Space-time Models for Inferring Infectious Disease Risk and Burden
Restricted (Penn State Only)
Author:
Li, Xiaoxiao
Graduate Program:
Statistics
Degree:
Doctor of Philosophy
Document Type:
Dissertation
Date of Defense:
June 01, 2022
Committee Members:
Ephraim Hanks, Professor in Charge/Director of Graduate Studies Matthew Ferrari, Outside Unit & Field Member Stephen Berg, Major Field Member Le Bao, Major Field Member Murali Haran, Chair & Dissertation Advisor
Keywords:
infectious disease space-time model disease transmission
Abstract:
Infectious diseases are a leading cause of death and have had a major impact on societies since the beginning of human civilization. Understanding infectious disease transmission is essential in strengthening disease surveillance, prevention and control. Given the increasing availability of rich spatial, temporal, and spatio-temporal epidemiological data, statistical methods are a powerful tool to study and uncover complex disease susceptibility and transmission mechanisms. My dissertation develops several statistical approaches for infectious diseases: (i) a new model for inferring the spatially varying risk of infectious disease susceptibility, developed in the context of a study of Foot-and-Mouth Disease in Turkey, (ii) individual-level spatial-varying classifiers of disease to provide better disease burden estimation using both clinical symptomatic surveillance data and diagnostic testing data in the context of measles burden estimation in Ethiopia, and (iii) a Hawkes self-exciting point process model that attempts to flexibly capture both background and transmission dynamics, thereby potentially characterizing the endemic or epidemic nature of an infectious disease.
