What is a key feature of interrupted time series analysis in evaluating an intervention?

• A. It uses pre/post comparison without considering serial data.
• B. It relies on cross-sectional comparisons.
• C. It estimates immediate effects only.
• D. It uses serial data to detect changes in level and trend after the intervention.

Answer: (D)

Interrupted time series analysis hinges on using data collected at multiple time points before and after an intervention to see how the outcome changes over time. This serial data lets you detect both an immediate shift in level right after the intervention and any change in the trajectory (the slope) of the outcome in the period following the intervention. That combination is what makes this approach powerful for distinguishing the intervention's effect from existing trends or random fluctuations.

Relying on a simple pre/post comparison without serial data misses how the outcome was behaving before the intervention, so it can misattribute ongoing trends to the intervention. Cross-sectional data, looking at one point in time, can’t reveal those temporal dynamics either. And while an immediate change can occur, interrupted time series is capable of capturing changes in both level and trend, not limited to immediate effects alone.