Review of Economics and Statistics · 2023 · Mu‐Jeung Yang、Marinho Bertanha、Nathan Seegert、Maclean Gaulin、Adam Looney、Brian Orleans
中文摘要
我们提出了一种实时追踪COVID-19现患率的方法，该方法校正了基于症状的检测数据中随时间变化的样本选择偏误，以及对康复病例和死亡病例追踪不完整的问题。该方法只需将公开可得的检测阳性率数据与一个参数结合使用；我们基于2020年5月和6月在犹他州对近10,000名受检者开展的代表性随机抽样来估计这一参数。我们利用2020年4月在印第安纳州开展的外部研究以及2021年3月在犹他州两个县开展的外部研究验证了该方法。在上述三个地点和时点，我们对潜在现患率的估计均落在随机检测所得现患率估计的95%置信区间内。将该方法应用于美国全部50个州后，我们发现真实现患率是公开报告水平的2至3倍。
Abstract
Abstract We provide a method to track the active prevalence of COVID-19 in real time, correcting for time-varying sample selection in symptom-based testing data and incomplete tracking of recovered cases and fatalities. Our method only requires publicly available data on positive testing rates in combination with one parameter, which we estimate based on a representative randomized sample of nearly 10,000 individuals tested in Utah in May and June 2020. We validate our method using external studies in Indiana in April 2020 and two counties in Utah in March 2021. In all three locations and times, our estimates of latent prevalence are within the 95 percent confidence intervals of prevalence estimates from randomized testing. Applying our method to all 50 states, we show that true prevalence is 2–3 times higher than publicly reported.