

7月9日 Partha Mukherjee( Boise State University)学术报告


发布时间： 20170705  
学术报告 报告题目：Phase II Monitoring of Big Data by Data Pruning 报告人：Partha Mukherjee （Associate Professor） 时 间：7月9日(星期日)上午 11:00 地 点：统计研究院426教室 摘 要： Statistical process control (SPC) charts are widely used in industry for monitoring the stability of certain sequential processes like manufacturing, health care systems etc. Most SPC charts assume that the parametric form of the “incontrol” process distribution $F_1$ is available. However, it has been demonstrated in the literature that their performances are unreliable when the prespecified process distribution is incorrect. Moreover, most SPC charts are designed to detect any shift in mean and/or variance. In real world problems, shifts in higher moments can happen without much change in mean or variance. If we fail to detect those and let the process run, it can eventually become worse and a shift in mean or variance can creep in. Moreover, the special cause which initiated that shift can inflict further damage to the system and can be more difficult to fix it. This talk considers the challenging problem of Phase II monitoring of univariate continuous processes when the parametric form of the “incontrol” process distribution is unknown, but substantial amount of Phase I observations that are believed to be i.i.d. realizations of $F_1$ is available. Although several statistical tests are available to check whether two groups of i.i.d. data are from the same distribution (e.g., KolmogorovSmirnov (KS) test), this SPC problem is still challenging, because if any shift in distribution occurs after a lot of “incontrol” Phase II observations, then we may need to have many “outofcontrol” Phase II data to statistically detect that shift, which should not be allowed to happen in real life big data applications. This talk addresses this issue by throwing away some parts of data from long past, depending on pvalues of the current KS test. 欢迎广大师生参加！ 统计研究院 



