Multivariate data sets are prevalent in many biological research fields, and they are often approached from an exploratory perspective, with the aim of generating new and potentially relevant hypotheses and reveal previously unknown structure and patterns. An initial exploratory analysis can also be helpful for detecting anomalies in the measured data. Having a graphical representation of the data is very useful for such exploratory analysis. However, since the human brain is essentially limited to interpreting at most three-dimensional graphical representations, efficient summarization methods must be applied before a high-dimensional data set can be visually explored.
In this workshop, we will discuss some of the most common methods for summarizing and creating graphical representations of multivariate data, such as principal component analysis (PCA), multidimensional scaling (MDS) and correspondence analysis (CA).