A0243
Title: Using Hasse diagrams to understand complex experimental designs
Authors: Simon Bate - GlaxoSmithKline (United Kingdom) [presenting]
Abstract: In many areas of scientific research, scientists routinely use complex experimental designs when conducting their experiments. With the advent of the modern statistical package, the scientist often carries out the analysis of data generated from such experiments. This can lead to incorrect and misleading results, especially if the scientist has failed to correctly identify the experimental design they are using and the effect the design has on the statistical analysis. The aim is to describe a procedure, and associated R package, that allows non-statisticians to identify the structure of the experimental design using a Hasse diagram. It is then possible to use this diagram, along with the randomization performed, to produce an appropriate model for the statistical analysis. Placing experimental design at the center of the statistical process not only reduces the complexity for non-statisticians but also improves the reliability of any statistical results generated.
