Abstract
We investigate the asymptotic behavior of a robust version of local linear regression estimators with variable bandwidth for spatial associated processes. The weak consistency of the proposed estimators is given under appropriate conditions. Furthermore, we establish the asymptotic normality of the estimators, from which expressions for the asymptotic bias and variance can be derived.
Original language | English |
---|---|
Pages (from-to) | 11-29 |
Number of pages | 19 |
Journal | Metrika |
Volume | 67 |
Issue number | 1 |
DOIs | |
Publication status | Published - 1 Jan 2008 |
Keywords
- local M-estimation
- association
- CONVERGENCE
- consistency
- RANDOM-FIELDS
- VARIABLE BANDWIDTH
- PROBABILITY DENSITIES
- SMOOTHERS
- NEGATIVE ASSOCIATION
- ASYMPTOTIC NORMALITY
- REGRESSION
- asymptotic normality
- spatial processes