Influence function

Tuesday, April 24, 2018 - 11:00am - 11:30am
Peter Filzmoser (Technische Universität Wien)
The maximum association between two multivariate variables X and Y is defined as the maximal value that a bivariate ssociation measure between one-dimensional projections a'X and b'Y can attain. Taking the Pearson correlation as projection index results in the first canonical correlation coefficient. We propose to use more robust association measures, such as Spearman's or Kendall's rank correlation, or association measures derived from bivariate scatter matrices.
Subscribe to RSS - Influence function