A Minimum Discrepancy Approach to Multivariate Dimension Reduction via K-means Inverse Regression
We proposed a new method to estimate the intra-cluster adjusted central subspace for regressions with multivariate responses. Following Setodji and Cook (2004), we made use of the k-means algorithm to cluster the observed response vectors. Our method was designed to recover the intracluster information and outperformed previous method with respect to estimation accuracies on both the central subspace and its dimension. It also allowed us to test the predictor effects in a model-free approach. Simulation and a real data example were given to illustrate our methodology.
X. M. Wen et al., "A Minimum Discrepancy Approach to Multivariate Dimension Reduction via K-means Inverse Regression," Statistics and Its Interface, International Press, Jan 2009.
The definitive version is available at http://dx.doi.org/10.4310/SII.2009.v2.n4.a11
Mathematics and Statistics
Keywords and Phrases
multivariate regression; dimension reduction; central subspaces; intra-cluster information; k-means clustering
Article - Journal
© 2009 International Press, All rights reserved.