Report assumptions

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: report
 Type: Package
 Title: Automated Reporting of Results and Statistical Models
-Version: 0.6.4
+Version: 0.6.5
 Authors@R:
     c(person(given = "Dominique",
              family = "Makowski",
@@ -117,6 +117,7 @@ Collate:
     'report.stanreg.R'
     'report.brmsfit.R'
     'report.character.R'
+    'report.check_outliers.R'
     'report.compare.loo.R'
     'report.compare_performance.R'
     'report.coxph.R'
@@ -135,6 +136,7 @@ Collate:
     'report.test_performance.R'
     'report.zeroinfl.R'
     'report_ai.R'
+    'report_assumptions.R'
     'report_effectsize.R'
     'report_htest_chi2.R'
     'report_htest_cor.R'
@@ -162,3 +164,4 @@ Collate:
     'zzz.R'
 Roxygen: list(markdown = TRUE)
 Config/roxygen2/version: 8.0.0
+RoxygenNote: 7.3.3

NAMESPACE

@@ -38,6 +38,7 @@ S3method(report,bayesfactor_inclusion)
 S3method(report,bayesfactor_models)
 S3method(report,brmsfit)
 S3method(report,character)
+S3method(report,check_outliers)
 S3method(report,compare.loo)
 S3method(report,compare_performance)
 S3method(report,coxph)
@@ -247,6 +248,7 @@ S3method(report_text,bayesfactor_inclusion)
 S3method(report_text,bayesfactor_models)
 S3method(report_text,brmsfit)
 S3method(report_text,character)
+S3method(report_text,check_outliers)
 S3method(report_text,compare_performance)
 S3method(report_text,coxph)
 S3method(report_text,data.frame)
@@ -305,7 +307,7 @@ export(is.report)
 export(print_html)
 export(print_md)
 export(report)
-export(report_ai)
+export(report_assumptions)
 export(report_date)
 export(report_effectsize)
 export(report_info)

NEWS.md

@@ -1,9 +1,23 @@
 # report (devel)
 
+New features
+
+* `report_assumptions()`: new function that reports model assumption checks for a model, covering influential observations (via `performance::check_outliers()`), collinearity (via `performance::check_collinearity()`), and homoskedasticity (via `performance::check_heteroskedasticity()`). Calling `summary()` on the result returns a compact one-sentence version integrating all checks. Supports `audience = "ai"` for a compact token-efficient structured output.
+
+* `report()` / `report_text()` for linear models: assumption checks (from `report_assumptions()`) are now automatically included right after the model description (before the performance sentence). For human audience, the compact one-sentence summary is inserted there; for AI audience, a structured `## Assumptions` section is added there in the output.
+
+Bug fixes
+
+* Fixed missing `@exportS3Method` roxygen2 tags on `report_ai` S3 methods (`default`, `lm`, `glm`, `merMod`, `glmmTMB`), which caused warnings during package loading.
+
+* `report_text()`: new method for `performance::check_outliers()` output, producing a brief sentence such as "2 observations (5.88%) were detected as potential outliers based on Cook's distance (threshold = 0.806)."
+
 Bug fixes
 
 * Fixed an issue in `report()` where the reference level for logical predictors was incorrectly displayed as `[?]` instead of `FALSE` for the intercept (@M-Colley, #598).
 
+* Fixed the *AI-Optimized Reports* vignette to no longer refer to the internal `report_ai()` function; all examples now use `report(x, audience = "ai")`.
+
 # report 0.6.4
 
