This project explores the validity of standard risk factor assessment methods used in epidemiology when the risk factors involved affect the transmission of an infectious agent. In that case an assumption intrinsic to the most common uses of risk ratios, risk differences, and other parameters relating exposure to disease such as logistic regression coefficients is violated. That assumption is that the outcome of exposure in one individual is independent of the outcome of exposure in other individuals. Most epidemiologists do not realize that violation of this assumption can cause severe distortion of risk factor assessments. This project will define when, where, and how such distortions arise and what we can do about them.

Group Members:

Jim Koopman, Professor of Epidemiology

Andrew Adams, Software Engineer and Computer Simulation Scientist

Linnette Rodriguez, Doctoral student in Epidemiology

Matt Conaway, Masters student in Epidemiology

Purpose, Overview, Background, Objectives

Retrospective Partner Design to Assess STD Risk Factors: A project which Matt Conaway might undertake

First Protocol, Comments on preliminary First Protocol Results