报告题目：Statistical estimation and regression for infectious disease outcomes
报 告 人: Forrest W. Crawford, Assistant Professor
Many infectious diseases seem to cluster in households, but traditional regression methods for dealing with clustered data do not account for transmission. Likewise, traditional epidemic models of contagion do not permit adjustment for measured individual-level characteristics. In this presentation, I outline a class of infectious disease regression models that permit simultaneous estimation of the within-household and community force of infection and allow individual- and household-level covariates. The approach is motivated by construction of a continuous-time stochastic epidemic process, which is shown to be a generalization of Poisson regression. The approach translates to the network setting in an easy way. I apply these methods to a large study of household tuberculosis in Lima, Peru, and conclude with new ideas about adjusting for possible confounding in causal inference for contagious outcomes.
Forrest W. Crawford PhD is affiliated with the Center for Interdisciplinary Research on AIDS, the Institute for Network Science, and the Computational Biology and Bioinformatics program. He is the recipient of the NIH Director's New Innovator Award and a Yale Center for Clinical Investigation Scholar Award. His research interests include networks, graphs, stochastic processes, and optimization for plications in epidemiology, public health, and social science.