A mean squared error criterion for the design of experiments
A mean squared error criterion for the design of experiments
复制标题
DOI：
10.1093/biomet/70.1.205
复制
发表时间：
1983-04
期刊：
影响因子：
2.7
通讯作者：
W. Welch
中科院分区：
文献类型：
--
作者：
W. Welch
在估计感兴趣的设计区域上的响应曲面时，均方误差可能来自采样方差和模型不足引起的偏差。这里采用的实验设计的标准试图防止偏差所造成的一大类偏离假设的模型。提出了构造近似设计和精确设计的两种算法，并给出了一个例子。
In estimating a response surface over a design region of interest, mean squared error can arise both from sampling variance and bias introduced by model inadequacy. The criterion adopted here for experimental design attempts to protect against bias resulting from a large class of deviations from the assumed model. Two algorithms are proposed for the construction of either approximate or exact designs and an example is given.