13 - Time-series Designs and Analyses

Abstract

Time-series data can be applied to an array of different research purposes and analyzed with a variety of statistical techniques. This chapter focuses primarily on interrupted time-series (ITS) design and on Autoregressive Integrated Moving Average (ARIMA) statistical analyses. In the ITS design, a series of observations is collected over time, both before and after a treatment is implemented. The pattern in the pretreatment observations provides a comparison with which to assess a possible treatment effect in the post-treatment observations. Advantages of ITS designs include that they can be used to estimate the effects of a treatment when only a single individual, or on a single aggregated unit such as a city, is available for study. It reveals the pattern of the treatment effect over time, and provides an estimate of the treatment effect without withholding the treatment from anyone who is eligible to receive it. Moreover, ITS designs can be among the most credible quasi-experimental designs.