Indirect inference in spatial autoregression
Indirect inference in spatial autoregression
Ordinary least squares (OLS) is well-known to produce an inconsistent estimator of the spatial parameter in pure spatial autoregression (SAR). This paper explores the potential of indirect inference to correct the inconsistency of OLS. Under broad conditions, it is shown that indirect inference (II) based on OLS produces consistent and asymptotically normal estimates in pure SAR regression. The II estimator is robust to departures from normal disturbances and is computationally straightforward compared with pseudo Gaussian maximum likelihood (PML). Monte Carlo experiments based on various specifications of the weighting matrix confirm that the indirect inference estimator displays little bias even in very small samples and gives overall performance that is comparable to the Gaussian PML.
bias, binding function, inconsistency, indirect inference, spatial autoregression
University of Southampton
Kyriacou, Maria
6234587e-81f1-4e1d-941d-395996f8bda7
Phillips, Peter C.B.
f67573a4-fc30-484c-ad74-4bbc797d7243
Rossi, Francesca
1cdd87b3-bc01-40b0-ad91-0db0ee24e8e0
22 September 2014
Kyriacou, Maria
6234587e-81f1-4e1d-941d-395996f8bda7
Phillips, Peter C.B.
f67573a4-fc30-484c-ad74-4bbc797d7243
Rossi, Francesca
1cdd87b3-bc01-40b0-ad91-0db0ee24e8e0
Kyriacou, Maria, Phillips, Peter C.B. and Rossi, Francesca
(2014)
Indirect inference in spatial autoregression
(Discussion Papers in Economics and Econometrics, 1418)
Southampton, GB.
University of Southampton
49pp.
Record type:
Monograph
(Discussion Paper)
Abstract
Ordinary least squares (OLS) is well-known to produce an inconsistent estimator of the spatial parameter in pure spatial autoregression (SAR). This paper explores the potential of indirect inference to correct the inconsistency of OLS. Under broad conditions, it is shown that indirect inference (II) based on OLS produces consistent and asymptotically normal estimates in pure SAR regression. The II estimator is robust to departures from normal disturbances and is computationally straightforward compared with pseudo Gaussian maximum likelihood (PML). Monte Carlo experiments based on various specifications of the weighting matrix confirm that the indirect inference estimator displays little bias even in very small samples and gives overall performance that is comparable to the Gaussian PML.
Text
1418 combined.pdf
- Other
More information
Published date: 22 September 2014
Keywords:
bias, binding function, inconsistency, indirect inference, spatial autoregression
Organisations:
Economics
Identifiers
Local EPrints ID: 374156
URI: http://eprints.soton.ac.uk/id/eprint/374156
PURE UUID: 03b77939-0229-482f-b45a-beefbf0b09fe
Catalogue record
Date deposited: 09 Feb 2015 16:53
Last modified: 14 Mar 2024 19:03
Export record
Contributors
Author:
Francesca Rossi
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
