Density Regression with Conditional Support Points

Density regression characterizes the conditional density of the response variable given the covariates, and provides much more information than the commonly used conditional mean or quantile regression. However, it is often computationally prohibitive in applications with massive datasets, especially when there are multiple covariates. In this article, we develop a new data reduction approach for the density regression problem using conditional support points. After obtaining the representative data, we exploit the penalized likelihood method as the downstream estimation strategy. Based on the connections among the continuous ranked probability score, the energy distance, the <i>L</i>₂ discrepancy and the symmetrized Kullback–Leibler distance, we investigate the distributional convergence of the representative points and establish the rate of convergence of the density regression estimator. The usefulness of the methodology is illustrated by modeling the conditional distribution of power output given multivariate environmental factors using a large scale wind turbine dataset.