<?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>topazape</title>
<link>https://topazape.dev/</link>
<atom:link href="https://topazape.dev/index.xml" rel="self" type="application/rss+xml"/>
<description>Statistical modeling and causal inference, with applications in advertising effectiveness measurement.</description>
<generator>quarto-1.10.18</generator>
<lastBuildDate>Wed, 16 Sep 2026 00:00:00 GMT</lastBuildDate>
<item>
  <title>Estimating unique users for genre combinations with latent class analysis</title>
  <link>https://topazape.dev/posts/audience-modeling-size/</link>
  <description><![CDATA[ Approximate the joint distribution of genre indicators with latent class analysis and estimate unique users for arbitrary genre combinations. ]]></description>
  <category>audience-modeling</category>
  <category>mixture-models</category>
  <category>statistics</category>
  <guid>https://topazape.dev/posts/audience-modeling-size/</guid>
  <pubDate>Wed, 16 Sep 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/audience-modeling-size/index_files/figure-html/fig-genre-correlation-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>Modeling Ad Frequency Distributions with Finite Mixtures of Negative Binomials</title>
  <link>https://topazape.dev/posts/audience-modeling-frequency/</link>
  <description><![CDATA[ Model heterogeneous ad exposure counts with a finite mixture of negative binomial distributions and derive reach curves from the fitted parameters. ]]></description>
  <category>audience-modeling</category>
  <category>reach-frequency</category>
  <category>statistics</category>
  <guid>https://topazape.dev/posts/audience-modeling-frequency/</guid>
  <pubDate>Wed, 09 Sep 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/audience-modeling-frequency/index_files/figure-html/fig-freq-dist-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>Differential Attrition in Brand Lift: Diagnosing Selection Bias with Lee Bounds</title>
  <link>https://topazape.dev/posts/bls-lee-bounds-diagnostic/</link>
  <description><![CDATA[ Diagnose selection bias from differential survey response in Brand Lift studies using Lee bounds, with binary-outcome examples and reusable R code. ]]></description>
  <category>brand-lift</category>
  <category>statistics</category>
  <category>causal-inference</category>
  <guid>https://topazape.dev/posts/bls-lee-bounds-diagnostic/</guid>
  <pubDate>Wed, 26 Aug 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/bls-lee-bounds-diagnostic/index_files/figure-html/fig-bounds-vs-p-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>From Risk Ratios to Odds Ratios: Choosing an Aggregation Scale for Brand Lift</title>
  <link>https://topazape.dev/posts/bls-or-vs-rr/</link>
  <description><![CDATA[ Compare risk ratios and odds ratios across Brand Lift studies, derive the log-odds confidence interval, and pool campaign effects by inverse variance. ]]></description>
  <category>brand-lift</category>
  <category>statistics</category>
  <category>meta-analysis</category>
  <guid>https://topazape.dev/posts/bls-or-vs-rr/</guid>
  <pubDate>Wed, 12 Aug 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/bls-or-vs-rr/index_files/figure-html/fig-pooled-ci-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>Fieller’s Confidence Interval for Risk Ratios: Removing the Taylor Approximation</title>
  <link>https://topazape.dev/posts/bls-fieller-ci/</link>
  <description><![CDATA[ Derive Fieller’s confidence interval for Brand Lift risk ratios, compare its coverage with delta and bootstrap methods, and implement it in R and BigQuery. ]]></description>
  <category>brand-lift</category>
  <category>statistics</category>
  <guid>https://topazape.dev/posts/bls-fieller-ci/</guid>
  <pubDate>Wed, 29 Jul 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/bls-fieller-ci/index_files/figure-html/fig-ci-comparison-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>How Reliable Is the Delta Method CI? Bootstrap Validation and Sample Size Planning</title>
  <link>https://topazape.dev/posts/bls-bootstrap-validation/</link>
  <description><![CDATA[ Validate delta-method confidence intervals for Brand Lift risk ratios by simulation and bootstrap, then derive sample sizes for a target power. ]]></description>
  <category>brand-lift</category>
  <category>statistics</category>
  <guid>https://topazape.dev/posts/bls-bootstrap-validation/</guid>
  <pubDate>Wed, 15 Jul 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/bls-bootstrap-validation/index_files/figure-html/fig-coverage-1.png" medium="image" type="image/png"/>
</item>
<item>
  <title>Confidence Intervals for Brand Lift: The Delta Method on Risk Ratios</title>
  <link>https://topazape.dev/posts/bls-delta-method-rr/</link>
  <description><![CDATA[ Derive a confidence interval for Brand Lift risk ratios with the log-scale delta method, including worked examples and production-ready R and BigQuery SQL. ]]></description>
  <category>brand-lift</category>
  <category>statistics</category>
  <guid>https://topazape.dev/posts/bls-delta-method-rr/</guid>
  <pubDate>Wed, 01 Jul 2026 00:00:00 GMT</pubDate>
  <media:content url="https://topazape.dev/posts/bls-delta-method-rr/index_files/figure-html/fig-ci-comparison-1.png" medium="image" type="image/png"/>
</item>
</channel>
</rss>
