Choosing a Kernel for Cross-Validation

Simple item page
dc.contributorHart, Jeffrey D.
dc.contributorSheather, Simon J.
dc.creatorSavchuk, Olga
dc.date.accessioned2010-01-15T00:16:54Z
dc.date.accessioned2010-01-16T00:13:52Z
dc.date.accessioned2017-04-07T19:54:36Z
dc.date.available2010-01-15T00:16:54Z
dc.date.available2010-01-16T00:13:52Z
dc.date.available2017-04-07T19:54:36Z
dc.date.created2009-08
dc.date.issued2010-01-14
dc.description.abstractThe 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.urihttp://hdl.handle.net/1969.1/ETD-TAMU-2009-08-7002
dc.language.isoen_US
dc.subjectbandwidth selection
dc.subjectcross-validation
dc.subjectkernel density estimation
dc.subjectkernel regression
dc.subjectnonparametric function estimation
dc.titleChoosing a Kernel for Cross-Validation
dc.typeBook
dc.typeThesis

Files

Collections

Texas A&M University at College Station