Experimental Design to Make the Most of Microarray Studies

Statistics is often thought to concern only the analysis of observational or experimental data. However, experimental design is one of the oldest subfields of statistics. The founder of modern statistics, R. A. Fisher, noted that “statistical procedure and experimental design are only two different aspects of the same whole, and that whole comprises all the logical requirements of the complete process of adding to natural knowledge by experimentation” (1 ). The design of an experiment affects many things: the analyses that will be possible, the questions that will be answerable, and the quality of the results. While a good design does not guarantee a successful experiment, a suitably bad design guarantees a failed experiment—no results or incorrect results.