Theory Experimental Design

W. J. Diamond, Practica/ Experimenta/ Designs for Engineers and Scientists, 2nd ed.. Van Nostrand Reinhold, New York, 1989. "This book is for engineers and scientists with Httie or no statistical background who want to learn to design efficient experiments and to analyze data correctiy. .. The emphasis is on practical methods, rather than on statistical theory." The discussion is quite detailed in some areas, eg, experimental designs based on Hadamard matrices, and scanty in others. 

This section is primarily concerned with the behaviour of simple homo-polymers. The development of viscoelastic theory was intimately linked with the study of polymeric species. This area of activity has led the way in the development of rheological models and experimental design and so is a very important area for the proto-rheologist to understand. So far in this chapter we have taken the approach of developing phase diagrams from a rheological perspective in order to understand linear viscoelastic... 

Essentially all of the engineering thermodynamic correlations used in pollution control models and synthesis gas phase equilibria, chemical equilibria, and enthalpy calculation schemes have their foundations in fundamental theory. Experimental data, in addition to being directly useful to designers, allows the correlation developer to assess the validity and suitability of his model. Included within the third section (Properties of Aqueous Solutions—Theory, Experiment, and Prediction) are chapters providing both comprehensive reviews and detailed descriptions of specific areas of concern in the theory and properties of aqueous solutions. 

Traditionally, the progress in dynamics has been achieved by a synergetic experimental-theoretical approach where the questions which were being raised by new experimental capabilities stimulated the development of theoretical tools. In a complementary fashion, suggestions by the theory as to hitherto unexplored effects were addressed by new experimental designs. 

Hailing, P.J., Thermodynamic predictions for biocatalysis in nonconventional media theory, tests, and recommendations for experimental design and analysis. Enzyme Microb. TechnoL, 1994,16, 178-206. 

Optimal design theory provides an alternative approach to the selection of an experimental design. For a description of the theory of optimal design see, for example, Atkinson and Donev [22]. 

Furthermore, optimal design theory assumes that the model is true within the region defined by the candidate design points, since the designs are optimal in terms of minimizing variance as opposed to bias due to lack-of-fit of the model. In reality, the response surface model is only assumed to be a locally adequate polynomial approximation to the truth it is not assumed to be the truth. Consequently, the experimental design chosen should reflect doubt in the validity of the model by allowing for model lack-of-fit to be tested. 

For our validations, a CVp is a pooled estimate calculated from the particular type of statistical data set (36 samples) described earlier in the Statistical Experimental Design section of this report. A statistical procedure is given in Hald JL for determining an upper confidence limit for the coefficient of variation. This general theory had o be adapted appropriately for application to a pooled CVp estimate. For this design, and under the stated assumptions, there is a one-to-one correspondence between values of CVp and upper confidence limits for CVp. Therefore, the confidence limit criterion given above is equivalent to another criterion based on the relationship of CVp and its critical value. The... 

The techniques involved in the analysis of variance will differ somewhat for each particular experimental design. Brownlee (Industrial Experimentation) [l] handles many of these variations in a readable cookbook style and is recommended for the practitioner who wants to know how to , but not necessarily how come . More of the background theory can be found in Davies [4], Dixon and Massey [Si, and Cochran and Cox 13). For our purposes, let us go through a typical example. 

Shortly after Ochoa s studies, Sam Weiss began a search for a DNA-directed RNA polymerase. His experimental design was influenced by the theory that RNA must be made on a DNA template if it is to carry the genetic message. He was also influenced by Komberg s discovery that DNA synthesis required nucleoside triphosphates for substrates rather than nucleoside diphosphates. With crude liver extracts, Weiss was able to demonstrate a capacity for RNA synthesis that was severely inhibited by DNase. Weiss s results touched off systematic investigations of RNA metabolism in many laboratories. A continuous expansion of research effort from that time on has yielded a wealth of understanding about the transcription process and related aspects of RNA metabolism. 

Although factorial designs are very useful for studying multiple variables at various levels, typically they will not be applicable to cosolvent solubility studies because of the constraint that all of the components must add to 100%. Forthis reason, mixtures of experimental designs are typically used. The statistical theory behind mixture designs has been extensively published [81-85], There... 

Based on previous testing of the research subject, the design of the full factorial experiment 23 with one replication to determine experimental error has been chosen. To eliminate the influence of systematic error in doing the experiment, the sequence of doing design point-trials, in accord with theory of design of experiments, has been completely random. The outcomes are given in Table 2.107. 

Experimental design and analysis have become essential because of the greater detail in modem biological theories and the complexities in treatments of disease. The clinician is usually interested in small, but biologically important, treatment effects that can be obscured by uncontrolled natural variation and bias in non-rigorous studies. This places well-performed clinical trials at the very center of clinical research today (pp. 9-10). 

---