Assessing Excess Mortality in Times of Pandemics Based on Principal Component Analysis of Weekly Mortality Data -- The Case of COVID-19

TL;DR

This paper introduces a novel statistical approach combining PCA and demographic models to accurately estimate excess mortality during pandemics, accounting for long-term trends and correlations, demonstrated through COVID-19 data from 19 countries.

Contribution

It develops a comprehensive model integrating PCA with a Lee-Carter type approach to improve excess mortality estimation during pandemics.

Findings

The model effectively captures long-term mortality trends.

It accounts for correlations among demographic groups.

It provides realistic excess mortality estimates during COVID-19.

Abstract

The current outbreak of COVID-19 has called renewed attention to the need for sound statistical analysis for monitoring mortality patterns and trends over time. Excess mortality has been suggested as the most appropriate indicator to measure the overall burden of the pandemic on mortality. As such, excess mortality has received considerable interest during the first months of the COVID-19 pandemic. Previous approaches to estimate excess mortality are somewhat limited, as they do not include sufficiently long-term trends, correlations among different demographic and geographic groups, and the autocorrelations in the mortality time series. This might lead to biased estimates of excess mortality, as random mortality fluctuations may be misinterpreted as excess mortality. We present a blend of classical epidemiological approaches to estimating excess mortality during extraordinary events with an established demographic approach in mortality forecasting, namely a Lee-Carter type model, which covers the named limitations and draws a more realistic picture of the excess mortality. We illustrate our approach using weekly age- and sex-specific mortality data for 19 countries and the current COVID-19 pandemic as a case study. Our proposed model provides a general framework that can be applied to future pandemics as well as to monitor excess mortality from specific causes of deaths.