A new test for the parametric form of the variance function in nonparametric regression
Loading...
Date
2005-10-11T14:37:10Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In the common nonparametric regression model the problem of testing for the parametric form of the conditional variance is considered. A stochastic process based on the difference between the empirical processes obtained from the standardized
nonparametric residuals under the null hypothesis (of a specific parametric form of the variance function) and the alternative is introduced and its weak convergence established. This result is used for the construction of a Cramér von Mises type statistic for testing the parametric form of the conditional variance. The finite
sample properties of a bootstrap version of this test are investigated by means of a simulation study. In particular the new procedure is compared with some of the currently available methods for this problem and its performance is illustrated by
means of a data example.
Description
Table of contents
Keywords
Bootstrap, Kernel estimation, Nonparametric regression, Residual distribution, Testing heteroscedasticity, Testing homoscedasticity