A1299
Title: Quantifying and testing dependence to categorical variables
Authors: Siegfried Hoermann - Graz University of Technology (Austria)
Daniel Strenger-Galvis - Graz University of Technology (Austria) [presenting]
Abstract: The purpose is to suggest a dependence coefficient between a categorical variable and some general variable taking values in a metric space. Important theoretical properties are derived, and the large sample behavior of the suggested estimator is studied. Moreover, an independence test is developed which has an asymptotic $\chi^2$-distribution if the variables are independent, and it is proven that this test is consistent against any violation of independence. Some extensions are discussed, including a variant of the coefficient for measuring conditional dependence.
