Nonparametric regression under alternative data environments

This manuscript proposes a nonparametric regression estimator which can accommodate two empirically relevant data environments. The first data environment assumes that at least one of the explanatory variables is discrete. In such an environment a “cell” approach which consists of partitioning the data and estimating a separate regression for each discrete cell has usually been employed. The second data environment assumes that one needs to estimate a set of conditional mean functions that belong to different experimental units. In both environments the proposed estimator attempts to reduce estimation error by incorporating extraneous data from the other experimental units (or cells) when estimating the conditional mean function for a given experimental unit. Consistency and asymptotic normality of the proposed estimator are established. Its computational simplicity and simulation results demonstrate a strong potential for empirical application.