| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 1154371 | Statistics & Probability Letters | 2009 | 5 Pages |
Abstract
We propose a new linear boundary kernel for bivariate density estimation on a compact region. This kernel is simple to implement even for irregular boundaries, and reduces the boundary bias to the same asymptotic order as for an interior point.
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Martin L. Hazelton, Jonathan C. Marshall,