International Conference of the ERCIM Working Group on Computational and Methodological Statistics (ERCIM) edition:7 location:Pisa (Italy) date:6-8 December 2014
Canonical correlation analysis (CCA) is a multivariate method which describes the associations between two sets of variables. The objective is to find linear combinations of the variables in each data set having maximal correlation. This talk discusses a method for Robust Sparse CCA. Sparse estimation produces canonical vectors with some of their elements estimated as exactly zero. As such, their interpretability is improved. We also robustify the method so that it can cope with outliers in the data. Outliers are a common problem in applied data analysis. If the presence of outliers is ignored, then the estimation performance of standard estimation methods deteriorates drastically. To estimate the canonical vectors, we convert the CCA problem into an alternating regression framework. Sparse canonical vectors that are not attracted by outliers are obtained using the robust Sparse Least Trimmed Squares estimator. We illustrate the good performance of the Robust Sparse CCA method in several simulation studies and an empirical application.