摘要
本文通过国内的二组、韩国一组新型冠状病毒肺炎潜伏期数据,通过两种方法对这三组数据进行了拟合检验,认为都服从两参数BS疲劳寿命分布。针对多组两参数BS疲劳寿命分布,给出了参数相等的近似检验方法,就本文的三组潜伏期数据可以认为其参数是相同的,并得到了刻度参数β与形状参数α的点估计,进而求得了确诊病例在其暴露开始后的14天和21天内出现临床症状或检测试剂呈阳性的概率分别达到0.950213和0.993651,通过与已有文献相应结果的比较,发现两参数BS疲劳寿命分布来拟合潜伏期比Weibull分布与对数正态分布更合适、更具有优势,这与当前的防控策略比较吻合。
On the basis of two sets of COVID-19 incubation period data from China and one set from Korea,they all follow two-parameter BS fatigue life distribution through two methods of fitting tests.The approximate test method for parameter equality is proposed for multi-group two-parameter BS fatigue life distribution,and it can be concluded that these three sets of incubation period data have the same parameters.Then the point estimates of scale parameter and shape parameter β and shape parameter αare obtained,and the probability of a confirmed case showing clinical symptoms or positive test reagents within 14 days and 21 days of the onset of exposure reaches respectively 0.950213 and 0.993651.Through the comparison with the corresponding results in existing literature,it can be found that it is more appropriate and advantageous to use two-parameter BS fatigue life distribution to fit the incubation period than Weibull distribution and Lognormal distribution,which is quite consistent with the current prevention and control strategies.
作者
徐昕怡
顾蓓青
XU Xin-yi;GU Bei-qing(Facility of Art and Science,University of Toronto,Toronto M5S2E8,Canada;School of Statistics and Information,Shanghai University of International Business and Economics,Shanghai 201620,China)
出处
《数理统计与管理》
CSSCI
北大核心
2022年第6期982-988,共7页
Journal of Applied Statistics and Management
基金
国家自然科学基金资助(11671264)。
