32.5 Assumptions

1. Good Donor Pool Matching
   • The synthetic control should closely resemble the treated unit in pre-treatment periods.
   • The gap between pre-treatment outcomes of the treated unit and synthetic control should be zero (or very small).
2. No Contamination
   • Only the treated unit experiences the intervention.
   • Control units in the donor pool do not receive treatment.
3. No Other Major Changes
   • The treatment is the only significant event affecting the treated unit.
4. Linearity Assumption
   • The counterfactual outcome of the treated unit can be constructed as a weighted sum of the control units.
5. Exlusion Restriction (Identification Assumption):
   • The exclusion restriction holds conditional on pre-treatment outcomes.

The Synth package provides an algorithm to determine the optimal weight for each control unit such that the synthetic control best resembles the treated unit before treatment.

---