Monash University
Korevaar_thesis_final_20230426.pdf (46.35 MB)

Statistical methods for meta-analysis of interrupted time series studies

Download (46.35 MB)
posted on 2023-04-28, 03:38 authored by ELIZABETH ANNE KOREVAAR
An interrupted time series study is a type of non-randomised study that allows researchers to quantify the immediate and long-term impact of interruptions like public health policies. For example, the impact of a mass media campaign on HIV testing rates. The results from multiple interrupted time series may be combined using a statistical technique called meta-analysis. However, there are many meta-analysis methods and no research on how these methods perform when combining interrupted time series studies. This thesis describes how interrupted time series are combined in the published literature and evaluates how well the statistical methods perform.


Principal supervisor

Joanne Ellen Mckenzie

Additional supervisor 1

Andrew B Forbes

Additional supervisor 2

Amalia Karahalios

Year of Award


Department, School or Centre

Public Health and Preventive Medicine

Additional Institution or Organisation

Department of Epidemiology and Preventive Medicine

Campus location



Doctor of Philosophy

Degree Type



Faculty of Medicine, Nursing and Health Sciences