Publication details

Kernel Regression Model with Correlated Errors

Authors

LAJDOVÁ Dagmar KOLÁČEK Jan HOROVÁ Ivanka

Year of publication 2014
Type Chapter of a book
MU Faculty or unit

Faculty of Science

Citation
Description Kernel regression is one of the commonly used nonparametric methods for an estimation of a regression function. Nevertheless, there is a problem of choosing the value of the smoothing parameter, the bandwidth. In the case of independent observations the literature on the bandwidth selection is quite extensive. However, these standard methods, like cross-validation, perform badly when the errors are correlated. There are several possibilities how to overcome this. We will present and compare the partitioned cross-validation method and the plug-in method.

You are running an old browser version. We recommend updating your browser to its latest version.

More info