did-causal

Community

Estimate causal effects with modern DID

Authorxjtulyc
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Difference-in-differences methods estimate causal treatment effects, but classic estimators can produce biased results under staggered adoption and heterogeneous effects; this Skill helps you compute credible DID estimates while validating key assumptions.

Core Features & Use Cases

  • Two-Way Fixed Effects (TWFE) DID: Estimate treatment effects with unit and time fixed effects for panel data.
  • Parallel trends pre-testing & event-study plots: Diagnose whether treated and control groups follow similar pre-treatment trends.
  • Staggered adoption support (Callaway-Sant'Anna) & bias diagnosis (Goodman-Bacon): Use C&S ATT(g,t) for heterogeneous staggered rollout and use Bacon decomposition to understand TWFE bias patterns.

Quick Start

Use the did-causal skill to estimate the causal impact of a policy change on an outcome using a panel dataset, including a parallel trends pre-test and (if treatment timing is staggered) a Callaway-Sant'Anna estimator.

Dependency Matrix

Required Modules

linearmodelspandasnumpymatplotlibstatsmodelsdidbacondecompfixestdplyrggplot2

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: did-causal
Download link: https://github.com/xjtulyc/awesome-rosetta-skills/archive/main.zip#did-causal

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.