A0778
Title: A Bayesian framework for correlated continuous outcomes using individual and aggregate data
Authors: Shengqiang Chen - The University of Memphis (United States) [presenting]
Hongmei Zhang - The University of Memphis (United States)
Abstract: A Bayesian network meta-analysis (NMA) framework is proposed for jointly modeling correlated continuous outcomes, incorporating both individual participant data (IPD) and aggregate data (AD). The method addresses common challenges in clinical and epidemiological research, including partially available IPD and correlated outcomes. Under the Bayesian framework, the approach borrows strength across different treatments and correlated outcomes while addressing certain feature-specific treatment effects based on relevant information available in both data levels. Implemented in RJAGS, the method enables robust evidence synthesis for complex mixed-data problems. Simulations are used to assess the proposed approach with respect to estimation bias and precision in comparison with findings from standard NMA approaches.
