Posts
All the articles I've posted.
-
The Table 2 Fallacy: Your Control Variables Aren't What You Think
Controlling for a variable to identify your treatment effect doesn't mean that variable's coefficient is causally interpretable — and confusing the two is surprisingly common.
-
Hello, world
Welcome to my corner of the internet. A quick note on what this blog is for.
-
Atlas: Budget Optimization Over Any Model
A fitted model predicts response; it doesn't hand you the best budget. Atlas is a model-agnostic framework that turns any predictive model into constraint-respecting spend recommendations.
-
Bayesian Models as Configuration
Treating a Bayesian marketing-mix model as declarative configuration — variables, transforms, normalization, and priors in JSON — so a malformed input file fails validation before you fit instead of after you've shipped the wrong number.