Wolfgang Viechtbauer<p>Very important work by James Pustejovsky (<span class="h-card" translate="no"><a href="https://fediscience.org/@jepusto" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>jepusto</span></a></span>), Jingru Zhang (not on Mastodon as far as I can tell), and Elizabeth Tipton (<span class="h-card" translate="no"><a href="https://toot.community/@stats_tipton" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>stats_tipton</span></a></span>) on how to conduct meta-regression analyses when at least some studies provide multiple (possibly dependent) effect size estimates corresponding to different values of the moderator: </p><p><a href="https://www.jepusto.com/talk/sree-2023-equity-related-moderator-analysis/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">jepusto.com/talk/sree-2023-equ</span><span class="invisible">ity-related-moderator-analysis/</span></a></p><p>In general, there are a lot of lessons from the multilevel literature we can learn from.</p><p><a href="https://scholar.social/tags/MetaAnalysis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MetaAnalysis</span></a> <a href="https://scholar.social/tags/MetaRegression" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MetaRegression</span></a> <a href="https://scholar.social/tags/MultilevelModeling" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MultilevelModeling</span></a></p>