Built site for ModelArray@0.1.5: ea4c053

Author: araikes

llms.txt

@@ -175,17 +175,12 @@ These functions are called internally by the analysis functions. Most
 users should not call them directly.
 
 - [`analyseOneElement.lm()`](https://pennlinc.github.io/ModelArray/reference/analyseOneElement.lm.md)
-  :
-
-  Fit a linear model for a single element If the number of subjects with
-  finite scalar values (not `NaN`, `NA`, or `Inf`) does not exceed
-  `num.subj.lthr`, the element is skipped and all statistics are set to
-  `NaN`.
+  : Fit a linear model for a single element
 
 - [`analyseOneElement.gam()`](https://pennlinc.github.io/ModelArray/reference/analyseOneElement.gam.md)
   :
 
-  Fit a GAM for a single element returns metadata (column names, smooth
+  Fit a GAM for a single element Returns metadata (column names, smooth
   term names, parametric term names, and the smoothing parameter
   criterion attribute name) used by `ModelArray.gam` to initialise the
   output data.frame. When `flag_initiate = FALSE`, it returns a numeric

pkgdown.yml

@@ -12,7 +12,7 @@ articles:
   installations: installations.html
   modelling: modelling.html
   walkthrough: walkthrough.html
-last_built: 2026-04-08T19:53Z
+last_built: 2026-04-09T22:18Z
 urls:
   reference: https://pennlinc.github.io/ModelArray/reference
   article: https://pennlinc.github.io/ModelArray/articles

reference/ModelArray.wrap.html

@@ -173,9 +173,19 @@ ModelArray.wrap(
 
 ## Value
 
-A tibble with one row per element and first column `element_id`
-(0-based). Remaining columns are determined by the return value of
-`FUN`.
+If `flag_initiate = TRUE`, a list with one component:
+
+- column_names:
+
+  Character vector. The column names derived from the return value of
+  `user_fun`, with `"element_id"` prepended. For unnamed list or atomic
+  returns, columns are named `v1`, `v2`, etc. Set to `NaN` if the
+  element was skipped or errored.
+
+If `flag_initiate = FALSE`, a numeric vector of length `num.stat.output`
+with `element_id` (0-based) first and the coerced output of `user_fun`
+in subsequent positions. All-`NaN` (except `element_id`) if the element
+was skipped or if an error occurred with `on_error = "skip"`.
 
 ## Details
 

reference/ModelArray.wrap.md

@@ -1,4 +1,4 @@
-# Fit a GAM for a single element returns metadata (column names, smooth term names, parametric term names, and the smoothing parameter criterion attribute name) used by [`ModelArray.gam`](https://pennlinc.github.io/ModelArray/reference/ModelArray.gam.md) to initialise the output data.frame. When `flag_initiate = FALSE`, it returns a numeric vector representing one row of the final results matrix.
+# Fit a GAM for a single element Returns metadata (column names, smooth term names, parametric term names, and the smoothing parameter criterion attribute name) used by [`ModelArray.gam`](https://pennlinc.github.io/ModelArray/reference/ModelArray.gam.md) to initialise the output data.frame. When `flag_initiate = FALSE`, it returns a numeric vector representing one row of the final results matrix.
 
 If the number of subjects with finite scalar values does not exceed
 `num.subj.lthr`, the element is skipped and all statistics are set to
@@ -9,18 +9,19 @@ If the number of subjects with finite scalar values does not exceed
 ``` r
 analyseOneElement.gam(
   i_element,
-  formula,
-  modelarray,
-  phenotypes,
-  scalar,
-  var.smoothTerms,
-  var.parametricTerms,
-  var.model,
+  formula = NULL,
+  modelarray = NULL,
+  phenotypes = NULL,
+  scalar = NULL,
+  var.smoothTerms = c("statistic", "p.value"),
+  var.parametricTerms = c("estimate", "statistic", "p.value"),
+  var.model = c("dev.expl"),
   num.subj.lthr,
   num.stat.output = NULL,
   flag_initiate = FALSE,
   flag_sse = FALSE,
   on_error = "stop",
+  ctx = NULL,
   ...
 )
 ```
@@ -40,18 +41,18 @@ analyseOneElement.gam(
 
   A
   [ModelArray](https://pennlinc.github.io/ModelArray/reference/ModelArray-class.md)
-  object.
+  object. Ignored when `ctx` is provided.
 
 - phenotypes:
 
   A data.frame of the cohort with columns of independent variables and
   covariates. Must contain a `"source_file"` column matching
-  `sources(modelarray)[[scalar]]`.
+  `sources(modelarray)[[scalar]]`. Ignored when `ctx` is provided.
 
 - scalar:
 
   Character. The name of the element-wise scalar to analyse. Must be one
-  of `names(scalars(modelarray))`.
+  of `names(scalars(modelarray))`. Ignored when `ctx` is provided.
 
 - var.smoothTerms:
 
@@ -110,6 +111,10 @@ analyseOneElement.gam(
   [`browser`](https://rdrr.io/r/base/browser.html) (if interactive) then
   skips. Default: `"stop"`.
 
+- ctx:
+
+  A precomputed context list from `.build_gam_context()`, or `NULL`.
+
 - ...:
 
   Additional arguments passed to