主 题：Design and analysis of experiments--From traditional experiments to modern high tech
主讲人：艾明要
主持人：林华珍教授
时 间：2013年11月1日（星期五）下午3：00-4：00
地 点：通博楼B212学术会议室
主办单位：统计学院（中心） 科研处
主讲人简介：
艾明要教授现为北京大学数学科学学院统计学教研室主任、教授、博士生导师,兼任中国数学会概率统计学会副秘书长，中国现场统计研究会理事、副秘书长，中国现场统计研究会试验设计专业委员会副主任，国际统计杂志《Journal of Statistical Planning and Inference》和《STAT》编委。
Abstract：Design and analysis of experiments is an indispensable tool for experimenters and one of the core topics of Statistics. In this talk, we first briefly review main design and modeling methods applied in agricultural and industrial experiments, and then shift to computer experiments popular in high tech fields. The significant difference of computer experiments from the traditional experiments is discussed and the related design and modeling of these experiments is also investigated. Some general frameworks are proposed for constructing nested and sliced space-filling designs in computer experiments for more flexible parameters in which the whole design and each slice not only achieve maximum stratification in univariate margins, but also achieve stratification in two- or more-dimensional margins. Compared with other designs, the new constructed designs have better space-filling property.