 New features

R/report.check_outliers.R

@@ -0,0 +1,112 @@
+#' Reporting outlier detection results
+#'
+#' Create a brief textual report for outlier detection results from
+#' [performance::check_outliers()].
+#'
+#' @param x Object of class `check_outliers` as returned by
+#'   [performance::check_outliers()].
+#' @inheritParams report
+#'
+#' @inherit report return seealso
+#'
+#' @examplesIf requireNamespace("performance", quietly = TRUE)
+#' \donttest{
+#' library(report)
+#' library(performance)
+#'
+#' mt2 <- rbind(
+#'   mtcars[, c("mpg", "disp", "hp")],
+#'   data.frame(mpg = c(37, 40), disp = c(300, 400), hp = c(110, 120))
+#' )
+#' model <- lm(disp ~ mpg + hp, data = mt2)
+#' rez <- performance::check_outliers(model)
+#' report(rez)
+#' }
+#'
+#' @return An object of class [report_text()].
+#' @export
+report_text.check_outliers <- function(x, ...) {
+  n_outliers <- sum(x)
+  n_total <- length(x)
+  pct <- n_outliers / n_total
+
+  methods <- attr(x, "method")
+  thresholds <- attr(x, "threshold")
+
+  method_labels <- .format_outlier_method_names(methods)
+
+  method_parts <- vapply(
+    seq_along(methods),
+    function(i) {
+      m <- methods[i]
+      thresh <- thresholds[[m]]
+      if (!is.null(thresh) && length(thresh) == 1L && !is.na(thresh)) {
+        paste0(
+          method_labels[i],
+          " (threshold = ",
+          insight::format_value(thresh, digits = 3),
+          ")"
+        )
+      } else {
+        method_labels[i]
+      }
+    },
+    character(1L)
+  )
+
+  method_str <- paste(method_parts, collapse = " and ")
+
+  if (n_outliers == 0L) {
+    text <- "No observations were detected as potential outliers."
+  } else if (n_outliers == 1L) {
+    text <- paste0(
+      "1 observation (",
+      insight::format_value(pct, as_percent = TRUE),
+      ") was detected as a potential outlier based on ",
+      method_str,
+      "."
+    )
+  } else {
+    text <- paste0(
+      n_outliers,
+      " observations (",
+      insight::format_value(pct, as_percent = TRUE),
+      ") were detected as potential outliers based on ",
+      method_str,
+      "."
+    )
+  }
+
+  as.report_text(text)
+}
+
+
+#' @rdname report_text.check_outliers
+#' @export
+report.check_outliers <- function(x, ...) {
+  result_text <- report_text(x, ...)
+  as.report(text = result_text, ...)
+}
+
+
+# Helper ------------------------------------------------------------------
+
+.format_outlier_method_names <- function(methods) {
+  method_map <- c(
+    cook = "Cook's distance",
+    mahalanobis = "Mahalanobis distance",
+    mahalanobis_robust = "robust Mahalanobis distance",
+    zscore = "z-score",
+    zscore_robust = "robust z-score",
+    iqr = "IQR",
+    ci = "confidence intervals",
+    optics = "OPTICS",
+    iforest = "Isolation Forest",
+    lof = "Local Outlier Factor",
+    mcd = "MCD"
+  )
+  labels <- method_map[methods]
+  # Fall back to the raw method name for any unknown method
+  labels[is.na(labels)] <- methods[is.na(labels)]
+  unname(labels)
+}

R/report.lm.R

@@ -8,6 +8,9 @@
 #' @param include_diagnostic If `FALSE`, won't include diagnostic related
 #'   indices for Bayesian models (ESS, Rhat).
 #' @param include_intercept If `FALSE`, won't include the intercept.
+#' @param assumptions If `FALSE`, assumption checks (see
+#'   [report_assumptions()]) are skipped and not included in the report.
+#'   Defaults to `TRUE`.
 #' @param effectsize_method See documentation for
 #'   [effectsize::effectsize()].
 #' @param parameters Provide the output of `report_parameters()` to avoid
@@ -55,6 +58,7 @@ report.lm <- function(
   x,
   include_effectsize = TRUE,
   effectsize_method = "refit",
+  assumptions = TRUE,
   ...
 ) {
   result_table <- report_table(
@@ -63,7 +67,12 @@ report.lm <- function(
     effectsize_method = effectsize_method,
     ...
   )
-  result_text <- report_text(x, table = result_table, ...)
+  result_text <- report_text(
+    x,
+    table = result_table,
+    assumptions = assumptions,
+    ...
+  )
 
   as.report(result_text, table = result_table, ...)
 }
@@ -729,7 +738,7 @@ report_info.lm <- function(
 
