Presenters: Nolan Cole, Mathematical & Physical Sciences, Statistics
Authors: Nolan Cole, Jake Baldauf, Brinley Zabriskie
Faculty Advisor: Brinley Zabriskie, College of Mathematical & Physical Sciences, Statistics
Institution: Brigham Young University
Meta-analyses have become increasingly popular to conduct, especially in public health and medicine where multiple, independent clinical trials can be combined to produce one overall conclusion. Meta-analyses are especially useful when small clinical trials lack sufficient power in themselves to detect a treatment effect or when events are rare or adverse. A crucial part of a meta-analysis is determining the extent of heterogeneity in the data, the degree to which individual studies’ treatment effects differ in areas not due to chance alone. When events are rare, the computational complexity of estimating heterogeneity increases drastically due to zero events in either a single treatment arm or both. We investigate the impact to which the inclusion and exclusion of these studies, continuity corrections, and the ability to detect heterogeneity via tests of homogeneity has on heterogeneity estimates.