A nonparametric spatial regression model using partitioning estimators
A nonparametric spatial regression model using partitioning estimators
Conventional spatial regression models are extended by modelling the spatial effects of the exogenous regressor model (SLX) as a functional coefficient. This coefficient is estimated by partitioning the domain of the spatial variable into a set of disjoint intervals and approximating the function using local Taylor expansions. The asymptotic properties of the proposed partitioning estimator are derived, and pointwise and uniform tests for the presence of spatial effects are developed. An empirical application of this work is used to study environmental Engel curves and provides strong evidence of neighbouring effects in the relationship between households’ income and the amount of pollution embodied in the goods and services they consume.
Spatial regression, asymptotic theory, environmental Engel curve, interaction matrix, partitioning estimator
Olmo, Jose
706f68c8-f991-4959-8245-6657a591056e
Sanso-navarro, Marcos
39ed49fd-2d29-4763-898b-9117bf977956
20 February 2023
Olmo, Jose
706f68c8-f991-4959-8245-6657a591056e
Sanso-navarro, Marcos
39ed49fd-2d29-4763-898b-9117bf977956
Olmo, Jose and Sanso-navarro, Marcos
(2023)
A nonparametric spatial regression model using partitioning estimators.
Econometrics and Statistics.
(doi:10.1016/j.ecosta.2023.02.003).
Abstract
Conventional spatial regression models are extended by modelling the spatial effects of the exogenous regressor model (SLX) as a functional coefficient. This coefficient is estimated by partitioning the domain of the spatial variable into a set of disjoint intervals and approximating the function using local Taylor expansions. The asymptotic properties of the proposed partitioning estimator are derived, and pointwise and uniform tests for the presence of spatial effects are developed. An empirical application of this work is used to study environmental Engel curves and provides strong evidence of neighbouring effects in the relationship between households’ income and the amount of pollution embodied in the goods and services they consume.
Text
network_regression
- Accepted Manuscript
More information
Accepted/In Press date: 13 February 2023
e-pub ahead of print date: 20 February 2023
Published date: 20 February 2023
Additional Information:
Funding Information:
The authors acknowledge financial support from Gobierno de Aragón (grants LMP21-21 and S39-20R ADETRE Research Group) and Ministerio de Ciencia e Innovacion/Agencia Estatal de Investigación (grants PID2019-104326GB-I00 and PID2020-112773GB-I00). Jose Olmo also acknowledges financial support from Fundación Agencia Aragonesa para la Investigación y el Desarrollo.
Publisher Copyright:
© 2023 EcoSta Econometrics and Statistics
Keywords:
Spatial regression, asymptotic theory, environmental Engel curve, interaction matrix, partitioning estimator
Identifiers
Local EPrints ID: 476481
URI: http://eprints.soton.ac.uk/id/eprint/476481
ISSN: 2452-3062
PURE UUID: 4ea9fa8d-5fbe-467e-add3-6de71e55899f
Catalogue record
Date deposited: 03 May 2023 17:43
Last modified: 17 Mar 2024 07:44
Export record
Altmetrics
Contributors
Author:
Marcos Sanso-navarro
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
