Choosing a Kernel for Cross-Validation
dc.contributor | Hart, Jeffrey D. | |
dc.contributor | Sheather, Simon J. | |
dc.creator | Savchuk, Olga | |
dc.date.accessioned | 2010-01-15T00:16:54Z | |
dc.date.accessioned | 2010-01-16T00:13:52Z | |
dc.date.accessioned | 2017-04-07T19:54:36Z | |
dc.date.available | 2010-01-15T00:16:54Z | |
dc.date.available | 2010-01-16T00:13:52Z | |
dc.date.available | 2017-04-07T19:54:36Z | |
dc.date.created | 2009-08 | |
dc.date.issued | 2010-01-14 | |
dc.description.abstract | The statistical properties of cross-validation bandwidths can be improved by choosing an appropriate kernel, which is different from the kernels traditionally used for cross- validation purposes. In the light of this idea, we developed two new methods of bandwidth selection termed: Indirect cross-validation and Robust one-sided cross- validation. The kernels used in the Indirect cross-validation method yield an improvement in the relative bandwidth rate to n^1=4, which is substantially better than the n^1=10 rate of the least squares cross-validation method. The robust kernels used in the Robust one-sided cross-validation method eliminate the bandwidth bias for the case of regression functions with discontinuous derivatives. | |
dc.identifier.uri | http://hdl.handle.net/1969.1/ETD-TAMU-2009-08-7002 | |
dc.language.iso | en_US | |
dc.subject | bandwidth selection | |
dc.subject | cross-validation | |
dc.subject | kernel density estimation | |
dc.subject | kernel regression | |
dc.subject | nonparametric function estimation | |
dc.title | Choosing a Kernel for Cross-Validation | |
dc.type | Book | |
dc.type | Thesis |