Experimental design decision limit

Experimental Design. The first objective of the experiment was to determine which of the five factors listed above were of decisive importance, and to quantify their effects and their eventual interactions. The number of variables (k = 5) being limited, a screening was not required, and a 2k factorial design was chosen [130,136]. In this type of design, all experiments are performed with variables set at two different levels, which correspond to the limits of the experimental region and which are coded (-1) and ( +1) (coded variables are denoted Xf) (Table 2). 

The statistical concepts behind CCa and CC/3 are identical to the concepts of Lc and LDs, respectively. However, due to the different experimental design, the different interpretation and the legal framework, CCa and CC/3 should not be considered as alternative definitions of decision limit and LoDs. A graphical representation of CCa and CC/3 in the case of an established limit is given in Figure 6.6. 

A decision about the validity/suitability of an analytical method for routine testing of study samples is taken, based on the estimated measurement error profile. Such a decision is possible only when no more than one section of the concentration range has its measurement error profile within the acceptance limits. For example, it is not reasonable to consider a method to be valid in a certain section of low concentrations and a different section of higher concentrations. In such cases, the measurement error profile is probably not precise enough to define a unique section of the range where the method is valid. In such cases, it is recommended to add a few more runs in the experimental design to obtain a more reliable estimate of the measurement error profile. 

In Sections 2 to 4, we review the technology of synthetic oligonucleotide microarrays and describe some of the popular statistical methods that are used to discover genes with differential expression in simple comparative experiments. A novel Bayesian procedure is introduced in Section 5 to analyze differential expression that addresses some of the limitations of current procedures. We proceed, in Section 6, by discussing the issue of sample size and describe two approaches to sample size determination in screening experiments with microarrays. The first approach is based on the concept of reproducibility, and the second approach uses a Bayesian decision-theoretic criterion to trade off information gain and experimental costs. We conclude, in Section 7, with a discussion of some of the open problems in the design and analysis of microarray experiments that need further research. 

Analyte Detection. This is a primary focus for this volume, the specification of critical levels or thresholds for analyte detection decisions, and the design of CMP s to achieve requisite analyte detection limits. The following section includes an historical perspective on the topic. A tutorial is provided in the chapter by Kirchmer (14), where a crucial distinction is noted that is, the detection decision is made in reference to an observed, random experimental outcome (estimated concentration),... 

Comparisons of results across studies have been made by means of metaanalyses. These are relatively new techniques which have been designed largely for use on the results of experimental studies. In the present context they may be useful, but they do have several limitations. Like all cumulating techniques there have to be decisions about the criteria for inclusion or exclusion of studies, so meta-analyses are not necessarily objective or value-free. Studies must be checked for heterogeneity, and where this is present the results cannot simply be combined. In particular this applies to the differential treatment of confounders, or differences in confounders controlled in different studies. 

---