lintrs, spelling

R/check_overdispersion.R

@@ -303,10 +303,10 @@ check_overdispersion.performance_simres <- function(x, alternative = c("two.side
 
   # check for special arguments - we may pass "object_name" from other methods
   dots <- list(...)
-  if (!is.null(dots$object_name)) {
-    obj_name <- dots$object_name
-  } else {
+  if (is.null(dots$object_name)) {
     obj_name <- insight::safe_deparse_symbol(substitute(x))
+  } else {
+    obj_name <- dots$object_name
   }
 
   # statistics function

R/check_predictions.R

@@ -106,7 +106,7 @@ check_predictions.default <- function(object,
   minfo <- insight::model_info(object, verbose = FALSE)
 
   # try to find sensible default for "type" argument
-  suggest_dots <- (minfo$is_bernoulli || minfo$is_count || minfo$is_ordinal || minfo$is_categorical || minfo$is_multinomial)
+  suggest_dots <- (minfo$is_bernoulli || minfo$is_count || minfo$is_ordinal || minfo$is_categorical || minfo$is_multinomial) # nolint
   if (missing(type) && suggest_dots) {
     type <- "discrete_interval"
   }

R/check_residuals.R

@@ -13,7 +13,7 @@
 #'
 #' @details Uniformity of residuals is checked using a Kolmogorov-Smirnov test.
 #' There is a `plot()` method to visualize the distribution of the residuals.
-#' The test fpr uniformity basically tests to which extent the observed values
+#' The test for uniformity basically tests to which extent the observed values
 #' deviate from the model expectations (i.e. simulated values). In this sense,
 #' the `check_residuals()` function has similar goals like [`check_predictions()`].
 #'

R/simulate_residuals.R

@@ -97,15 +97,15 @@ plot.performance_simres <- function(x, ...) {
 
 .simres_statistics <- function(x, statistic_fun, alternative = "two.sided") {
   # summarize the observed and simulated residuals
-  if (!is.null(statistic_fun)) {
-    # either apply a function to observed and simulated residusls,
+  if (is.null(statistic_fun)) {
+    # we pass the values to compute the p-value directly (for "check_outliers()")
+    observed <- x
+    simulated <- statistic_fun
+  } else {
+    # or apply a function to observed and simulated residusls,
     # to calcualte a summary statistic
     observed <- statistic_fun(x$observedResponse)
     simulated <- apply(x$simulatedResponse, 2, statistic_fun)
-  } else {
-    # or we pass the values to compute the p-value directly (for "check_outliers()")
-    observed <- x
-    simulated <- statistic_fun
   }
   # p is simply ratio of simulated zeros to observed zeros
   p <- switch(alternative,