Dr Mircea Zloteanu 🌼🐝<p><a href="https://mastodon.social/tags/statstab" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>statstab</span></a> #234 Not all alphas can be justified</p><p>Thoughts: When using discrete distributions, with few outcomes, your alpha cannot always take the values you want. Same with the distribution of p-values under the null.</p><p><a href="https://mastodon.social/tags/pvalues" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pvalues</span></a> <a href="https://mastodon.social/tags/nhst" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nhst</span></a> <a href="https://mastodon.social/tags/errorcontrol" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>errorcontrol</span></a> <a href="https://mastodon.social/tags/alpha" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>alpha</span></a></p><p><a href="https://osf.io/preprints/psyarxiv/erwvk" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">osf.io/preprints/psyarxiv/erwv</span><span class="invisible">k</span></a></p>