📝 SummarXiv

Abstract

Observational data are often used to estimate real-world effectiveness and durability of vaccines. A sequence of trials can be emulated to draw inference from such data while minimizing selection bias, immortal time bias, and confounding. Typically, when nested trial emulation (NTE) is employed, effect estimates are pooled across trials. However, such pooled estimates may lack a clear interpretation when the treatment effect is heterogeneous across trials. For vaccines against certain viruses, vaccine effectiveness may vary over calendar time due to newly emerging variants of the virus. This manuscript considers a NTE inverse probability weighted estimator of vaccine effectiveness that may vary over calendar time, time since vaccination, or both. Statistical testing of the trial effect homogeneity assumption is considered. As observed changes in vaccine effectiveness across trials may be attributable to variation in covariate distributions across trial-eligible populations, standardization of trial-specific inferences is also considered. Simulation studies are presented examining the finite-sample performance of the proposed methods under a variety of scenarios. The methods are used to estimate vaccine effectiveness against COVID-19 outcomes using observational data on over 110,000 residents of Abruzzo, Italy during 2021.