Predictive Modeling of County-level Contributing Factors to COVID-19 Propagation in the United States

Abstract: This work presents a methodology to systematically examine and quantify the relationship between predictors and the COVID-19 cases at county level. The main objective is to extract predictors that characterize different aspects of a county from publicly available data and investigate the relevance between the predictors and the COVID-19 cases so that we can predict the propagation of COVID-19 in the near future. For this purpose, we extract predictors in social economy, health, demography and mobility and use Pearson correlation coefficient and lasso regularization model to find non-redundant predictors that are highly correlated to COVID-19 cases. With these predictors, we formulate a fixed-effect regression model at county level to quantify the relationship. The results clearly show that the significant predictors selected and the model can capture the relationship well.

Advisor Information: Hui Yang, Ph.D. PI & Site Director: NSF Center for Health Organization Transformation Professor: Industrial and Manufacturing Engineering Affiliate Faculty: Bioengineering, Institute of Cyberscience, CIMP-3D Office: Leonhard 221, Tel: 814-865-7397 The Pennsylvania State University, University Park, PA 16802-1401 Email: huy25@psu.edu

Files

Metadata

Work Title Predictive Modeling of County-level Contributing Factors to COVID-19 Propagation in the United States
Access
Open Access
Creators
  1. Yidan Wang
Keyword
  1. COVID-19
  2. Correlation
  3. Lasso regularization
  4. Fixed-effect regression model
License CC0 1.0 (Public Domain Dedication)
Work Type Research Paper
Acknowledgments
  1. The US National Science Foundation (grant IIP-2026875)
Publication Date 2021
Deposited March 22, 2021

Versions

Analytics

Collections

This resource is currently not in any collection.

Work History

Version 1
published

  • Created
  • Updated Acknowledgments Show Changes
    Acknowledgments
    • The US National Science Foundation (grant IIP-2026875)
  • Added Creator Yidan Wang
  • Added Master_Paper_Yidan.pdf
  • Updated License Show Changes
    License
    • http://creativecommons.org/publicdomain/zero/1.0/
  • Published
  • Updated
  • Updated