did_causal_analysis

What problem does it solve?

Difference-in-Differences causal analysis to identify demographic drivers of behavioral changes with p-value significance testing. Use for event effects, A/B testing, or policy evaluation.

Core Features & Use Cases

• Multivariate Heterogeneous DiD: estimate collective treatment effects across multiple features with interaction terms.
• Univariate DiD fallback: robust when sample size is small, providing per-feature estimates.
• Transparent reporting: outputs include DiD estimates, p-values, standard errors, and confidence intervals for interpretation across groups and periods.
• Data preparation guidance: supports both intensive (sparse, participants-only) and extensive (complete panel) margins, with code examples for proper data structuring.
• Flexible usage: designed for event studies, A/B tests, policy evaluation, and other pre/post intervention analyses.

Quick Start

Provide a dataset with a 'Period' column (baseline or treatment), feature columns for groups, and a numeric outcome column, then run the analysis to obtain DiD estimates, p-values, and confidence intervals.