The COVID-19 pandemic has affected all countries in the world and brings a major disruption in our daily lives. Estimation of the prevalence and contagiousness of COVID-19 infections may be challenging due to under-reporting of infected cases. For a better understanding of such pandemic in its early stages, it is crucial to take into consideration unreported infections. In this study we propose a truncation model to estimate the under-reporting probabilities for infected cases. Hypothesis testing on the differences in truncation probabilities, that are related to the under-reporting rates, is implemented. Large sample results of the hypothesis test are presented theoretically and by means of simulation studies. We also apply the methodology to COVID-19 data in certain countries, where under-reporting probabilities are expected to be high.
Truncation data analysis for the under-reporting probability in COVID-19 pandemic
Dai Hongsheng
;Restaino Marialuisa
2021-01-01
Abstract
The COVID-19 pandemic has affected all countries in the world and brings a major disruption in our daily lives. Estimation of the prevalence and contagiousness of COVID-19 infections may be challenging due to under-reporting of infected cases. For a better understanding of such pandemic in its early stages, it is crucial to take into consideration unreported infections. In this study we propose a truncation model to estimate the under-reporting probabilities for infected cases. Hypothesis testing on the differences in truncation probabilities, that are related to the under-reporting rates, is implemented. Large sample results of the hypothesis test are presented theoretically and by means of simulation studies. We also apply the methodology to COVID-19 data in certain countries, where under-reporting probabilities are expected to be high.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.