Integrated Partial Sufficient Dimension Reduction with Heavily Unbalanced Categorical Predictors
Jae‐Keun Yoo · Korean Journal of Applied Statistics · 2010
In this paper, we propose an approach to conduct partial sufficient dimension reduction with heavily unbalanced categorical predictors. For this, we consider integrated categorical predictors and investigate certain conditions that the integrated categorical predictor is fully informative to partial sufficient dimension reduction. For illustration, the proposed approach is implemented on optimal partial sliced inverse regression in simulation and data analysis.