Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/namakala/inappropriate-acid-suppressor-agent-use/llms.txt

Use this file to discover all available pages before exploring further.

visualize.R provides two plotting functions for meta-analysis results. vizForest() produces a publication-ready forest plot with a custom column layout saved to PDF, and vizFunnel() produces a contour-enhanced funnel plot for assessing publication bias. Both wrap functions from the meta package and accept ... for further customization.

​
vizForest()

vizForest <- function(mod, ...) {
  #' Forest Plot
  #'
  #' Visualize meta-analysis model using forest plot
  #'
  #' @param mod Meta-analysis model from the `meta` package
  require("meta")
  pdf.options(encoding = "ISOLatin2.enc")

  plt <- meta::forest(
    mod,
    leftcols = c(
      "studlab", "Sample_size", "Inappropriate_indication", "w.random",
      "effect", "ci"
    ),
    leftlabs = c(
      "Study", "Sample Size", "Events", "Weight (%)", "Proportion", "95% CI"
    ),
    sortvar     = TE,
    rightcols   = FALSE,
    xlim        = c(0, 1),
    digits      = 2,
    width       = 9,
    colgap.left = "0.15cm",
    fontsize    = 10,
    prediction  = TRUE,
    backtransf  = TRUE,
    ...
  )

  return(plt)
}

​
Parameters

​
mod
metaprop
required
A metaprop object from fitMetaprop() or fitSubMetaprop(). The object must have been fitted with prediction = TRUE to show the prediction interval row.
​
...
any
Additional arguments passed to meta::forest(). The most important is file for writing the plot to a PDF path. For subgroup forest plots, pass print.subgroup.name = FALSE to suppress the redundant subgroup header row.

​
Returns

A forest plot object (returned invisibly). The primary output is the rendered PDF when file is specified via ....

​
Appearance and column layout

ColumnSource slotLabel
StudystudlabStudy
Sample sizeSample_sizeSample Size
EventsInappropriate_indicationEvents
Weightw.randomWeight (%)
ProportioneffectProportion
Confidence intervalci95% CI
Additional settings:
  • Studies are sorted in ascending order of effect size (sortvar = TE).
  • The x-axis runs from 0 to 1 (xlim = c(0, 1)).
  • backtransf = TRUE back-transforms Freeman-Tukey values so displayed proportions are on the natural scale.
  • The prediction interval is shown (prediction = TRUE).
  • Right-side columns are suppressed (rightcols = FALSE).
  • PDF encoding is set to ISOLatin2 to support special characters in author names.

​
Usage

targets::tar_load(mod_prop)
vizForest(mod_prop, file = "docs/figures/meta-analysis-prevalence.pdf")
In _targets.R: 
tar_target(plt_forest_prop, vizForest(mod_prop, file = "docs/figures/meta-analysis-prevalence.pdf"))

​
vizFunnel()

vizFunnel <- function(mod, ...) {
  #' Funnel Plot
  #'
  #' Visualize meta-analysis model using funnel plot
  #'
  #' @param mod Meta-analysis model from the `meta` package
  require("meta")

  plt <- meta::funnel(
    mod,
    type = "contour",
    common = TRUE,
    random = TRUE
  )

  return(plt)
}

​
Parameters

​
mod
meta object
required
A meta object (such as a metaprop from fitMetaprop()) or an rma object from fitMetareg().
​
...
any
Additional arguments passed to meta::funnel(). Use these to control significance contour levels, axis labels, or symbol appearance.

​
Returns

A funnel plot object (returned invisibly). The plot is rendered to the active graphics device.

​
Plot type

vizFunnel() produces a contour-enhanced funnel plot (type = "contour"). Contour regions shade the areas of statistical significance, helping to distinguish between publication bias and genuine heterogeneity. Both common-effect and random-effects reference lines are drawn (common = TRUE, random = TRUE).

​
Usage

targets::tar_load(mod_prop)
vizFunnel(mod_prop)
title("Publication bias assessment: overall model")
For formal asymmetry assessment, this pipeline prefers Doi plots (metasens::doiplot()) over funnel plots. Doi plots are more robust when the number of studies is small and do not rely on assumptions about funnel symmetry.

Build docs developers (and LLMs) love

Get started for freeTalk to us