In a systematic review and meta-analysis heterogeneity is defined as any variation among the studies and is categorized as clinical, methodological, and statistical. There are multiple methods suggested in the literature to identify and estimate statistical heterogeneity. However, it is often difficult to deal with its presence, while misconceptions may lead to wrong interpretation of review findings.
In April 2023, Afroditi Kanellopoulou and Sofia Tsokani from the Methods Support Unit explained the concept of heterogeneity, discussed how to deal with its presence and avoid common mistakes related to it.
Below you will find the videos from the webinar. Recordings from other Methods Support Unit web clinics are available here.
Part 1: Definition and identifying heterogeneity
Part 2: Dealing with heterogeneity and Q&A
Afroditi Kanellopoulou is a Statistics Editor in the Methods Support Unit. She is a biostatistician with a strong interest on cancer prevention and progression, evidence synthesis as well as causal inference methods. She was trained at National and Kapodistrian University of Athens, Greece, where she received a Bachelor’s in Mathematics and a Master’s in Biostatistics. Since 2019, she is a Research Associate at the Department of Hygiene and Epidemiology, University of Ioannina, Greece and a PhD candidate under the supervision of Associate Professor, Konstantinos Tsilidis. Her doctoral research is focused on the investigation of the associations between a wide range of non-therapeutic modifiable risk factors and colorectal cancer survival.
Sofia Tsokani is a Statistics Editor in the Methods Support Unit. She holds a BSc in Mathematics, a MSc in Statistics and Operations Research, and a PhD, all obtained from the University of Ioannina. Her PhD focused on evidence synthesis methods, with an emphasis on meta-analysis and network meta-analysis of diagnostic tests. She has worked as a research associate in biostatistics prior to joining MSU; during this time period she was involved in several methodological and empirical projects, mainly in the field of network meta-analysis. Her research interests encompass systematic reviews, and statistical modelling for meta-analysis and network meta-analysis of both interventions and diagnostic tests.