tetano
Editor, Senior Moderator
Emerg Infect Dis
. 2021;27(3):767-778.
doi: 10.3201/eid2703.203364.
Daily Forecasting of Regional Epidemics of Coronavirus Disease with Bayesian Uncertainty Quantification, United States
Yen Ting Lin, Jacob Neumann, Ely F Miller, Richard G Posner, Abhishek Mallela, Cosmin Safta, Jaideep Ray, Gautam Thakur, Supriya Chinthavali, William S Hlavacek
Abstract
To increase situational awareness and support evidence-based policymaking, we formulated a mathematical model for coronavirus disease transmission within a regional population. This compartmental model accounts for quarantine, self-isolation, social distancing, a nonexponentially distributed incubation period, asymptomatic persons, and mild and severe forms of symptomatic disease. We used Bayesian inference to calibrate region-specific models for consistency with daily reports of confirmed cases in the 15 most populous metropolitan statistical areas in the United States. We also quantified uncertainty in parameter estimates and forecasts. This online learning approach enables early identification of new trends despite considerable variability in case reporting.
Keywords: Bayesian statistics; COVID-19; SARS-CoV-2; United States; compartmental model; coronavirus disease; epidemics; mathematical model; severe acute respiratory syndrome coronavirus 2; statistics; uncertainty; viruses; zoonoses.
Yen Ting Lin, Jacob Neumann, Ely F Miller, Richard G Posner, Abhishek Mallela, Cosmin Safta, Jaideep Ray, Gautam Thakur, Supriya Chinthavali, William S Hlavacek
Abstract
To increase situational awareness and support evidence-based policymaking, we formulated a mathematical model for coronavirus disease transmission within a regional population. This compartmental model accounts for quarantine, self-isolation, social distancing, a nonexponentially distributed incubation period, asymptomatic persons, and mild and severe forms of symptomatic disease. We used Bayesian inference to calibrate region-specific models for consistency with daily reports of confirmed cases in the 15 most populous metropolitan statistical areas in the United States. We also quantified uncertainty in parameter estimates and forecasts. This online learning approach enables early identification of new trends despite considerable variability in case reporting.
Keywords: Bayesian statistics; COVID-19; SARS-CoV-2; United States; compartmental model; coronavirus disease; epidemics; mathematical model; severe acute respiratory syndrome coronavirus 2; statistics; uncertainty; viruses; zoonoses.
. 2021;27(3):767-778.
doi: 10.3201/eid2703.203364.
Daily Forecasting of Regional Epidemics of Coronavirus Disease with Bayesian Uncertainty Quantification, United States
Yen Ting Lin, Jacob Neumann, Ely F Miller, Richard G Posner, Abhishek Mallela, Cosmin Safta, Jaideep Ray, Gautam Thakur, Supriya Chinthavali, William S Hlavacek
- PMID: 33622460
- DOI: 10.3201/eid2703.203364
Abstract
To increase situational awareness and support evidence-based policymaking, we formulated a mathematical model for coronavirus disease transmission within a regional population. This compartmental model accounts for quarantine, self-isolation, social distancing, a nonexponentially distributed incubation period, asymptomatic persons, and mild and severe forms of symptomatic disease. We used Bayesian inference to calibrate region-specific models for consistency with daily reports of confirmed cases in the 15 most populous metropolitan statistical areas in the United States. We also quantified uncertainty in parameter estimates and forecasts. This online learning approach enables early identification of new trends despite considerable variability in case reporting.
Keywords: Bayesian statistics; COVID-19; SARS-CoV-2; United States; compartmental model; coronavirus disease; epidemics; mathematical model; severe acute respiratory syndrome coronavirus 2; statistics; uncertainty; viruses; zoonoses.
Yen Ting Lin, Jacob Neumann, Ely F Miller, Richard G Posner, Abhishek Mallela, Cosmin Safta, Jaideep Ray, Gautam Thakur, Supriya Chinthavali, William S Hlavacek
- PMID: 33622460
- DOI: 10.3201/eid2703.203364
Abstract
To increase situational awareness and support evidence-based policymaking, we formulated a mathematical model for coronavirus disease transmission within a regional population. This compartmental model accounts for quarantine, self-isolation, social distancing, a nonexponentially distributed incubation period, asymptomatic persons, and mild and severe forms of symptomatic disease. We used Bayesian inference to calibrate region-specific models for consistency with daily reports of confirmed cases in the 15 most populous metropolitan statistical areas in the United States. We also quantified uncertainty in parameter estimates and forecasts. This online learning approach enables early identification of new trends despite considerable variability in case reporting.
Keywords: Bayesian statistics; COVID-19; SARS-CoV-2; United States; compartmental model; coronavirus disease; epidemics; mathematical model; severe acute respiratory syndrome coronavirus 2; statistics; uncertainty; viruses; zoonoses.