Statistical Designs

A randomized block design should be the standard in this case, ensuring that adequate washout times are allowed between treatments. 

---

Mason, R. L. Gunst, R. F. Hess, J. L. Statistical Design and Analysis of Experiments. Wiley New York, 1989. 

Statistical designs for experiments maximize information and reduce research time and costs. These techniques are less likely to miss synergistic factors affecting performance or product quaUty, minimize the element of human bias, eliminate less productive avenues of experimentation by taking... 

The practice of estabHshing empirical equations has provided useflil information, but also exhibits some deficiencies. Eor example, a single spray parameter, such as may not be the only parameter that characterizes the performance of a spray system. The effect of cross-correlations or interactions between variables has received scant attention. Using the approach of varying one parameter at a time to develop correlations cannot completely reveal the tme physics of compHcated spray phenomena. Hence, methods employing the statistical design of experiments must be utilized to investigate multiple factors simultaneously. 

Statistically designed studies should be performed to determine accuracy, precision, and selectivity of the methodology used for trace or ultratrace analyses. The rehabihty requirements for these studies are that the data generated withstand iatedaboratory comparisons. 

Study. Their location represents the range of the conditions that should be used in a statistically designed set of experiments for kinetic studies and not actual conditions at the particular location. This way, the same flow is again maintained on all three scales and the troublesome effect of changing flow conditions on scale-up can be eliminated. The proposed idea, for scale-up by scale-down from the view point of the catalyst, was proven to be effective in many industrial projects. 

Lipson, C. and Sheth, N. J. 1973 Statistical Design and Analysis of Engineering Experiments. NY McGraw-Hill. 

Because all the variables that influence the properties of the final product are known, one can use a statistical design (known as a one-half factorial) to optimize the properties of the GPC/SEC gels. Factorial experiments are described in detail by Hafner (10). For example, four variables at two levels can be examined in eight observations. From these observations the significance of each variable as related to the performance of the gel can be determined. An example of a one-half factorial experiment applied to the production of GPC/SEC gel is set up in Table 5.2. The four variables are the type of DVB, amount of dodecane, type of methocel, and rate of stirring. 

The use of statistically designed experiments in the development of both PS and RF foams has led to very significant progress, where critical problems were identified and solved quickly and where previously unexplored ranges of variables led to substantially improved materials. We shall continue to employ it in our development of low-density foams, and we strongly recommend it to other researchers. 

OS 68] [R 19] [P 50/The experiments on micro-channel processing followed a statistical design [134]. The dependence of the yield on temperature and on the ratio... 

Figure 4.82 Results of trials according to the statistical design of experiments [134].

Determine the components of variance that should be built Into the statistical design Proper stratification of the study area will allow Identification and quantification of several sources of variation. The sources of variation that can be controlled by the sampling are determined by the particular sampling design and by the pattern of sample collection superimposed over the area. An analysis of variance of the data provides estimates of the components of variance ... 

Because the sampling plan is central to the overall objective of an LSMBS, the plan should be statistically designed. The overall intent of the design is that... 

In the OPMBS, a statistical design for the selection of stores from which samples could be collected was developed. This design used key factors including the geographic location of the store, the size of the store, and the population density of the area in which the store was located. In addition, secondary stores were designated. Secondary stores were used when a commodity was not available at the primary store, or the primary store was not accessible. Primary and secondary stores were chosen so that the demographics of the selected stores reflected the overall population. 

The field phase of an LSMBS is critically important. Close monitoring of shoppers by field phase study management personnel is required, especially when a sampling plan includes frequent collections, such as weekly or bimonthly. Missed, delayed, or deficient commodity samples can throw a laboratory off schedule, which in turn can adversely affect both the timeliness and the quality of the analyses. Missed, delayed, or deficient samples can also affect the study outcome and interpretation, because a statistical design typically requires a certain number of data points, each represented by analysis of a commodity sample. 

The translation of the statistical design into physical units is shown in Table 5. Again the formulations were prepared and the responses measured. The data were subjected to statistical analysis, followed by multiple regression analysis. This is an important step. One is not looking for the best of the 27 formulations, but the... 

The emphasis, once again, is that appropriate statistical design is an important consideration. For a formulator planning such a study, it should be noted that the independent variables can be anything that he or she can quantitate and control and the dependent variables can be anything that he or she can quantitate. 

Sheng-Chung Chow and Jen-Pei Liu, Statistical Design and Analysis in Pharmaceutical Science, Marcel Dekker Inc, New York, 1997. 

---