A family truck, back in the family. Restoring a ~1992 Toyota pickup with my son, backed by real forum data on what breaks on a 22RE, and why it matters in Hawaii.

• [ Data Viz ]
• [ Web Scraping ]
• [ Personal ]

Test twenty metrics at once and something will look like a winner by chance, even when nothing real changed. A live simulation of why, and what actually controls it.

• [ Statistics ]
• [ A/B Testing ]
• [ Data Viz ]

Most of the variance in your metric has nothing to do with your treatment. A live simulation of CUPED, the technique that removes it, without touching your false-positive rate.

• [ Statistics ]
• [ A/B Testing ]
• [ Data Viz ]

Checking your A/B test results early feels harmless. A live simulation of what it actually costs you, in both frequentist and Bayesian terms.

• [ Statistics ]
• [ A/B Testing ]
• [ Data Viz ]

How much should you trust surfboard volume calculators? A comparison of how thirteen recommendation systems disagree for the same surfer.

• [ Data Viz ]
• [ Web Scraping ]
• [ Consumer Data ]

An open-source library for designing, analyzing, and reporting on A/B tests: the parts of an experimentation platform worth sharing publicly.

• [ Python ]
• [ Experimentation ]
• [ Statistics ]

Notes and worked examples as I learn causal methods (diff-in-diff, synthetic control, instrumental variables) for questions where a randomized test isn't possible.

• [ Causal Inference ]
• [ Python ]