Designing, analysing and interpreting evidence from interrupted time series studies in public health

The interrupted time series (ITS) study design is frequently used to evaluate the effects of policy and health systems interventions, providing evidence to underpin decisions that impact on population health. In a simple ITS design, measures of an outcome are collected at regular time points pre and post the introduction of the policy, intervention or exposure; for example the effect of mass media campaigns on smoking has been studied by measuring smoking rates at multiple time points pre and post the introduction of the campaigns. Despite the increasing popularity of the design, there is limited guidance available to researchers on how to appropriately design and analyse such studies, how the results from multiple ITS studies should be synthesized using meta-analysis, or how the results from such studies are best communicated to policy makers and guideline developers. We are undertaking research to address these gaps, funded through a National Health and Medical Research Council project grant. Through our research, we are identifying many additional questions that need to be addressed. For example, there is a need to develop a method for searching for ITS studies in databases, and for assessing the trustworthiness (bias) of the results from ITS designs. A set of projects for a doctorate could be tailored to be statistical or methodological, so you do not need to be a statistician to apply. Working on this topic would provide the opportunity to work with researchers based at Monash University and internationally. To be eligible for doctoral candidature at Monash University requires a degree at the equivalent Monash level of at least high second class honours and research experience. For a scholarship, a first class honours degree and at least one publication in a Scopus-listed journal is required.