An Ecological Study Assessing the Relationship between Public Health Policies and Severity of the COVID-19 Pandemic

Abstract

Reliance on government-led policies have heightened during the COVID-19 pandemic. Further research on the policies associated with outcomes other than mortality rates remains warranted. We aimed to determine associations between government public health policies on the severity of the COVID-19 pandemic. This ecological study including countries reporting ≥25 daily COVID-related deaths until end May 2020, utilised public data on policy indicators described by the Blavatnik school of Government. Associations between policy indicators and severity of the pandemic (mean mortality rate, time to peak, peak deaths per 100,000, cumulative deaths after peak per 100,000 and ratio of mean slope of the descending curve to mean slope of the ascending curve) were measured using Spearman rank-order tests. Analyses were stratified for age, income and region. Among 22 countries, containment policies such as school closures appeared effective in younger populations (r_s = -0.620, p = 0.042) and debt/contract relief in older populations (r_s = -0.743, p = 0.009) when assessing peak deaths per 100,000. In European countries, containment policies were generally associated with good outcomes. In non-European countries, school closures were associated with mostly good outcomes (r_s = -0.757, p = 0.049 for mean mortality rate). In high-income countries, health system policies were generally effective, contrasting to low-income countries. Containment policies may be effective in younger populations or in high-income or European countries. Health system policies have been most effective in high-income countries.

Keywords: COVID-19; ecological study; public health.

Figure 2

Key to visual interpretation of Table 2, Table 3, Table 4, Table 5, Table 6 and Table 7. The strength of association can be visualised using the colour gradient denoted above where a more saturated green represents a stronger association to a good outcome, and darker red represents a stronger association to a bad outcome. In contrast, the lighter the shades of red or green, the closer the representation to having no association with the outcome (white).

Figure 1

Derivation of parameters for outcome measures from daily mortality data, using data from the United Kingdom as an example.