Two-level Experiment Plan with Fractionary Reply

Two-level Experiment Plan with Fractionary Reply 

To solve this problem where we have 3 unknowns, we can chose a type 2 CFE in which the XjX2 column will be the plan for X3. Table 5.19 gives CFE 2 whereas Table 5.20 shows the transformation of our problem into an FFE plan. Thus, from 

Using the experimental plan from Table 5.20 it is possible to estimate the constant terms and the three coefScients related to the linear terms from the regression relationship. 

Practically, we cannot a priori postulate the nullity of the effects of the interaction. Indeed, we can accept the fact that some or all of the effects of the interaction are insignificant according to the linear effects but these are present. Then, from a practical point of view, when the coefficients corresponding to the effects of interaction are not zero and when we have the coefficients obtained by a 2 i plan, it is dear that these last coefficients include the participation of interactions on the major linear partidpations into the process response. The estimators of the general or theoretical coeffidents are P, P, pf, P, P, Pf and consequently, we can write  

In order to complete the FFE we can add a new column which contains the multiplication XjX3 to Table 5.20. However, we observe that the elements of this multi- 

---