Abstract
We apply tools from functional data analysis to model cumulative trajectories of COVID-19 cases across countries, establishing a framework for quantifying and comparing cases and deaths across countries longitudinally. It emerges that a country’s trajectory during an initial first month “priming period” largely determines how the situation unfolds subsequently. We also propose a method for forecasting case counts, which takes advantage of the common, latent information in the entire sample of curves, instead of just the history of a single country. Our framework facilitates to quantify the effects of demographic covariates and social mobility on doubling rates and case fatality rates through a time-varying regression model. Decreased workplace mobility is associated with lower doubling rates with a roughly 2 week delay, and case fatality rates exhibit a positive feedback pattern.
Highlights
We apply tools from functional data analysis to model cumulative trajectories of COVID-19 cases across countries, establishing a framework for quantifying and comparing cases and deaths across countries longitudinally
For the 64 countries in the study, case counts per million generally follow one of four paths over time. They are either (1) consistently higher than average (e.g., Switzerland), (2) consistently lower than average (e.g., India), (3) initially lower but experience a dramatic increase over time, or (4) initially higher before entering a period of control (e.g. Slovenia). These archetypes are derived from the extreme ends of the two main modes of v ariation[29,30] observed for the sample, which emerge from functional principal component analysis (FPCA, Fig. 2)
Functional principal component analysis (FPCA) is similar to ordinary principal component analysis in the sense that it projects high dimensional curve data into a low dimensional space, representing them as a random vector of functional principal component (FPC) scores, as seen in Fig. 2a
Summary
We apply tools from functional data analysis to model cumulative trajectories of COVID-19 cases across countries, establishing a framework for quantifying and comparing cases and deaths across countries longitudinally. Statistical inquiries have focused on estimation of doubling rates, and case fatality rates with SIRD and SEIM models[3,4], which are compartmental epidemiological models. A related approach focused on the real-time estimation of case fatality rates using Poisson mixture models[15] Our analysis complements these studies and introduces an alternative way of obtaining relevant dynamic quantities, associating metrics of disease progression with baseline covariates across many countries. It should be noted that COVID-19 analyses based on published case and death counts, including those conducted here, are subject to the same biases which affect the accuracy of the data, primarily due to underreporting[21], the degree of which varies by c ountry[22] The reasons for such under-reporting are many, including insufficient testing materials, political incentives, and administrative delays.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
