Abstract
This paper proposes an epidemic model-based approach to inference the
incubation period distribution of COVID-19 just utilizing the publicly
reported confirmed case number. This method can reduce the biases of
traditional survey-based methods, and it can be practiced without the
assumption of the shape of the incubation period’s distribution. The
most commonly studied metrics (e.g., expectation, median, and 95th
percentile) obtained from our estimated incubation period distribution
of COVID-19 are in line with current studies’ results. However, due to
the mathematical-model-based nature of this method, the inference
results are somewhat sensitive to the setting of parameters. Therefore,
this method should be practiced reasonably on the basis of a certain
understanding of the studied epidemic.