摘要
A supersaturated design is a design whose run size is not enough for estimating all the main effects represented by the columns of the design matrix. It is widely used in the preliminary stages of industrial statistics and other scientific experiments. In this paper, formulas for computing the E(s2) values of E(s2) optimal supersaturated designs with m = t(n - 1) ± e(e = 1 and 2) are given, and the accuracy and convenience of using these formulas are demonstrated by an example.
A supersaturated design is a design whose run size is not enough for estimating all the main effects represented by the columns of the design matrix. It is widely used in the preliminary stages of industrial statistics and other scientific experiments. In this paper, formulas for computing the E(s2) values of E(s2) optimal supersaturated designs with m = t(n - 1) ± e(e = 1 and 2) are given, and the accuracy and convenience of using these formulas are demonstrated by an example.
基金
This research was supported by the NNSF project 19771049 of China
