Estimation of hidden carriers of infectious diseases

We consider the general problem of estimating missing information in a given dataset. We focus specifically on the problem of estimating the asymptomatic segment of the population that is COVID-19 infected, given datasets for which subjects have self-selected to be tested, that is, the data do not comprise a random sample. We present several methods to estimate the number of persons infected with COVID-19 that are not captured by traditional methods. We first present a simple comparison of incidence numbers between datasets with varying levels of completion, approximating different degrees of random sampling. We then use the Chao estimator to obtain a ratio of total cases to observed cases. Finally, we employ several other methods to compare against those results, such as a second order jackknife, a SAIRS epidemic model, and an incidence rate.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Industrial Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Hoff, Vincent

Contributors dc:contributor

• Beck, Carolyn L.

• COVID-19
• pandemic
• infectious diseases
• chao estimator
• bootstrap
• jackknife
• SAIRS

Statement dc:rights

• Copyright 2022 Vincent Hoff

Language dc:language

eng

Handle dc:identifier

https://hdl.handle.net/2142/115181

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/115181