We investigate the problem of estimating the distribution of the individual reproduction number governing the COVID-19 pandemic. Under the assumption that this random variable follows a Negative Binomial distribution, we focus on constructing estimators of the parameters of this distribution using reported infection data and taking into account issues like under-reporting or the time behavior of the infection and of the reporting processes. To this end, we extract information from regionally dissaggregated data reported by German health authorities, in order to estimate not only the mean but also the variance of the distribution of the individual reproduction number. In contrast to the mean, the latter parameter also depends on the unknown under-reporting rate of the pandemic. The estimates obtained allow not only for a better understanding of the time-varying behavior of the expected value of the individual reproduction number but also of its dispersion, for the construction of bootstrap confidence intervals and for a discussion of the implications of different policy interventions. Our methodological investigations are accompanied by an empirical study of the development of the COVID-19 pandemic in Germany, which shows a strong overdispersion of the individual reproduction number.
翻译:我们调查了有关COVID-19大流行的个人生殖号码分布的估计问题,假设这一随机变量是按负比量分布,我们的重点是利用报告的感染数据,并考虑到诸如报告不足或感染的时间行为以及报告过程等问题,来估计这种分布的参数;为此目的,我们从德国卫生当局报告的区域分解数据中提取信息,以便不仅估计个人生殖号码分布的平均值,而且估计个人生殖号码分布的差异;相反,后者的参数还取决于该流行病的未知的低报告率;获得的估计数不仅使人们更好地了解个人生殖号码预期价值的改变时间行为,而且了解其分散情况,以构建牢固的信心间隔,并讨论不同政策干预的影响;我们的方法调查伴随着对德国COVID-19大流行的发展进行实证研究,表明个人生殖号码的高度偏差。