Revisiting Révész’s stochastic approximation method for the estimation of a regression function

Abstract. In a pioneer work, Révész (1973) introduces the stochastic approximation method to build up a recursive kernel estimator of the regression function x 7→ E(Y |X = x). However, according to Révész (1977), his estimator has two main drawbacks: on the one hand, its convergence rate is smaller than that of the nonrecursive Nadaraya-Watson’s kernel regression estimator, and, on the other hand, the required assumptions on the density of the random variable X are stronger than those usually needed in the framework of regression estimation. We first come back on the study of the convergence rate of Révész’s estimator. An approach in the proofs completely different from that used in Révész (1977) allows us to show that Révész’s recursive estimator may reach the same optimal convergence rate as Nadaraya-Watson’s estimator, but the required assumptions on the density ofX remain stronger than the usual ones, and this is inherent to the definition of Révész’s estimator. To overcome this drawback, we introduce the averaging principle of stochastic approximation algorithms to construct the averaged Révész’s regression estimator, and give its asymptotic behaviour. Our assumptions on the density of X are then usual in the framework of regression estimation. We prove that the averaged Révész’s regression estimator may reach the same optimal convergence rate as Nadaraya-Watson’s estimator. Moreover, we show that, according to the estimation by confidence intervals point of view, it is better to use the averaged Révész’s estimator rather than Nadaraya-Watson’s estimator.