Finance Working Papers, Department of Business Studies, Aarhus School of Business, University of Aarhus
Jens Perch Nielsen
Variable Bandwidth Kernel Hazard Estimators
Abstract: Variable kernel hazard estimators are considered in the
case, where the bandwidth is allowed to depend on the exposure. Simulations
show, that when the exposure varies substantially, then this can improve
the performance of the basic kernel smoother con-siderable. A two-stage
approach for kernel function smoothing of hazard functions is also
suggested. The pilot estimator is a fixed bandwidth kernel estimator. The
second and final estimator is a variable bandwidth kernel estimator, where
the bandwidthis determined by Abramson's square root law, see Abramson
(1982). This approach reduces the theoretical bias compared to the fixed
andwidth kernel estimator, but simulations show that the exposure dependent
kernel hazard estimators have better small sample performance.
Keywords: Counting Process Theory; Kernel estimation; Bias reduction; Variable Bandwidth; Predictability; (follow links to similar papers)
53 pages, June 1, 2000
Before downloading any of the electronic versions below
you should read our statement on
for viewing Postscript files and the
Acrobat Reader for viewing and printing pdf files.
Questions (including download problems) about the papers in this series should be directed to Helle Vinbaek Stenholt ()
Report other problems with accessing this service to Sune Karlsson ()
or Helena Lundin ().
Design Joakim Ekebom