Cross design

Fig. 6. Error structure of HTS results. This figure shows how the reproducibility of activity data varies with differences in activity. The circles represent compounds designated as inactive and crosses designate active compounds. From this figure it is obvious that assay variability is closest at the cutoff between active and inactive compounds.

Note that even if the environmental variables are at two levels so that a 2 fractional factorial design can be run for the Taguchi environmental array, the complete crossed design has 9x8 = 72 runs, still more than the Box-Behnken design of Table 2.12, while providing estimates of fewer coefficients of the second-order model. 

Full Factorial Combined with Mixture Design-Crossed Design I 543... 

An integrated poly(dimethylsiloxane), PDMS, microchip for SPE and CE followed by ESl/TOF MS has been developed and evaluated by Dahlin and coworkers [122]. The microchip (see Fig. 7) was fabricated in a two-level cross design with PDMS cast over steel wires. Following PDMS polymerization and removal of the wires, 50 pm... 

Figure 8.15. Diagram of a simple cross design for electrophoresis on a microchip (left) and illustration of cross injection and double-T injection systems (right).

The termfactorial design which can also be called combination design or crossed design [1] means that all combinations of factor levels are executed. It is an efficient approach when two or more factors are considered because factor interactions can be estimated. However, the factorial design can be quite burdensome because it requires the experimenter perform all possible combinations of aU factor levels. For example, consider a process that has two factors and each factor has four and five levels, respectively, hi this case, a total of 20 combinations must be randomized and tested. 

---