 #' @rdname report.lm
 #' @export
-report_text.lm <- function(x, table = NULL, ...) {
+report_text.lm <- function(x, table = NULL, assumptions = TRUE, ...) {
   params <- report_parameters(x, table = table, include_intercept = FALSE, ...)
   report_table_data <- attributes(params)$table
 
@@ -753,6 +762,18 @@ report_text.lm <- function(x, table = NULL, ...) {
     )
   }
 
+  # --- Assumptions (requires performance) ---------------------------------
+  assumptions_summary <- ""
+  if (isTRUE(assumptions) && requireNamespace("performance", quietly = TRUE)) {
+    assumptions_obj <- tryCatch(
+      report_assumptions(x),
+      error = function(e) NULL
+    )
+    if (!is.null(assumptions_obj)) {
+      assumptions_summary <- as.character(summary(assumptions_obj))
+    }
+  }
+
   # Helpers
   sep_after <- function(x) {
     x <- trimws(x)
@@ -773,6 +794,7 @@ report_text.lm <- function(x, table = NULL, ...) {
     "We fitted a ",
     model,
     ". ",
+    if (nzchar(assumptions_summary)) paste0(assumptions_summary, " ") else "",
     perf,
     sep_after(perf),
     intercept,
@@ -787,6 +809,7 @@ report_text.lm <- function(x, table = NULL, ...) {
     "We fitted a ",
     summary(model),
     ". ",
+    if (nzchar(assumptions_summary)) paste0(assumptions_summary, " ") else "",
     summary(perf),
     sep_after(summary(perf)),
     summary(intercept),

R/report_ai.R

@@ -3,6 +3,7 @@
   UseMethod("report_ai")
 }
 
+#' @exportS3Method
 report_ai.default <- function(x, ...) {
   insight::format_warning(
     paste0(
@@ -14,16 +15,22 @@
   report(x, ..., audience = "humans")
 }
 
+#' @exportS3Method
 report_ai.lm <- function(x, ...) {
   .report_ai_models(x, ...)
 }
 
-report_ai.glm <- report_ai.lm
+#' @exportS3Method
+report_ai.glm <- function(x, ...) {
+  .report_ai_models(x, ...)
+}
 
+#' @exportS3Method
 report_ai.merMod <- function(x, ...) {
   .report_ai_models(x, ...)
 }
 
+#' @exportS3Method
 report_ai.glmmTMB <- function(x, ...) {
   .report_ai_models(x, ...)
 }
@@ -79,6 +86,8 @@
   } else {
     desc_str <- "- No variables found."
   }
+  # Remove any leading blank lines introduced by the report() header
+  desc_str <- sub("^\\n+", "", desc_str)
 
   params <- parameters::model_parameters(x, ...)
 
@@ -153,6 +162,12 @@
   perf_markdown <- insight::export_table(perf_table, format = "markdown")
   perf_str <- paste(perf_markdown, collapse = "\n")
 
+  # Assumptions (requires performance; silently skipped if unsupported)
+  assumptions_str <- tryCatch(
+    as.character(report_assumptions(x, audience = "ai")),
+    error = function(e) NULL
+  )
+
   if ("p" %in% names(fixed_params) && "Parameter" %in% names(fixed_params)) {
     sig_effects <- fixed_params$Parameter[
       !is.na(fixed_params$p) &
@@ -221,6 +236,7 @@
     "\n\n",
     "## Variables\n",
     desc_str,
+    if (!is.null(assumptions_str)) paste0("\n\n", assumptions_str) else "",
     "\n\n",
     param_section,
     "\n\n",