Experimental Designs Part

The next several chapters will deal with the philosophy of experimental designs. Experimental design is at the very heart of the scientific method without proper design, it is well-nigh impossible to glean high-quality information from experimental data collected. No amount of sophisticated processing or chemometrics can create information not presented within the data. 

Every scientist has designed experiments. So what is there left for us to say about that topic that chemometrics/statistics can shed some light on Well, quite a bit actually, since not all experiments are designed equally, but some are definitely more equal than others (to steal a paraphrase). Another way to say it is that every experiment is a designed experiment, but some designs are better than others. 

In point of fact, the sciences of both statistics and chemometrics each have their own approach to how experiments should be designed, each with a view toward making experimental procedures better in some sense. There is a gradation between the two approaches, nevertheless there is also somewhat of a distinction between what might be thought of as classical statistical experimental design and the more currently fashionable experimental designs considered from a chemometric point of view. These differences in approach reflect differences in the nature of the information to be obtained from each. 

Experimental designs, and in particular statistical experimental designs, are used in order to achieve one or more of the following goals  

1) Increase efficiency of resource use, that is, obtain the desired information using the fewest possible necessary experiments (this is usually what is thought of when statistical experimental designs are considered). This aspect of experimentation is particularly important when the experiment is large to begin with, or if the experiment uses resources that are rare or expensive, or if the experiment is destructive, so that materials (especially expensive ones) are used up. 

---

Experimental Designs Part 4 - Varying Parameters to Expand the Design... 

Allen AM (1978) Clinical trial design in dermatology Experimental design, part I. Int I Dermatol 17 42-51 Bannan EA (1975) Personal communication. 

---