Google

An interrupted time-series design is a quasi-experimental approach and a variant of the pretest-posttest design. In this methodology, a researcher takes a time series—multiple measurements of a dependent variable at regular intervals—both before and after a treatment is introduced. The treatment effectively 'interrupts' the ongoing measurements. Unlike the simpler pretest-posttest design, which relies on a single before-and-after measurement, the inclusion of multiple measurements allows researchers to better distinguish the actual effect of the intervention from normal variation.

Interrupted Time-Series Design

A classic example of an interrupted time-series design is a study analyzing a factory's reduction of work shifts from 10 hours to 8 hours. Researchers took a time series of weekly worker productivity measurements over an extended period. The change in shift length served as the experimental 'interruption'. Because productivity increased rapidly following the shift reduction and remained consistently elevated for many months afterward, the researchers could confidently conclude that the shortened shifts were the direct cause of the increased productivity.

Example of an Interrupted Time-Series Design: Factory Shift Reduction

An interrupted time-series design can be illustrated by tracking the number of student absences per week in a course. In this scenario, the 'interruption' is the instructor beginning to publicly take daily attendance. If the multiple measurements show a consistently high number of absences before this treatment, followed by an immediate and sustained drop afterward, the treatment is deemed effective. However, if the long-term trend of absences remains virtually unchanged on average after the intervention, it suggests the treatment failed to produce a meaningful effect, even if minor weekly fluctuations exist.

Example of an Interrupted Time-Series Design: Student Absences

An interrupted time-series design with nonequivalent groups is a quasi-experimental approach that enhances the basic interrupted time-series design by incorporating a control group. This methodology involves taking multiple measurements of a dependent variable at regular intervals over an extended period both before and after an intervention is implemented across two or more groups that were not randomly assigned. By comparing the baseline and post-intervention trends of the treatment group to those of the nonequivalent control group, researchers can obtain stronger evidence regarding the effectiveness of the intervention.

Interrupted Time-Series Design with Nonequivalent Groups

An AB design is a basic single-subject research structure that involves only two phases: an initial baseline phase (A) followed by a single treatment phase (B). This methodology functions similarly to an interrupted time-series design applied to a single participant. A significant limitation of the AB design is its susceptibility to confounding variables; if the dependent variable changes following the intervention, it remains unclear whether the treatment or a coincidental extraneous variable caused the change, resulting in lower internal validity compared to reversal designs.

AB Design

A primary advantage of the interrupted time-series design over a simpler one-group pretest-posttest design is its ability to account for normal, ongoing fluctuations in the dependent variable. By collecting multiple measurements both before and after an intervention, researchers can establish a baseline trend. This prevents them from falsely attributing a change to the treatment when it might simply be normal week-to-week variation, a crucial distinction that a single pretest and posttest measurement cannot reliably detect.

Learn Before

Related