Introduction to Statistical Mediation Analysis & Application to Epigenetic Data by Jack Napeloni '25

Introduction to Statistical Mediation Analysis and Application to Epigenetic Data by Jack Napeloni ’25, Wednesday November 20, 1:00 – 1:50pm, North Science Building 015, Wachenheim, Statistics Colloquium

Abstract:

Mediation Analysis is a statistical approach used to explore the relationship between an independent variable and an outcome through a third intermediate variable, known as the mediator. The goal of mediation analysis is to quantify the effects of an independent variable on an outcome through both the direct effect (how X affects Y) and indirect effect (how X affects M, which then affects Y) in both single and multiple mediation models. Mediation models are heavily employed in fields such as health sciences and psychology to uncover the effects of treatment on outcomes through effective mediators. In this talk, I will introduce the model, estimation, and interpretation of the simple and multi-mediator mediation models. I will also discuss tools and methods for mediation selection in a complex setting with applications to an epigenetic study.