Robust testing for superiority between two regression curves

BOENTE, GRACIELA; PARDO FERNANDEZ, JUAN CARLOS

COMPUTATIONAL STATISTICS AND DATA ANALYSIS

ELSEVIER SCIENCE BV

Lugar: Amsterdam; Año: 2016 vol. 97 p. 151 - 168

0167-9473

The problem of testing the null hypothesis that the regression functions of two populations are equal versus one-sided alternatives under a general nonparametric homoscedastic regression model is considered. To protect against atypical observations, the test statistic is based on the residuals obtained by using a robust estimate for the regression function under the null hypothesis. The asymptotic distribution of the test statistic is studied under the null hypothesis and under root−n local alternatives. A Monte Carlo study is performed to compare the finite sample behaviour of the proposed tests with the classical one obtainedusing local averages. A sensitivity analysis is carried on a real data set.