A minimum discrepancy approach to multivariate dimension reduction via k-means inverse regression

作者：Wen Xuerong Meggie^*; Setodji C Messan; Adekpedjou Akim

来源：Statistics and Its Interface, 2009, 2(4): 503-511.

DOI：10.4310/sii.2009.v2.n4.a11

• Multivariate Regression
• Dimension Reduction
• Central Subspaces
• Intra-cluster Information
• k-means Clustering

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 intra-cluster 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.

• 出版日期2009