designing-experiments
Selects the appropriate quasi-experimental method (DiD, ITS, SC) based on data structure and research questions. Use when the user is unsure which method to apply.
When & Why to Use This Skill
This Claude skill provides a specialized decision framework for causal inference, helping researchers and data analysts select the most robust quasi-experimental method for their studies. By analyzing data structures—such as panel data versus time series—and the availability of control groups, it guides users to the optimal statistical approach, including Difference-in-Differences (DiD), Interrupted Time Series (ITS), or Synthetic Control (SC), ensuring scientific rigor in experimental design.
Use Cases
- Policy Impact Assessment: Determining the effectiveness of a new local regulation by constructing a counterfactual using the Synthetic Control (SC) method when only one treated unit is available.
- Product Feature Rollout: Utilizing Difference-in-Differences (DiD) to compare performance trends between a group of users who received a new feature and a control group that did not.
- Intervention Analysis: Applying Interrupted Time Series (ITS) to evaluate the change in a single organization's performance metrics immediately following a specific internal policy change without a control group.
- Academic Research Design: Assisting researchers in identifying the necessary data requirements (e.g., parallel trends or convex hull assumptions) for different causal inference models.
| name | designing-experiments |
|---|---|
| description | Selects the appropriate quasi-experimental method (DiD, ITS, SC) based on data structure and research questions. Use when the user is unsure which method to apply. |
Designing Experiments
Helps select the appropriate causal inference method.
Decision Framework
Control Group?
- Yes: Go to Step 2.
- No: Consider Interrupted Time Series (ITS).
Unit Structure?
- Single Treated Unit:
- With multiple controls: Synthetic Control (SC).
- No controls: ITS.
- Multiple Treated Units:
- With control group: Difference-in-Differences (DiD).
- Single Treated Unit:
Time Structure?
- Panel Data (Multiple units over time): Required for DiD and SC.
- Time Series (Single unit over time): Required for ITS.
Method Quick Reference
- Difference-in-Differences (DiD): Compares trend changes between treated and control groups. Assumes Parallel Trends.
- Interrupted Time Series (ITS): Analyzes trend/level change for a single unit after intervention. Assumes Trend Continuity.
- Synthetic Control (SC): Constructs a synthetic counterfactual from weighted control units. Assumes Convex Hull (treated unit within range of controls).