Arbeitspapier
Bias in nearest-neighbor hazard estimation
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 cross-validation, and a plug-in selector. A Monte Carlo simulation within the three-parameter exponentiated Weibull distribution indicates that a counter-factual 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. Cross-validation has a similar bias to the rule of thumb, but also with high variability.
- Sprache
-
Englisch
- Erschienen in
-
Series: Technical Report ; No. 2008,15
- Thema
-
hazard rate
kernel smoothing
bandwidth selection
nearest neighbor bandwidth
rule of thumb
plug-in
cross-validation
credit risk
- Ereignis
-
Geistige Schöpfung
- (wer)
-
Weißbach, Rafael
Dette, Holger
- Ereignis
-
Veröffentlichung
- (wer)
-
Technische Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
- (wo)
-
Dortmund
- (wann)
-
2008
- Handle
- Letzte Aktualisierung
-
10.03.2025, 11:44 MEZ
Datenpartner
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Objekttyp
- Arbeitspapier
Beteiligte
- Weißbach, Rafael
- Dette, Holger
- Technische Universität Dortmund, Sonderforschungsbereich 475 - Komplexitätsreduktion in Multivariaten Datenstrukturen
Entstanden
- 2008
Ähnliche Objekte (12)
Bias in nearest-neighbor hazard estimation
A note on all-bias designs with applications in spline regression models
Föderierte Nearest-Neighbor-Queries
On robust and efficient designs for risk estimation in epidemiologic studies
Canonical moments, orthogonal polynomials with application to statistics
Strong approximation of eigenvalues of large dimensional Wishart matrices by roots of generalized Laguerre polynomials
On the risk of nearest neighbor rules
Optimized Nearest-Neighbor Classifiers Using Generated Instances
Fast Nearest Neighbor Search in High-Dimensional Spaces
On the risk of the nearest neighbor rules
Efficient nearest neighbor search on metric time series
Weighted k-nearest-neighbor techniques and ordinal classification
Bias in nearest-neighbor hazard estimation
A note on all-bias designs with applications in spline regression models
Föderierte Nearest-Neighbor-Queries
On robust and efficient designs for risk estimation in epidemiologic studies
Canonical moments, orthogonal polynomials with application to statistics
Strong approximation of eigenvalues of large dimensional Wishart matrices by roots of generalized Laguerre polynomials
On the risk of nearest neighbor rules
Optimized Nearest-Neighbor Classifiers Using Generated Instances
Fast Nearest Neighbor Search in High-Dimensional Spaces
On the risk of the nearest neighbor rules
Efficient nearest neighbor search on metric time series
Weighted k-nearest-neighbor techniques and ordinal classification
Bias in nearest-neighbor hazard estimation
A note on all-bias designs with applications in spline regression models
Föderierte Nearest-Neighbor-Queries
On robust and efficient designs for risk estimation in epidemiologic studies
Canonical moments, orthogonal polynomials with application to statistics
Strong approximation of eigenvalues of large dimensional Wishart matrices by roots of generalized Laguerre polynomials
On the risk of nearest neighbor rules
Optimized Nearest-Neighbor Classifiers Using Generated Instances
Fast Nearest Neighbor Search in High-Dimensional Spaces
On the risk of the nearest neighbor rules
Efficient nearest neighbor search on metric time series