The Basics of Experimental Design for Multivariate Analysis
Steve Figard, Abbott Laboratories
This paper is designed for the beginner to intermediate practitioner of the form of analysis known as Design of Experiments (DOE). Specific objectives include:
• Defining some of the terminology
• Introducing major thought processes, philosophy, strategies, and rules of thumb
• Keeping objectives in the context of JMP® as an example of how this type of analysis is implemented in software
• Presenting a relevant example of the use of DOE in assay development Letting the software worry about the how of DOE, this paper focuses on the when and why to do what.
This is a very useful reference that provides a nice practical foundation for design of experiments in an applied problem context (in-vitro diagnostic immunoassay development). The example case is a 2-level, 4-factor screening design; and the technical writeup and interpretation of various fitted model output in JMP is quite clear and comprehensive.
