Improved prediction of new COVID-19 cases using a simple vector autoregressive model: evidence from seven New York state counties.
Biol Methods Protoc
; 8(1): bpac035, 2023.
Article
in English
| MEDLINE | ID: covidwho-2231951
ABSTRACT
With the rapid spread of COVID-19, there is an urgent need for a framework to accurately predict COVID-19 transmission. Recent epidemiological studies have found that a prominent feature of COVID-19 is its ability to be transmitted before symptoms occur, which is generally not the case for seasonal influenza and severe acute respiratory syndrome. Several COVID-19 predictive epidemiological models have been proposed; however, they share a common drawback - they are unable to capture the unique asymptomatic nature of COVID-19 transmission. Here, we propose vector autoregression (VAR) as an epidemiological county-level prediction model that captures this unique aspect of COVID-19 transmission by introducing newly infected cases in other counties as lagged explanatory variables. Using the number of new COVID-19 cases in seven New York State counties, we predicted new COVID-19 cases in the counties over the next 4 weeks. We then compared our prediction results with those of 11 other state-of-the-art prediction models proposed by leading research institutes and academic groups. The results showed that VAR prediction is superior to other epidemiological prediction models in terms of the root mean square error of prediction. Thus, we strongly recommend the simple VAR model as a framework to accurately predict COVID-19 transmission.
Full text:
Available
Collection:
International databases
Database:
MEDLINE
Type of study:
Experimental Studies
/
Observational study
/
Prognostic study
/
Randomized controlled trials
Language:
English
Journal:
Biol Methods Protoc
Year:
2023
Document Type:
Article
Affiliation country:
Biomethods
Similar
MEDLINE
...
LILACS
LIS