Multivariate component methods - Hervé Abdi, Vincent Guillemot

Most recent biological research projects incorporate multi-modal dependent variables in their design. The challenge, with these studies, is then to integrate the information in these heterogeneous blocks to reveal their commonalities and differences. To do so requires to develop new methods able to cope with the complexity of the datasets and also to disseminate and relate them to more classical statistical methods. These new multivariate statistical methods—mostly based on the singular value decomposition (SVD) and its generalizations—include Principal Component Analysis (PCA), Correspondence Analysis (CA), Multiple Correspondence Analysis (MCA), Canonical Correlation Analysis (CCA), Partial Least Squares Correlation (PLSC), and Partial Least Squares Regression (PLSR), Multiple Factor Analysis (MFA) and some of their derivatives.

Our event is composed of two workshops : (i) a workshop for “beginners” on PCA, CA, and MCA, and (ii) a workshop for “experts” on PLSC, PLSR, and CCA.

More details here.