De Gooijer, Jan G. and Reichardt, Hugo (2021) A multi-step kernel–based regression estimator that adapts to error distributions of unknown form. Communications in Statistics - Theory and Methods, 50 (24). 6211 - 6230. ISSN 0361-0926
Text (03610926.2020)
- Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) |
Abstract
For linear regression models, we propose and study a multi-step kernel density-based estimator that is adaptive to unknown error distributions. We establish asymptotic normality and almost sure convergence. An efficient EM algorithm is provided to implement the proposed estimator. We also compare its finite sample performance with five other adaptive estimators in an extensive Monte Carlo study of eight error distributions. Our method generally attains high mean-square-error efficiency. An empirical example illustrates the gain in efficiency of the new adaptive method when making statistical inference about the slope parameters in three linear regressions.
Item Type: | Article |
---|---|
Official URL: | https://www.tandfonline.com/journals/lsta20 |
Additional Information: | © 2020 The Authors |
Divisions: | Centre for Macroeconomics |
Subjects: | H Social Sciences > HB Economic Theory Q Science > QA Mathematics |
Date Deposited: | 11 May 2022 13:36 |
Last Modified: | 14 Sep 2024 09:05 |
URI: | http://eprints.lse.ac.uk/id/eprint/115083 |
Actions (login required)
View Item |