TY - JOUR AU - Nordhausen, Klaus AU - Oja, Hannu AU - Ollila, Esa PY - 2016/04/03 Y2 - 2024/03/28 TI - Robust Independent Component Analysis Based on Two Scatter Matrices JF - Austrian Journal of Statistics JA - AJS VL - 37 IS - 1 SE - Articles DO - 10.17713/ajs.v37i1.290 UR - https://www.ajs.or.at/index.php/ajs/article/view/vol37%2C%20no1%20-%209 SP - 91–100 AB - <p align="LEFT">Oja, Sirkiä, and Eriksson (2006) and Ollila, Oja, and Koivunen (2007) showed that, under general assumptions, any two scatter matrices with the so called independent components property can be used to estimate the unmixing matrix for the independent component analysis (ICA). The method is a generalization of Cardoso’s (Cardoso, 1989) FOBI estimate which uses the regular covariance matrix and a scatter matrix based on fourth moments. Different choices of the two scatter matrices are compared in a simulation study. Based on the study, we recommend always the use of two robust scatter matrices. For possible asymmetric independent components, symmetrized versions of the scatter matrix estimates should be used.</p> ER -