A consistent test for heteroscedasticity in nonparametric regression based on the kernel method

This paper presents a new residual based test for heteroscedasticity in nonparametric regression. The construction of the test statistic is motivated by the idea that the problem of testing heteroscedasticity is equivalent to the problem of testing pseudoresiduals for a constant mean. Asymptotic normality is established with different rates corresponding to the null hypothesis of homoscedasticity and the alternative. A Monte Carlo simulation is conducted in order to investigate the finite sample performance of a bootstrap version of the proposed test. (C) 2002 Elsevier Science B.V. All rights reserved.