Skip to content
StatsOtter A workspace for causal thinking
Log in Join the workspaceJoin

THE CAUSAL INFERENCE WORKSPACE

Good questions.
Credible answers.

Find a method for your question. Follow the analysis, inspect its evidence, and discuss every step.

TRY A QUESTIONDifference-in-differences Causal forest Field guide ↗

THE METHOD STUDIO

01 / 03

What changed after the policy?

Difference-in-differencesΔYᵀ − ΔYᶜ
Difference-in-differences: a hypothetical policy effectIllustrative group averages. Treated and comparison groups have parallel pre-policy trends. After the policy, the treated series rises above its dashed no-policy path. That counterfactual is an assumption, not an observed outcome.Policy beginsOutcomeBeforeAfterEffect
TreatedComparisonNo-policy path
Event-time effects
0−30+3+1.65τ(t) · illustrativeAbove no-policy path
Read the policy effect
  1. Compare groups
  2. Check trends
  3. Estimate change
Illustrative dataAssumes parallel untreated trends.

A world of methods.

COMMUNITY ATLAS
Method guides
68
Research fields
10
68 workflows 10 fields of inquiry Find your next methodSCROLL INTO THE NOTEBOOK

THE OPEN NOTEBOOK

Explore the methods.

68 workflows/10 fields of inquiry

Popular Newest