tetano
Editor, Senior Moderator
Sci Rep. 2019 Nov 25;9(1):17472. doi: 10.1038/s41598-019-53908-6. [h=1]Multivariate nonparametric chart for influenza epidemic monitoring.[/h]
Liu L[SUP]1[/SUP], Yue J[SUP]2[/SUP], Lai X[SUP]3[/SUP], Huang J[SUP]4[/SUP], Zhang J[SUP]5[/SUP].
[h=3]Author information[/h] 1 School of Mathematics and V.C. & V.R. Key Lab, Sichuan Normal University, Chengdu, China. 2 School of Mathematics, Sichuan University of Arts and Science, Dazhou, China. 3 School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China. laixin@xjtu.edu.cn. 4 School of Geosciences, China University of Petroleum(East China), Qingdao, China. 5 School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, China.
[h=3]Abstract[/h] Control chart methods have been received much attentions in biosurvillance studies. The correlation between charting statistics or regions could be considerably important in monitoring the states of multiple outcomes or regions. In addition, the process variable distribution is unknown in most situations. In this paper, we propose a new nonparametric strategy for multivariate process monitoring when the distribution of a process variable is unknown. We discuss the EWMA control chart based on rank methods for a multivariate process, and the approach is completely nonparametric. A simulation study demonstrates that the proposed method is efficient in detecting shifts for multivariate processes. A real Japanese influenza data example is given to illustrate the performance of the proposed method.
PMID: 31767888 DOI: 10.1038/s41598-019-53908-6
Liu L[SUP]1[/SUP], Yue J[SUP]2[/SUP], Lai X[SUP]3[/SUP], Huang J[SUP]4[/SUP], Zhang J[SUP]5[/SUP].
[h=3]Author information[/h] 1 School of Mathematics and V.C. & V.R. Key Lab, Sichuan Normal University, Chengdu, China. 2 School of Mathematics, Sichuan University of Arts and Science, Dazhou, China. 3 School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China. laixin@xjtu.edu.cn. 4 School of Geosciences, China University of Petroleum(East China), Qingdao, China. 5 School of Mathematical Sciences, University of Electronic Science and Technology of China, Chengdu, China.
[h=3]Abstract[/h] Control chart methods have been received much attentions in biosurvillance studies. The correlation between charting statistics or regions could be considerably important in monitoring the states of multiple outcomes or regions. In addition, the process variable distribution is unknown in most situations. In this paper, we propose a new nonparametric strategy for multivariate process monitoring when the distribution of a process variable is unknown. We discuss the EWMA control chart based on rank methods for a multivariate process, and the approach is completely nonparametric. A simulation study demonstrates that the proposed method is efficient in detecting shifts for multivariate processes. A real Japanese influenza data example is given to illustrate the performance of the proposed method.
PMID: 31767888 DOI: 10.1038/s41598-019-53908-6