This paper proposes a test for selecting explanatory variables in nonparametric regression. The test does not need to estimate the conditional expectation function given all the variables, but only those which are significant under the null hypothesis. This feature is computationally convenient and solves, in part, the problem of the “curse of dimensionality” when selecting regressors in a nonparametric context. The proposed test statistic is based on functionals of a $U$-process. Contiguous alternatives, converging to the null at a rate $n^{-1/2}$ can be detected. The asymptotic null distribution of the statistic depends on certain features of the data generating process,and asymptotic tests are difficult to implement except in rare circumstances. We justify the consistency of two easy to implement bootstrap tests which exhibit good level accuracy for fairly small samples, according to the reported Monte Carlo simulations. These results are also applicable to test other interesting restrictions on nonparametric curves, like partial linearity and conditional independence.
This paper proposes a test for the equality of nonparametric regression curves that does not depend on the choice of a smoothing number. The test statistic resembles in spirit the Kolmogorov-Smirnov statistic and it is easy to compute. It is powerful under alternatives that converge to the null hypothesis at a rate n ^ (-1/2). The disturbance distributions are arbitrary and possibly unequal, and conditions on the regressors distribution are very mild. A Monte Carlo study illustrates the performance of the test in small and moderate samples. We also study extensions to multiple regression, and test the equality of several regression curves.Publicad
Kim and Pollard (Annals of Statistics, 18 (1990) 191?219) showed that a general class of M-estimators converge at rate n1/3 rather than at the standard rate n1/2. Many times, this situation arises when the objective function is non-smooth. The limiting distribution is the (almost surely unique) random vector that maximizes a certain Gaussian process and is difficult to analyze analytically. In this paper, we propose the use of the subsampling method for inferential purposes. The general method is then applied to Manski?s maximum score estimator and its small sample performance is highlighted via a simulation study.Publicad
This paper presents and discusses a nonparametric test for detecting serial dependence. We consider a Cramèer‐von Mises statistic based on the difference between the joint sample distribution and the product of the marginals. Exact critical values can be approximated from the asymptotic null distribution, or by resampling, randomly permuting the original series. A Monte Carlo experiment illustrates the test performance with small sample sizes. The paper also includes an application, testing the random walk hypothesis of exchange rate returns for several currencies.