COMM 88 Lecture Notes - Lecture 15: Interrupted Time Series, Time Series, Experiment
Document Summary
Like all experimental designs, the goal is to determine if the treatment had any effect on the outcome. But it"s information only (nothing to compare it with) Like the one above, but now you can see if two different treatments lead to two different results. Like true experiments but done without random assignment. Instead use other criteria like eligibility cut-offs , or use convenience samples. Used when you can"t fully control your sample or your conditions well. Example: in field work, or online studies. Can still be used to estimate causality but may have less internal validity. They may actually have more external validity. Example of q-e designs: time series and multiple time series. Track many observations over time, before and after a manipulation. Called an interrupted time series because the researcher graphs the data before and after the intervention, and looks for an interruption in the graph where the intervention was introduced.