In the nonparametric regression model with random design and based on independent, identically distributed pairs of observations (Xi, Yi), where the regression function m is given by m(x) = 𝔼(Yi|Xi = x), estimation of the location θ (mode) of a unique maximum of m by the location &thetacrc; of a maximum of the Nadaraya–Watson kernel estimator &mcirc; for the curve m is considered. In order to obtain asymptotic confidence intervals for θ, the suitably normalized distribution of &thetacrc; is bootstrapped in two ways: we present a paired bootstrap (PB) where resampling is done from the empirical distribution of the pairs of observations and a smoothed paired bootstrap (SPB) where the bootstrap variables are generated from a smooth bivariate density based on the pairs of observations. While the PB requires only relatively small computational effort when carried out in practice, it is shown to work only in the case of vanishing asymptotic bias, i.e. of ‘undersmoothing’ when compared to optimal smoothing for mode estimation. On the other hand, the SPB, although causing more intricate computations, is able to capture the correct amount of bias if the pilot estimator for m oversmoothes.
