Urban density and COVID-19: understanding the US experience

Abstract

This paper revisits the debate around the link between population density and the severity of COVID-19 spread in the USA. We do so by conducting an empirical analysis based on graphical evidence, regression analysis and instrumental variable strategies borrowed from the agglomeration literature. Studying the period between the start of the epidemic and the beginning of the vaccination campaign at the end of 2020, we find that the cross-sectional relationship between density and COVID-19 deaths changed as the year evolved. Initially, denser counties experienced more COVID-19 deaths. Yet, by December, the relationship between COVID deaths and urban density was completely flat. This is consistent with evidence indicating density affected the timing of the outbreak-with denser locations more likely to have an early outbreak-yet had no influence on time-adjusted COVID-19 cases and deaths. Using data from Google, Facebook, the US Census and other sources, we investigate potential mechanisms behind these findings.

Fig. 1

And Population Density and COVID-19 in 2020. Notes The horizontal axis represents the logarithm of the county’s population density. Top left panel vertical axis represents the logarithm of the accumulated number of fatalities per hundred thousand inhabitants by the 5th of July 2020. Top right panel vertical axis represents the logarithm of the accumulated number of fatalities per hundred thousand inhabitants by the 1st of December 2020. Bottom-left panel vertical axis represents the number of days between the 22nd of January and the first fatality in each county. Bottom-right panel vertical axis represents the logarithm of the number of dead 60 days after the 10th case was reported in the county. Black markers correspond to counties forming part of a CBSA. Fitted lines estimated via Ordinary Least Squares. Univariate R-squared included in all Figures alongside fitted line

Fig. 2

OLS Accumulated COVID-19 Deaths-Density Elasticities over Time. Notes Both panels depict the cross-sectional relationship between the natural logarithms of accumulated deaths and population density for every monthly period ending in the 15th, from March through December 2020. Panel A: coefficients from univariate OLS regressions. Panel B: IV estimates obtained using both the geological and historical instruments for density. For each estimate, we report the 95% confidence interval based on standard errors clustered at the CBSA level

Fig. 3

Changes in Mobility Relative to January Baseline (2020). Notes The figures plot the daily change and local regression curve (LOESS) over time in mobility relative to the January 2020 baseline for sparse counties and dense counties, with the split based on median weighted county density. The left panel refers to adjustment of workplace-related activity. The middle panel refers to leisure time activities including restaurants, cafes, shopping centers, theme parks, museums, libraries, and movie theaters. The right panel refers to transit including public transport hubs such as subway, bus, and train stations

Fig. 4

Sample counties, COVID-19 and population density

Fig. 5

Validating Covid-19 figures. Notes In the left panel, the vertical axis represents the log of the officially confirmed COVID-19 mortality rate per county by the CDC and the horizontal axis the COVID-19 mortality rate by USAFacts. The right panel plots the USAFacts state-level mortality rate (vertical axis) over the excess death estimates by the CDC (horizontal axis). Blue fit lines estimated via Ordinary Least Squares including the 95% confidence interval in gray

Fig. 6

Aggregate Daily Number of COVID-19 Deaths (2020). Notes Daily COVID-related deaths reported in the USA between February and the 15th of December 2020. Solid line represents moving average of daily deaths

Fig. 7

Cases and Deaths per 100,000 in First-Wave versus Weighted Density. Notes The horizontal axis represents the logarithm of the county’s population-weighted density. In the left panel, the vertical axis represents the logarithm of the number of cases per 100,000 inhabitants. In the right panel, the vertical axis represents the logarithm of the number of fatalities per thousand inhabitants. Black markers correspond to counties forming part of a CBSA. Black fit lines estimated via Ordinary Least Squares