Half replicates

Figure 14.4 A one-half replicate of the three-factor two-level full factorial design shown in Figure 14.2. The open circle locates the center of the design.

It is possible to selectively choose a subset of 4 of the original 8 factor combinations and use these to fit the reduced model with 100% efficiency. The resulting design is called a fractional factorial design . A full 2 factorial design has two half-replicates as shown in Figures 14.4 and 14.5, or in cube plot form as ... 

Consider the half-replicate taken from the following 2 full factorial design (those experiments marked by arrows are taken) ... 

A five-factor central composite design consists of the five-factor, two-level factorial, with the centre point and with the star pattern in all five variables. This would ordinarily call for running 32 4- 10 + 4-1-43 conditions, with some replication at the centre. Usually, the half replicate of the factorial plus the star points and centre is enough to give an adequate picture of the relationships. 

Five-factor central composite, half replicate and star points. 

Block l Half replicate of factorial design and centre point. 

Table 6. Design and data for half-replicate of Williams experiment.

A series of 20 statistically-designed experiments were made varying five operating variables (at two levels with a half replicate of the statistical design). The variables and levels investigated are as follows ... 

The significance of the effect of any of the interactions between the variables could not be estimated using the half replicate because of confounding. 

I. Mohmood and H. Mahayni, A limited sampling approach in bioequivalence studies application to long half life drugs and replicate design studies, Int. J. Clin. Ther, 37, 275 (1999). 

Whether the DNA replication checkpoint directly affects the Plxl activation pathway for Cdc25C has not yet been established. It is possible that the replication checkpoint arrests the cell cycle prior to initiation of the Plxl kinase cascade. Further characterization of upstream components of the cascade should reveal whether it is directly regulated by replication checkpoint activation. Such a characterization will also have importance for other M phase events, inasmuch as Plxl also regulates bipolar spindle formation, APC activation and cytokinesis (Qian et al 1998, 1999). These multiple functions of Plxl are associated with changes in localization of Plxl, and are most likely mediated by protein—protein interaction with the polo box motif in the non-catalytic C-terminal half of Plxl. 

Marc Van Regenmortel I m trying to apply your idea to viruses and their replication. If you have a single-strand virus, lets call it plus , it gives rise to a minus and plus double strand in your case it s a half picture which gives the full picture of the other half without material overlap or actually only half of the overlap. Then the negative strand is used to make more positive strands, and there is no material overlap anymore. Now how does that fit into your scheme ... 

As in all computer applications for the past few decades, P has been growing exponentially with time. It is a straightforward calculation to show that in the 21 years between the BPTI simulation (t = KTns n 600) and the villin headpiece simulation (t = KT6 s n 12 000), P has been increasing by a factor of 10 every 3-4 years. A simple extrapolation would thus predict that a simulation covering the replication cyde of an intact E. coli with a volume of about 1 p3 (t 1000 s n=3x 1010) could be expected some time in the second half of the next century if computational power continued to grow exponentially at historical rates. 

Fig. 94 - LSD Replication of Aghajanian and Bing s half-life estimate using inhalation plasma levels (n=40)...

---