Jon Huang<p>The reflex to indiscriminately stratify and adjust on covariates is strong in biomedical research. I face this so often, especially with clinician-scientist collaborators.</p><p>The analyses and models that arise from this, in fact, often do not well represent how exposures and treatments exert their effect in reality.</p><p>A <a href="https://aus.social/tags/TargetTrial" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TargetTrial</span></a> approach crystallizes when, where, and how co-variates should be treated. </p><p>Take this great illustration from Target Trial originator <span class="h-card"><a href="https://fediscience.org/@MiguelHernan" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>MiguelHernan</span></a></span> where he explains the study design choices for study on COVID vaccine booster effectiveness:</p><p><a href="https://fediscience.org/@MiguelHernan/109331025655365201" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://</span><span class="ellipsis">fediscience.org/@MiguelHernan/</span><span class="invisible">109331025655365201</span></a></p><p><a href="https://aus.social/tags/epidemiology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>epidemiology</span></a> <a href="https://aus.social/tags/biostatistics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biostatistics</span></a> <a href="https://aus.social/tags/epitwitter" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>epitwitter</span></a> <a href="https://aus.social/tags/statstodon" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>statstodon</span></a> <a href="https://aus.social/tags/epiVerse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>epiVerse</span></a> @epiVerse</p>