(check_normality)
 export(check_outliers)
 export(check_overdispersion)
-export(check_posterior_predictions)
 export(check_predictions)
 export(check_residuals)
 export(check_singularity)
@@ -602,7 +601,6 @@ export(performance_rmse)
 export(performance_roc)
 export(performance_rse)
 export(performance_score)
-export(posterior_predictive_check)
 export(print_html)
 export(print_md)
 export(r2)
diff --git a/NEWS.md b/NEWS.md
index 4f0984b48..9eb5ded26 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,13 @@
+# performance 0.12.5
+
+## Breaking changes
+
+* Deprecated arguments and alias-function-names have been removed.
+
+## Changes
+
+* Increased accuracy for `check_convergence()` for *glmmTMB* models.
+
 # performance 0.12.4
 
 ## Changes
diff --git a/R/check_convergence.R b/R/check_convergence.R
index 6f7628a12..f60a7e298 100644
--- a/R/check_convergence.R
+++ b/R/check_convergence.R
@@ -98,9 +98,10 @@ check_convergence.merMod <- function(x, tolerance = 0.001, ...) {
 
 
 #' @export
-check_convergence.glmmTMB <- function(x, ...) {
+check_convergence.glmmTMB <- function(x, tolerance = 0.001, ...) {
   # https://github.com/glmmTMB/glmmTMB/issues/275
-  isTRUE(x$sdr$pdHess)
+  # https://stackoverflow.com/q/79110546/2094622
+  isTRUE(all.equal(x$fit$convergence, 0, tolerance = tolerance)) && isTRUE(x$sdr$pdHess)
 }
 
 
diff --git a/R/check_heterogeneity_bias.R b/R/check_heterogeneity_bias.R
index 755f47dfa..2414873cc 100644
--- a/R/check_heterogeneity_bias.R
+++ b/R/check_heterogeneity_bias.R
@@ -27,7 +27,6 @@
 #' @param nested Logical, if `TRUE`, the data is treated as nested. If `FALSE`,
 #'   the data is treated as cross-classified. Only applies if `by` contains more
 #'   than one variable.
-#' @param group Deprecated. Use `by` instead.
 #'
 #' @seealso
 #' For further details, read the vignette
@@ -44,15 +43,9 @@
 #' iris$ID <- sample(1:4, nrow(iris), replace = TRUE) # fake-ID
 #' check_heterogeneity_bias(iris, select = c("Sepal.Length", "Petal.Length"), by = "ID")
 #' @export
-check_heterogeneity_bias <- function(x, select = NULL, by = NULL, nested = FALSE, group = NULL) {
+check_heterogeneity_bias <- function(x, select = NULL, by = NULL, nested = FALSE) {
   insight::check_if_installed("datawizard", minimum_version = "0.12.0")
 
-  ## TODO: deprecate later
-  if (!is.null(group)) {
-    insight::format_warning("Argument `group` is deprecated and will be removed in a future release. Please use `by` instead.") # nolint
-    by <- group
-  }
-
   if (insight::is_model(x)) {
     by <- insight::find_random(x, split_nested = TRUE, flatten = TRUE)
     if (is.null(by)) {
diff --git a/R/check_predictions.R b/R/check_predictions.R
index fbc3b5eaf..c903f4309 100644
--- a/R/check_predictions.R
+++ b/R/check_predictions.R
@@ -423,26 +423,6 @@ pp_check.glmmTMB   <-
 #' S3method(bayesplot::pp_check, BFBayesFactor)
 
 
-
-# aliases --------------------------
-
-#' @rdname check_predictions
-#' @export
-posterior_predictive_check <- function(object, ...) {
-  .Deprecated("check_predictions()")
-  check_predictions(object, ...)
-}
-
-#' @rdname check_predictions
-#' @export
-check_posterior_predictions <- function(object, ...) {
-  .Deprecated("check_predictions()")
-  check_predictions(object, ...)
-}
-
-
-
-
 # methods -----------------------
 
