Bayesian Statistical Learning for Robust and Generalizable Causal Inferences in Alzheimer’s Disease and Related Disorders Research

Status: Current

This project aims to develop advanced statistical models for causal inference based on Bayesian joint approaches and computationally efficient coding packages to integrate existing longitudinal data in order to account for biases inherent in observational data from life-course epidemiology studies. The proposed approaches will enable causal inference on joint exposure effects and mediation analysis to inform policy for environmental exposures in mid-life in order to prevent late-life outcomes, such as Alzheimer’s disease and related dementias.

Principal Investigator(s)

• Linda Valeri, PhD

Team Member(s)

• Astrid Suchy-Dicey, PhD
  Co-Investigator

Focus Areas

• Bayesian methods
• causal inference
• neuroepidemiology