Synthetic Control Method (SCM)
The synthetic control method estimates the effect of an intervention on a single treated unit by constructing a weighted combination of untreated donor units that reproduces the treated unit's pre-intervention outcome path.
합성통제법은 처치 이전 결과 경로를 재현하도록 처치받지 않은 비교단위들을 가중 결합하여 하나의 처치단위에 대한 개입 효과를 추정하는 방법입니다.
How do I estimate the effect of a policy that affected only one region or country?
한 지역이나 국가에만 적용된 정책의 효과는 어떻게 추정하나요?
The synthetic control method builds a counterfactual for one treated unit, such as a state or city, from a weighted average of untreated units chosen to match its outcomes before the intervention, and the post-intervention gap estimates the effect. It fits aggregate panel data with a long pre-intervention period and a pool of comparable untreated units, with inference based on placebo tests.
When to use Synthetic Control Method (SCM)
- One region, country, or organization exposed to a policy or event
- Long series of outcomes before the intervention
- Several untreated units that can serve as donors
When to use something else
- Many treated units: use difference-in-differences or an event study design
- Short pre-intervention period or poor pre-treatment fit: use difference-in-differences with careful trend checks
Assumptions and requirements
- Good pre-intervention fit between treated and synthetic units
- Donor units unaffected by the intervention (no spillovers)
- No other major shocks to the treated unit at the same time
- Treated unit's outcomes within the range spanned by the donors
What the analysis reports
- Donor weights
- Predictor balance between treated and synthetic units
- Treated versus synthetic outcome plot and gap plot
- Pre-intervention RMSPE
- Placebo-in-space tests and permutation p-value
How to report it
Relative to its synthetic control (pre-intervention RMSPE = [value]), [treated unit]'s [outcome] was on average [value] lower after [intervention], with a placebo-based p-value of [value].
Related methods
- Difference-in-Differences
- Synthetic Difference-in-Differences
- Interrupted Time Series
Run Synthetic Control Method (SCM) on Quorant
- Data you need
- a table (CSV or Excel) with an outcome variable, a time variable, a unit (entity) ID and a treatment indicator
- Price
- 400 credits for one analysis up to 10,000 rows (complexity level 3); larger or wider data costs more. Optional methodologist review: 1800 credits.
- Checking
- Python results are cross-checked against R reference outputs in every deployment
- Before you pay
- A free pre-analysis diagnosis checks your data and gives an exact quote; nothing is deducted until you approve it.