Conditional quantile estimation through optimal quantization

In this paper, we use quantization to construct a nonparametric estimator of conditional quantiles of a scalar response  YY given a dd-dimensional vector of covariates  XX. First we focus on the population level and show how optimal quantization of  XX, which consists in discretizing  XX by projecting it on an appropriate grid of  NN points, allows to approximate conditional quantiles of  YY given  XX. We show that this approximation is arbitrarily good as  NN goes to infinity and provide a rate of convergence for the approximation error. Then we turn to the sample case and define an estimator of conditional quantiles based on quantization ideas. We prove that this estimator is consistent for its fixed-NN population counterpart. The results are illustrated on a numerical example. Dominance of our estimators over local constant/linear ones and nearest neighbor ones is demonstrated through extensive simulations in the companion paper Charlier et al. (2014).