ABSTRACT
We estimate the distribution of COVID-19 mortality (measured as daily deaths) from the start of the pandemic until July 31st, 2022, for six European countries and the USA. We use the Pareto, the stretched exponential, the log-normal and the log-logistic distributions as well as mixtures of the log-normal and log-logistic distributions. The main results are that the Pareto does not describe well the data and that mixture distributions tend to offer a very good fit to the data. We also compute Value-at-Risk measures as well as mortality probabilities with our estimates. We also discuss the implications of our results and findings from the point of view of public health planning and modelling.
ABSTRACT
I use extreme values theory and data on influenza mortality from the U.S. for 1900 to 2018 to estimate the tail risks of mortality. I find that the distribution for influenza mortality rates is heavy-tailed, which suggests that the tails of the mortality distribution are more informative than the events of high frequency (i.e., years of low mortality). I also discuss the implications of my estimates for risk management and pandemic planning.
ABSTRACT
BACKGROUND: I use Benford's law to assess whether there is misreporting of coronavirus disease of 2019 (COVID-19) deaths in the USA. METHODS: I use three statistics to determine whether the reported deaths for US states are consistent with Benford's law, where the probability of smaller digits is greater than the probability of larger digits. RESULTS: My findings indicate that there is under-reporting of COVID-19 deaths in the USA, although the evidence for and the extent of under-reporting does depend on the statistic one uses to assess conformity with Benford's law. CONCLUSIONS: Benford's law is a useful diagnostic tool for verifying data and can be used before a more detailed audit or resource intensive investigation.