Skip to content

Commit

Permalink
Remove rmd rendering
Browse files Browse the repository at this point in the history
  • Loading branch information
LukasWallrich committed Sep 9, 2024
1 parent 8b4e35e commit 727183f
Show file tree
Hide file tree
Showing 3 changed files with 17 additions and 3 deletions.
2 changes: 1 addition & 1 deletion .github/workflows/blogdown.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ jobs:
- name: Build site
run: |
R -e 'blogdown::build_site(build_rmd = TRUE, run_hugo = FALSE)'
# R -e 'blogdown::build_site(build_rmd = TRUE, run_hugo = FALSE)'
R -e 'if (!blogdown::hugo_build()==0) { stop("Hugo build failed.") }'
- name: Deploy to Netlify
Expand Down
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
---
title: Assessing interrater agreement in meta-analyses - what sample size do I need?
author: Lukas Wallrich
date: '2023-05-11'
date: '2024-05-11'
slug: assessing-interrater-agreement-in-meta-analyses-what-sample-size-do-i-need
categories: [statistics]
tags: []
Expand All @@ -28,6 +28,10 @@



<div style="border: 2px solid #ffcc00; padding: 10px; background-color: #fffbe6; border-radius: 5px;">
<p><strong>Work in Progress:</strong> This post is a draft and currently under review.
<br>Feedback is highly welcome. Please <strong>double-check the details</strong> before relying on them for decision-making.</p>
</div>
<div id="the-problem" class="section level2">
<h2>The problem</h2>
<p>Researchers conducting meta-analyses and systematic reviews need to decide whether to use one or multiple researchers at both the screening and coding stages. While double-coding leads to the identification of more relevant articles <span class="citation">(<a href="#ref-waffenschmidtSingleScreeningConventional2019">Waffenschmidt et al. 2019</a>)</span>, and (almost necessarily) to greater accuracy in coding, it is also much more resource-intensive. Therefore, many protocols specify that they will double-screen or double-code <em>a share</em> of articles and then either simply use that to report on interrater reliability or to decide on the approach for the remaining sources.</p>
Expand Down Expand Up @@ -166,6 +170,7 @@ <h3>Simulation</h3>
geom_point() + geom_hline(yintercept = .2, color = &quot;red&quot;) + geom_hline(yintercept = .1, color = &quot;red&quot;, linetype = &quot;dashed&quot;) +
labs(y = &quot;Uncertainty (estimate - lower bound of 90% CI)&quot;)</code></pre>
</details>
<p><img src="{{< blogdown/postref >}}index_files/figure-html/unnamed-chunk-3-1.png" width="672" /></p>
</div>
<div id="calculation-of-required-n" class="section level3">
<h3>Calculation of required N</h3>
Expand Down Expand Up @@ -653,6 +658,15 @@ <h3>Calculation of required N</h3>
#dqngmgsrdd .gt_indent_5 {
text-indent: 25px;
}

#dqngmgsrdd .katex-display {
display: inline-flex !important;
margin-bottom: 0.75em !important;
}

#dqngmgsrdd div.Reactable > div.rt-table > div.rt-thead > div.rt-tr.rt-tr-group-header > div.rt-th-group:after {
height: 0px !important;
}
</style>
<table class="gt_table" data-quarto-disable-processing="false" data-quarto-bootstrap="false">
<thead>
Expand Down
2 changes: 1 addition & 1 deletion layouts/shortcodes/blogdown/postref.html
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{{ .Page.Permalink }}
{{ if eq (getenv "HUGO_BLOGDOWN_POST_RELREF") "true" }}{{ .Page.RelPermalink }}{{ else }}{{ .Page.Permalink }}{{ end }}

0 comments on commit 727183f

Please sign in to comment.