 
diff --git a/R/performance_aicc.R b/R/performance_aicc.R
index eb10bc40f..74041ac1b 100644
--- a/R/performance_aicc.R
+++ b/R/performance_aicc.R
@@ -28,7 +28,7 @@
 #' scale. To get back to the original scale, the likelihood of the model is
 #' multiplied by the Jacobian/derivative of the transformation.
 #'
-#' In case it is not possible to return the corrected AIC value, a waring
+#' In case it is not possible to return the corrected AIC value, a warning
 #' is given that the corrected log-likelihood value could not be computed.
 #'
 #' @references
diff --git a/R/simulate_residuals.R b/R/simulate_residuals.R
index 7312c196f..1f58218c0 100644
--- a/R/simulate_residuals.R
+++ b/R/simulate_residuals.R
@@ -65,9 +65,10 @@
 #' @export
 simulate_residuals <- function(x, iterations = 250, ...) {
   insight::check_if_installed("DHARMa")
-  # TODO (low priority): Note that DHARMa::simulateResiduals(x, ...) does its own checks for whether
-  # or not the model passed to it is supported, do we want to use this or do our
-  # own checks so we can supply our own error message?
+  # TODO (low priority): Note that DHARMa::simulateResiduals(x, ...) does its
+  # own checks for whether or not the model passed to it is supported, do we
+  # want to use this or do our own checks so we can supply our own error
+  # message?
   if (iterations < 2) {
     insight::format_error("`iterations` must be at least 2.")
   }
diff --git a/man/check_heterogeneity_bias.Rd b/man/check_heterogeneity_bias.Rd
index 40b2b66ca..db18ae7ef 100644
--- a/man/check_heterogeneity_bias.Rd
+++ b/man/check_heterogeneity_bias.Rd
@@ -4,13 +4,7 @@
 \alias{check_heterogeneity_bias}
 \title{Check model predictor for heterogeneity bias}
 \usage{
-check_heterogeneity_bias(
-  x,
-  select = NULL,
-  by = NULL,
-  nested = FALSE,
-  group = NULL
-)
+check_heterogeneity_bias(x, select = NULL, by = NULL, nested = FALSE)
 }
 \arguments{
 \item{x}{A data frame or a mixed model object.}
@@ -41,8 +35,6 @@ See also section \emph{De-meaning for cross-classified designs} and
 \item{nested}{Logical, if \code{TRUE}, the data is treated as nested. If \code{FALSE},
 the data is treated as cross-classified. Only applies if \code{by} contains more
 than one variable.}
-
-\item{group}{Deprecated. Use \code{by} instead.}
 }
 \description{
 \code{check_heterogeneity_bias()} checks if model predictors or variables may
diff --git a/man/check_predictions.Rd b/man/check_predictions.Rd
index 148df6994..6c13fc0d5 100644
--- a/man/check_predictions.Rd
+++ b/man/check_predictions.Rd
@@ -3,8 +3,6 @@
 \name{check_predictions}
 \alias{check_predictions}
 \alias{check_predictions.default}
-\alias{posterior_predictive_check}
-\alias{check_posterior_predictions}
 \title{Posterior predictive checks}
 \usage{
 check_predictions(object, ...)
@@ -19,10 +17,6 @@ check_predictions(object, ...)
   verbose = TRUE,
   ...
 )
-
-posterior_predictive_check(object, ...)
-
-check_posterior_predictions(object, ...)
 }
 \arguments{
 \item{object}{A statistical model.}
diff --git a/man/performance_aicc.Rd b/man/performance_aicc.Rd
index 529ee53aa..b1d9a1255 100644
--- a/man/performance_aicc.Rd
+++ b/man/performance_aicc.Rd
@@ -47,7 +47,7 @@ unlike \code{stats::AIC()}, returns the "corrected" AIC value on the original
 scale. To get back to the original scale, the likelihood of the model is
 multiplied by the Jacobian/derivative of the transformation.
 
-In case it is not possible to return the corrected AIC value, a waring
+In case it is not possible to return the corrected AIC value, a warning
 is given that the corrected log-likelihood value could not be computed.
 }
 \examples{
diff --git a/tests/testthat/test-check_zeroinflation.R b/tests/testthat/test-check_zeroinflation.R
index 38a5c7726..53f8af9f5 100644
--- a/tests/testthat/test-check_zeroinflation.R
+++ b/tests/testthat/test-check_zeroinflation.R
@@ -111,22 +111,22 @@ test_that("check_zeroinflation, glmmTMB nbinom", {
   skip_if_not_installed("DHARMa")
   skip_on_cran()
 
+  data(Salamanders, package = "glmmTMB")
+  m <- glmmTMB::glmmTMB(
+    count ~ spp + mined + (1 | site),
+    family = glmmTMB::nbinom1(),
+    data = Salamanders
+  )
   set.seed(1234)
-  dat <- DHARMa::createData(sampleSize = 1000)
-  fit <- suppressWarnings(glmmTMB::glmmTMB(
-    observedResponse ~ Environment1 + (1 | group),
-    data = dat,
-    family = glmmTMB::nbinom1()
-  ))
   expect_equal(
-    check_zeroinflation(fit),
+    check_zeroinflation(m),
     structure(
       list(
-        predicted.zeros = 462,
-        observed.zeros = 482L,
-        ratio = 0.95850622406639,
+        predicted.zeros = 389,
+        observed.zeros = 387L,
+        ratio = 1.00635658914729,
         tolerance = 0.1,
-        p.value = 0.776
+        p.value = 0.944
       ),
       class = "check_zi"
     ),