Design of the experiment

Recognizing this is essential in the design of experiments and analysis of the results. The rapid pace of improvements and iimovation in electronic devices and computers have provided die experimenter with electronic solutions to experimental problems diat in the past could only be solved with custom hardware. 

C. R. Hicks, Fundamental Concepts in the Design of Experiments, Holt, Reinhart and Winston, New York, 1973. 

Design of experiments. When conclusions are to be drawn or decisions made on the basis of experimental evidence, statistical techniques are most useful when experimental data are subject to errors. The design of experiments may then often be carried out in such a fashion as to avoid some of the sources of experimental error and make the necessary allowances for that portion which is unavoidable. Second, the results can be presented in terms of probability statements which express the reliabihty of the results. Third, a statistical approach frequently forces a more thorough evaluation of the experimental aims and leads to a more definitive experiment than would otherwise have been performed. 

There is an entire discipline of Experimental Design that is devoted to the art and science of determining what should be in a training set. A detailed exploration of the Design of Experiments (DOE, or experimental design) is beyond the scope of this book. Please consult the bibliography for publications that treat this topic in more detail. 

Statistical benefit Using statistical methods in the design of experiments and data analy-... 

It is also possible to process copolymer composition data to obtain reactivity ratios for higher order models (e.g. penultimate model or complex participation, etc.). However, composition data have low power in model discrimination (Sections 7.3.1.2 and 7.3.1.3). There has been much published on the subject of the design of experiments for reactivity ratio determination and model discrimination.49 "8 136 137 Attention must be paid to the information that is required the optimal design for obtaining terminal model reactivity ratios may not be ideal for model discrimination.49... 

Reference to this oxide is included here to indicate a possible complication that may appear in kinetic and mechanistic studies of sublimation-type reactions, since the vacuum dissociation of V2Os has been shown [655] to produce a variety of molecular entities V4Oi0, V6014, V6012, V408 and V204. Allowance for the complexity of the product mixture must be made in the design of experiments. 

The experimental basis for the model should span a broader range of the independent variables than will be encountered in the use of the model. To develop a comprehensive model, it is often necessary to add components to the feed in amounts that would not normally be present. For A —> B, the concentration of B is correlated to that of A aj — a = b — bi . Varying bin wiU lessen the correlation and will help distinguish between rate expressions such 2i 01 = ka ox 01 = kfa — krb ox 01 = ka/ + ksb). Books and courses on the design of experiments can provide guidance, although our need for formalized techniques is less than that in the social and biological sciences, where experiments are much more difficult to control and reproduce. 

Different kinds of experimental procedures have been used and these should be evaluated against the background in which several organisms or several substrates are simultaneously present. There are no essential differences in the design of experiments using pure cultures and those employing metaboli-cally stable consortia. It should be emphasized, however, that even in the latter, the experiments should be carried out under aseptic conditions otherwise, interpretation of the results may be compromised by adventitious organisms. 

Sensitivity analysis is a very important tool in analysing the relative importance of the model parameters and in the design of experiments for their optimal determination. In many cases, it is be found that a model may be rather insensitive to a particular parameter value in the region of main interest, and then the parameter obviously does not need to be determined very accurately. 

Procedures on how to make inferences on the parameters and the response variables are introduced in Chapter 11. The design of experiments has a direct impact on the quality of the estimated parameters and is presented in Chapter 12. The emphasis is on sequential experimental design for parameter estimation and for model discrimination. Recursive least squares estimation, used for on-line data analysis, is briefly covered in Chapter 13. 

Fisher RA (1935) The design of experiments. Oliver Boyd, Edinburgh (7th edn 1960 9th edn 1971, Hafner Press, New York)... 

The factorial approach to the design of experiments allows all the tests involving several factors to be combined in the calculation of the main effects and their interactions. For a 23 design, there are 3 main effects, 3 two-factor interactions, and 1 three-factor interaction. Yates algorithm can be used to determine the main effects and their interactions (17). The data can also be represented as a multiple linear regression model... 

Joseph F. Louvar retired as director of BASF s Chemical Engineering Department to become a professor at Wayne State University, specializing in chemical process safety, risk assessment, and the design of experiments. He has authored many publications on process safety and chairs the Undergraduate Education Committee of the CCPS. 

A second concept and its understanding are essential to the design of experiments in toxicology, that of censoring. Censoring is the exclusion of measurements from certain experimental units, or indeed of the experimental units themselves, from... 

Much is known about the lifetimes of carbocation intermediates of solvolysis, and these data have proven critical in the design of experiments to estimate absolute rate constants for reorganization of ion pairs. Consider reorganization of an ion-pair reaction intermediate that exchanges the positions of the nucleophilic atoms of the leaving group (, Scheme 9) and that occurs in competition with diffusional separation to free ions (k-d) which is much faster than addition of solvent to the ion pair. Ion-pair separation is irreversible and will result in formation of solvolysis reaction products s ). Reorganization of the ion pair will result in formation of isomerization reaction product and the yield of this reaction product will provide a measure of the relative rate constant... 

The design of experiments to test the validity of a dynamic model can sometimes be a real challenge and should be carefrjlly thought out. We will talk... 

Structure. Simulation of rocking curves is an extremely powerful method of interpretation of complex stractures. In addition, it is veiy valuable for the design of experiments, optimisation of data collection strategy and education of new researchers and operators in high resolution diffractometiy. 

Mauritz summarized a number of molecular models of ionomer structure, including those pertaining to Nafion, that had had been formulated up to 1996. Within the context of the title of this review, it should be appreciated that the results contribute to the state of understanding only if they are verifiable by careful experimentation. To be sure, theoretical predictions are welcome in the design of experiments and pointing the way toward useful applications. 

Although our purpose in introducing the subject of data treatment has been to provide insight into the design of experiments, the technique of least squares (regression analysis) is often used to fit models to data that have been acquired by observation rather than by experiment. In this chapter we discuss an example of regression analysis applied to observational data. 

We do not believe that a course on the design of experiments must necessarily be preceded by a course on statistics. Instead, we have taken the approach that both subjects can be developed simultaneously, complementing each other as needed, in a course that presents the fundamentals of experimental design. 

The classic texts on the design of experiments in scientific and engineering studies emphasize (1) measurement and instrumentation, (2) sources of error, (3) factor design etc. [30, 31] This section addresses step-by-step many of these issues for in situ studies, and does so by integrating relevant chemical and chemical engineering concerns and concepts. This section attempts to provide a very useful short-list of design considerations for the experimentalist so that Eq. (2) can be solved. 

---