About
Reid Rhodes
A data scientist focused on causal inference, with most of that work at early and mid-stage startups. Based in Chicago, IL.
The work
At an early or mid-stage startup the measurement question is rarely which estimator to use. It is whether the data can support the claim at all, whether the team can run the design the statistics require, and what to do when the answer is needed before either is true. That means experimentation, incrementality, and attribution, plus the data engineering underneath when the pipeline is the reason nobody trusts the number.
What is here comes from answering those questions under real constraints. Tracking that lost a third of conversions to consent. A campaign that launched three days late into the wrong audience. A CFO who needed a number on Thursday. The methods matter, and the judgment about which one survives contact with the data in front of you matters more. That part is harder to find written down, which is most of why this site exists.
What this site is
A field guide to marketing measurement when the data is imperfect. It is organized around decisions rather than algorithms: a method appears here only when it is attached to a question someone has to answer, and it arrives with its assumptions, its diagnostics, and the conditions under which it stops working. Every worked example is regenerated from a seeded script named under each figure, so a number on a page can be traced to the line that produced it. Where a topic is on the roadmap but unwritten, it is labeled as planned and does not link anywhere.