smmargins¶
Stata-style margins for StatsModels: adjusted predictions, marginal
effects, elasticities, and difference-in-differences — with
delta-method, Krinsky–Robb simulation, or bootstrap standard errors,
robust covariance passthrough (HC0–HC3, cluster, HAC), and
simultaneous confidence intervals (Bonferroni, Šidák, sup-t) — for any
fitted model that exposes params, cov_params(), and
predict(params, exog).
User guide
- Introduction
- Mathematical motivation
- The delta method
- A single statistic schema
- Marginal effects of a single variable
- Elasticities
- Outer Jacobian: analytic vs. finite differences
- Beyond delta: simulation and bootstrap VCEs
- Simultaneous confidence intervals
- Prediction scales and the chain rule
- Subgroup AMEs (
over=) - Joint Wald and pairwise contrasts
- Why the response scale matters for DiD (Ai & Norton 2003)
- References
- Demos
Reference