Interrupted time-series study
Did the level or trend change after an intervention?
When to use this project
Use interrupted time series when an intervention has a defensible implementation time and repeated outcome measurements before and after it. Specify an expected immediate, gradual or delayed response and consider a suitable comparison series.
How it differs
A single before–after comparison cannot estimate the prior trend. Interrupted time series uses that trajectory to construct a counterfactual. Difference-in-differences centers on changes relative to a comparison group; controlled time-series designs can combine both ideas.
Decisions before you start
- Define implementation, transition or lag periods before choosing a model.
- Assess data continuity, denominators, seasonality, autocorrelation and coincident changes.
- Justify a control series using exposure to the intervention and shared external influences.
How the flows work together
Each flow below links to its diagram, steps and tables. Flow order organizes the project; it does not imply that all work is strictly sequential. Data assessment, analysis planning and protocol refinement may inform one another.
1. Time-series study overview
Overview · Question through intervention impact reporting
Use this overview to state the purpose and link to detailed decisions. Keep a versioned protocol and decision register, and add evidence references for the rationale.
2. Intervention and comparison definition
Design · Specify timing controls and mechanisms
Prespecify the expected intervention mechanism, timing and impact shape. Document concurrent policies and events, and justify any control series. Choosing the interruption date after seeing the outcome can bias interpretation.
3. Time-series data preparation
Data · Align intervals outcomes and denominators
Keep observation intervals, population denominators and definitions consistent. Investigate missing periods and recording-system changes; they can mimic an intervention effect.
4. Impact estimation plan
Statistics · Model level slope and correlation
Level and slope changes refer to a specified time origin and scale. Choose an appropriate outcome distribution and model serial correlation and seasonality. An offset may be needed for rates with changing populations.
5. Diagnostics and sensitivity
Statistics · Assess seasonality shocks and specifications
Check residual structure and sensitivity to trend, timing and comparison choices. A good-fitting model does not rule out concurrent changes or establish that the extrapolated trajectory is a valid counterfactual.
Equations and statistical interpretation
These explanations describe notation and assumptions. Flow does not calculate these values.
Segmented linear model
t indexes equally spaced observations, T₀ is the first intervention time and Iₜ is 1 from T₀ onward. β₂ is the immediate level change; β₃ is the slope change; β₁ is the pre-intervention slope.
This linear identity-link model is illustrative. Counts may need a count model and population offset. Serial correlation, seasonality, transition periods and concurrent shocks must be addressed; a fitted change alone does not identify a causal effect.
Published example
Inspect the legislation date, quarterly outcomes and extrapolated pre-legislation trend. Consider other changes that could affect the outcome and the sensitivity of the assumed counterfactual.
This publication illustrates a study design, not an endorsement of every method or a reproduction of its results. Follow its protocol, supplement and update history when studying the example.
Hypothetical scenario
A health service introduced a prescribing policy on a known date and wants to assess changes in monthly antibiotic prescriptions per registered population.
- Time-series study overview: Specify the policy, expected timing and prescribing outcome.
- Intervention and comparison definition: Define the intervention, possible lag, external changes and a plausible comparison series.
- Time-series data preparation: Build a consistent monthly series with population denominators and coding-change checks.
- Impact estimation plan: Estimate level and slope changes with seasonality, serial correlation and a prespecified horizon.
- Diagnostics and sensitivity: Check residuals and sensitivity to timing, trend form and concurrent policies.
Deliver a populated protocol, decision log, data specification, and planned outputs. Enter numerical findings only after analysis and verification. Keep decisions made before seeing results distinguishable from later amendments.
Sources
- Lopez Bernal, Cummins and Gasparrini (2017): interrupted time-series regression tutorial, with linked correction
- RECORD checklist for studies using routinely collected health data
- HMA–EMA Catalogue of RWD studies: registration and protocol guidance
Source check: 2026-09-17. Record the version of each reporting or appraisal tool used in your actual protocol.
Compare all Observational and RWE studies project types · Open editor in a new tab