Interrupted Time Series (ITS)

Interrupted Time Series (ITS) analysis is a statistical method used to determine the impact of an intervention or event on outcomes measured over time[1;2;3;4; ]. ITS analysis may also be referred to as a ‘change point analysis’ and specifically examines whether the intervention created a change in the level or trend of a time series. ITS is a valuable tool for evaluating the effects of policies, programs, or events when traditional randomized controlled trials may be impractical or unethical.

As a quasi-experimental design, ITS studies offer greater strength of causal inference than simple pre-post comparisons (e.g., difference-in-difference). The analysis focuses on patterns before and after the intervention, which helps control for underlying trends that might have occurred regardless of the intervention.

ITS analysis leverages data collected over time (longitudinal). This allows the researcher to establish an underlying pattern or baseline before the intervention occurred. After the intervention, any changes to the baseline (level or trend) may be potentially attributed to its effects.

In ITS studies, the event or intervention being investigated happens at a clearly defined point in time. This point becomes the focus for comparing the ‘before’ and ‘after’ segments of the time series.

Key Highlights

  • Pre- and Post-Intervention Data:

    • Data points are collected both before and after the intervention is introduced.

  • Population-Level Impact:

    • ITS is often used to study the impact of interventions that affect an entire population.

  • Control for Secular Trends:

    • ITS analysis attempts to account for ongoing trends that might exist independently of the intervention.