What to explore
Change parameters and watch the model adjust.
- True treatment effect, baseline group gap, common trend, trend violation, noise, and cell size
- The panel is simulated with a fixed seed so treatment and bias move predictably
Upper-undergraduate econometrics
Difference-in-Differences
A two-group, two-period panel notebook for treatment effects, common trends, and what happens when parallel trends fail.
Focus
Parallel trends, group means, and treatment-effect decomposition
Adjust treatment effects, group gaps, noise, and trend violations to see exactly when the DiD estimate matches the truth and when it drifts.Core ideas
Interpret the mechanics before you chase the graphs.
- Difference-in-differences works by netting out a common change that both groups would have shared.
- A treated-group-specific trend shock looks like extra treatment if the model cannot separate it.
- The four group-time means tell the identification story before any algebra does.
Learning goals
What this model should help students internalize.
- Construct the DiD estimate from treated and control group means across pre and post periods.
- Interpret the parallel-trends assumption as the key identifying restriction.
- See how trend violations contaminate the treatment estimate.
Prerequisites
Concepts to review before diving in.
- Simple regression intuition
- Comfort with group means and before-after comparisons
Next models to study
Keep moving through the track.
Upper-undergraduate econometrics
Instrumental Variables
See when IV improves on OLS, when weak instruments make the estimate unstable, and how exclusion violations undermine the design.
Intermediate price theory
Per-Unit Tax Incidence
See how a per-unit tax alters prices on both sides of the market and divides the burden between buyers and sellers.