<?xml version="1.0" encoding="UTF-8"?>
<rss  xmlns:atom="http://www.w3.org/2005/Atom" 
      xmlns:media="http://search.yahoo.com/mrss/" 
      xmlns:content="http://purl.org/rss/1.0/modules/content/" 
      xmlns:dc="http://purl.org/dc/elements/1.1/" 
      version="2.0">
<channel>
<title>Thoughts by Your Hommie</title>
<link>https://batestguy.github.io/QuartoWebsite-blog-others/blog.html</link>
<atom:link href="https://batestguy.github.io/QuartoWebsite-blog-others/blog.xml" rel="self" type="application/rss+xml"/>
<description>Statistical and machine learning cases, simulations that verify beliefs before the data arrives, and stats textbooks rewritten simpler.</description>
<generator>quarto-1.9.38</generator>
<lastBuildDate>Tue, 11 Aug 2026 23:00:00 GMT</lastBuildDate>
<item>
  <title>Separation makes logistic regression fail loudly in the warnings and quietly in the estimates</title>
  <dc:creator>Batesthommie </dc:creator>
  <link>https://batestguy.github.io/QuartoWebsite-blog-others/posts/logistic-separation/</link>
  <description><![CDATA[ As a predictor gets closer to perfectly separating a binary outcome, the maximum likelihood estimate diverges. R warns about fitted probabilities, not about the coefficient — which is the number people actually report. ]]></description>
  <category>stats-cases</category>
  <guid>https://batestguy.github.io/QuartoWebsite-blog-others/posts/logistic-separation/</guid>
  <pubDate>Tue, 11 Aug 2026 23:00:00 GMT</pubDate>
</item>
<item>
  <title>A Normal(0, 10) prior on a logistic coefficient is not weak — it is a confident bet on certainty</title>
  <dc:creator>Batesthommie </dc:creator>
  <link>https://batestguy.github.io/QuartoWebsite-blog-others/posts/weakly-informative-priors/</link>
  <description><![CDATA[ Priors are chosen on the log-odds scale and interpreted as vague. Pushed through the inverse logit, a wide Normal prior puts most of its mass on probabilities of essentially 0 or essentially 1. ]]></description>
  <category>prior-sims</category>
  <guid>https://batestguy.github.io/QuartoWebsite-blog-others/posts/weakly-informative-priors/</guid>
  <pubDate>Mon, 10 Aug 2026 23:00:00 GMT</pubDate>
</item>
<item>
  <title>The standard error, rewritten without the sampling-distribution detour</title>
  <dc:creator>Batesthommie </dc:creator>
  <link>https://batestguy.github.io/QuartoWebsite-blog-others/posts/standard-error-plainly/</link>
  <description><![CDATA[ Most textbooks introduce the standard error by first constructing an imaginary population of repeated samples. That detour is where readers lose the thread, and it is avoidable. ]]></description>
  <category>book-revisions</category>
  <guid>https://batestguy.github.io/QuartoWebsite-blog-others/posts/standard-error-plainly/</guid>
  <pubDate>Sun, 09 Aug 2026 23:00:00 GMT</pubDate>
</item>
</channel>
</rss>
