Authors: | Dette, Holger Weißbach, Rafael |
Title: | Bias in nearest-neighbor hazard estimation |
Language (ISO): | en |
Abstract: | In nonparametric curve estimation, the smoothing parameter is critical for performance. In order to estimate the hazard rate, we compare nearest neighbor selectors that minimize the quadratic, the Kullback-Leibler, and the uniform loss. These measures result in a rule of thumb, a crossvalidation, and a plug-in selector. A Monte Carlo simulation within the threeparameter exponentiated Weibull distribution indicates that a counterfactual normal distribution, as an input to the selector, does provide a good rule of thumb. If bias is the main concern, minimizing the uniform loss yields the best results, but at the cost of very high variability. Crossvalidation has a similar bias to the rule of thumb, but also with high variability. AMS: 62M02 |
Subject Headings: | Bandwidth selection Hazard rate Kernel estimation Nearest neighbor bandwidth Rule of thumb Variable bandwidth |
URI: | http://hdl.handle.net/2003/25878 http://dx.doi.org/10.17877/DE290R-14464 |
Issue Date: | 2008-11-26T14:48:51Z |
Appears in Collections: | Sonderforschungsbereich (SFB) 475 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
tr15-08-Weißbach.pdf | DNB | 371 kB | Adobe PDF | View/Open |
This item is protected by original copyright |
This item is protected by original copyright rightsstatements.org