Experimental Design Process

Many developments have been made in the use of statistics to aid in experimental design over the last decades. The most important aspect of experimental design methods is that they provide a mathematical framework for changing all pertinent factors simultaneously, and achieve this in a small number of experiments. The description of such methods, though, is beyond the scope of this book and the reader is referred to the literature (Box et al., 1978 Bayne and Rubin, 1986 Haaland, 1989 Morgan, 1991) or to the internet for the latest design software (e. g. StatSoft, 1999). 

To help the reader identify the activity associated with each aspect on the more intuitive level, checklists are presented. They are not comprehensive, but can help the beginning experimenter get started. We have placed them at the beginning of Part B to give an overview of the information necessary for successful experimentation. Each reader will spend more or less time initially reading through the checklists. They can be returned to when the practical work is in the planning phase. It is important to use them critically, checking which points apply to the situation at hand and to modify and add appropriate points that have been missed. 

Decide what information is necessary to achieve the experimental goal(s). 

---

In experimental work, it is important to recognize that although accidents can be minimized, the nature of gaining new knowledge suggests that they can never be eliminated completely. Any good experimental design process should identify hazards and develop... 

Randomization A random assignment of experimental material to treatments prior to the start of the experiment. Randomization is vital in the experimental design process and provides (1) the basis for a valid interpretation of the experimental outcomes in terms of a test of statistical significance, and (2) the basis for computing a valid estimate of experimental error by justifying the assumption of independence of responses over experimental units. 

When a reaction has many participants, which may be the case even of apparently simple processes like pyrolysis of ethane or synthesis of methanol, a factorial or other experimental design can be made and the data subjected to a re.spon.se. suiface analysis (Davies, Design and Analysis of Industrial Experiments, Oliver Boyd, 1954). A quadratic of this type for the variables X, Xo, and X3 is... 

EXPERIMENTAL DESIGN APPLIED TO THE OPTIMIZATION OF A DISTILLATION PROCESS FOR FLUORIDE DETERMINATION IN ANHYDRITE... 

The modules are computer-based laboratory simulations with engaging activities that emphasize experimental design and visualization of structures and processes at the molecular level. The modules are designed to help students connect chemical principles from lecture with their practical applications in the lab. Every module has a built-in accountability feature that records section completion for use in setting grades and a workbook for students to record and interpret their work. 

The system developed by personnel at Sanofl uses the Formulogic shell with specific preformulation data on the drug. The system recommends one first-pass clinical capsule formulation with as many subsequent formulations as desired to accommodate an experimental design [24]. An example of a formulation proposed for naproxen at a dose of 500 mg is shown in Table 28.2. In addition to the formulation the system provides advice on the milling of the drug, the process to be used for blending, and details of the capsule shell. 

The simplest and cheapest procedure to obtain standards is based on selective extraction followed by crystallization. A method developed to obtain lycopene from tomato residue using factorial experimental design consisted of a preliminary water removal with ethanol, followed by extraction with EtOAc and two successive crys-talhzation processes using dichloromethane and ethanol (1 4), producing lycopene crystals with 98% purity, measured by HPLC-PDA. Using this approach, bixin was extracted with EtOAc from annatto seeds that were previously washed with... 

The team members must represent the various scientific disciplines that are associated with the experimental processes of Interest. The methodology requires the design team to meet several times over a period of several weeks to carry out a set of formal agendas described below and to conclude Its efforts with a formal document. The document will contain either a detailed experimental design that meets the constraints of the envisioned test program, or the document will show that an acceptable experimental design does not exist and the envisioned experiment should not be Implemented. In either case, the detailed documentation permits subsequent peer review. 

The experimental designs discussed in Chapters 24-26 for optimization can be used also for finding the product composition or processing condition that is optimal in terms of sensory properties. In particular, central composite designs and mixture designs are much used. The analysis of the sensory response is usually in the form of a fully quadratic function of the experimental factors. The sensory response itself may be the mean score of a panel of trained panellists. One may consider such a trained panel as a sensitive instrument to measure the perceived intensity useful in describing the sensory characteristics of a food product. 

There are many books that address experimental design and present factorial experimental design in detail (for example Design and Analysis of Experiments by Montgomery (1997) or Design of Experiments by Anderson and McLean (1974)). As engineers, we are faced quite often with the need to design a set of preliminary experiments for a process that very little or essentially no information is available. 

Rippin, D.W.T., L.M. Rose and C. Schifferli. "Nonlinear Experimental Design with Approximate Models in Reactor Studies for Process Development", Chem. Eng. 5c/., 35, 356 (1980). 

---