Experimental design terminology

An excellent exposition of split-plot experimental designs can be found in D.R. Cox s book, Planning of Experiments [42]. He states that split-plot designs are particularly useful when one (or more) factors are what he calls classification factors. These factors are included in the experiment to determine whether they modify the effect of the other factors or indicate how the other factors work. The classification factors are included to examine their possible interaction with the other factors. Lower precision is tolerated for comparisons of the classification factors, in order that the precision of the other factors and the interactions can be increased. In the standard terminology associated with split-plot experiments, the classification factors are called whole-plot factors and are applied to the larger experimental units. The smaller experimental units are called subplots. 

The methodology of experimental design uses a terminology which is apparently different from the vocabulary frequently used in this chapter. Therefore, we call experimental conditions jwctors or factor when we have only one) in fact, in Fig. 5.1, the experimental conditions are entirely included in the class of independent variables of the process. The word level (or levels when we have more than one), introduces here the values taken by the factors (factor). The term response is used to quantitatively characterize the observed output of the process when the levels of the factors are changed. 

Statistics, numerical analysis other data processing, and experimental design terms are not addressed as individual terms, because they are not materials related, and the mathematical sciences possess an extensive, separate and distinct terminology while this book is primarily devoted to materials. 

The normal distribution has the familiar symmetrical beU shape as shown in Fig. 1 and is the basis for the most common statistical techniques of experimental design and data analysis. The characteristics of this distribution are described in the section on Terminology. Mass loss, mass gain, thickness loss, corrosion potential, corrosion rate, and pitting area may have a normal distribution. Although this may not be an established fact, in the past many researchers have assumed normal distributions for such data with apparent success. 

It was discussed above that two types of factors can influence our process or system controlled factors design factors in Taguchi s terminology) and uncontrolled factors noise factors. The latter are inherent to the experimentation and can only be estimated by replication of runs. If the variability between replications is too large, any conclusion drawn from our study may have no meaning at all. Further, their variability can be as important as the mean of the replicates. Noise factors must be identified properly and, if possible, simulated in our experimentation. Sometimes noise factors are actually uncontrolled and, in such a case, we must be able to simulate them by means of some alternative parameter controlled during the experiments. For instance, temperature inside an oven can be a noise factor, but we can measure it at different locations, and accordingly, the effect of temperature inside is simulated by a location factor. 

In 2002, IUPAC initiated work in the development of terminology of a standard for analytical data. The standard format, XML, is intended to be universal for all types of analytical instrumentation, without permutations for different techniques. The XML format is designed to have information content of data defined in several layers. The most generic information is in the first layer, or core. More specific information about the instrumentation, sample details and experimental settings are stored in subsequent layers. The layers are defined as core, sample, technique, vendor, enterprise and user.29 The existence of a universal format will aid in the analysis of data from multiple sources, as well as in the archival and retrieval of data from historical processes. 

All is not well in the technical camp. Confusion among scientists between the design of the MF to meet requisite levels of performance [Lq], and an experimental outcome or detection decision based on a specified criterion [1 ], is at the heart of much our internal disarray. That is, two different (albeit related) issues are under discussion, often unknowingly and with conflicting terminology. Ad hoc rules of thumb, or simplistic consensus ("voted") formulae are proffered -- often in the... 

After the initial presentation, refinements in both CSPT and the ERM were made. However, the basic approaches, terminology, and constructs used in each have remained quite stable. More recent work has focused on development of various components required for application of the ERM in nontrivial situations. This entails using CSPT and basic ERM concepts to guide a full fleshing out of the details of measurement parameterizations and models for different types of human subsystems, definition of standard conventions and notations, and development of computer-based tools. In addition, experimental studies designed to evaluate key constructs of the ERM and to demonstrate the... 

Stig and Hallstrom (2009) called this kind of composite material (following Khokar s terminology) a truly 3D woven fibre composite, and they also projected, Fully interlaced 3D fabric comprising carbon fibres have the potential of changing the way composite structures are designed and buUt. Unfortunately, their own experimental results do not support this expectation. 

---