Specification searches in spatial econometrics: The relevance of Hendry's methodology

Raymond J G M Florax, Hendrik Folmer, Sergio J. Rey

Research output: Contribution to journalArticle

232 Citations (Scopus)

Abstract

This article brings together a number of new specification search strategies in spatial econometric modeling. In the literature, experimental results for several forward stepwise strategies aimed at remedying spatial dependence, have been reported. Essentially, these strategies boil down to the expansion of a spatial linear regression model with spatially lagged variables, conditional upon the results of misspecification tests. We investigate a Hendry-like specification strategy, starting from the spatial common factor model and subsequently reducing the number of spatially lagged variables on the basis of significance tests. The experimental simulations pertain to various small to large sample sizes, with spatial processes modeled on regular lattice surfaces. Our main conclusion is that the classical forward stepwise approach outperforms the Hendry strategy in terms of finding the true data generating process as well as in the observed accuracy of the estimators for spatial and non-spatial parameters. It also dominates concurrent forward stepwise strategies recently suggested in the literature.

Original languageEnglish (US)
Pages (from-to)557-579
Number of pages23
JournalRegional Science and Urban Economics
Volume33
Issue number5
DOIs
StatePublished - Sep 2003
Externally publishedYes

Fingerprint

econometrics
methodology
significance test
modeling
simulation
test
Spatial econometrics
Methodology
regression
parameter

Keywords

  • Autocorrelation
  • Hendry methodology
  • Pre-testing
  • Spatial econometrics
  • Specification strategy

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Specification searches in spatial econometrics : The relevance of Hendry's methodology. / Florax, Raymond J G M; Folmer, Hendrik; Rey, Sergio J.

In: Regional Science and Urban Economics, Vol. 33, No. 5, 09.2003, p. 557-579.

Research output: Contribution to journalArticle

Florax, Raymond J G M ; Folmer, Hendrik ; Rey, Sergio J. / Specification searches in spatial econometrics : The relevance of Hendry's methodology. In: Regional Science and Urban Economics. 2003 ; Vol. 33, No. 5. pp. 557-579.
@article{a8867a717d7d455eb384a433a41fa3b4,
title = "Specification searches in spatial econometrics: The relevance of Hendry's methodology",
abstract = "This article brings together a number of new specification search strategies in spatial econometric modeling. In the literature, experimental results for several forward stepwise strategies aimed at remedying spatial dependence, have been reported. Essentially, these strategies boil down to the expansion of a spatial linear regression model with spatially lagged variables, conditional upon the results of misspecification tests. We investigate a Hendry-like specification strategy, starting from the spatial common factor model and subsequently reducing the number of spatially lagged variables on the basis of significance tests. The experimental simulations pertain to various small to large sample sizes, with spatial processes modeled on regular lattice surfaces. Our main conclusion is that the classical forward stepwise approach outperforms the Hendry strategy in terms of finding the true data generating process as well as in the observed accuracy of the estimators for spatial and non-spatial parameters. It also dominates concurrent forward stepwise strategies recently suggested in the literature.",
keywords = "Autocorrelation, Hendry methodology, Pre-testing, Spatial econometrics, Specification strategy",
author = "Florax, {Raymond J G M} and Hendrik Folmer and Rey, {Sergio J.}",
year = "2003",
month = "9",
doi = "10.1016/S0166-0462(03)00002-4",
language = "English (US)",
volume = "33",
pages = "557--579",
journal = "Regional Science and Urban Economics",
issn = "0166-0462",
publisher = "Elsevier",
number = "5",

}

TY - JOUR

T1 - Specification searches in spatial econometrics

T2 - The relevance of Hendry's methodology

AU - Florax, Raymond J G M

AU - Folmer, Hendrik

AU - Rey, Sergio J.

PY - 2003/9

Y1 - 2003/9

N2 - This article brings together a number of new specification search strategies in spatial econometric modeling. In the literature, experimental results for several forward stepwise strategies aimed at remedying spatial dependence, have been reported. Essentially, these strategies boil down to the expansion of a spatial linear regression model with spatially lagged variables, conditional upon the results of misspecification tests. We investigate a Hendry-like specification strategy, starting from the spatial common factor model and subsequently reducing the number of spatially lagged variables on the basis of significance tests. The experimental simulations pertain to various small to large sample sizes, with spatial processes modeled on regular lattice surfaces. Our main conclusion is that the classical forward stepwise approach outperforms the Hendry strategy in terms of finding the true data generating process as well as in the observed accuracy of the estimators for spatial and non-spatial parameters. It also dominates concurrent forward stepwise strategies recently suggested in the literature.

AB - This article brings together a number of new specification search strategies in spatial econometric modeling. In the literature, experimental results for several forward stepwise strategies aimed at remedying spatial dependence, have been reported. Essentially, these strategies boil down to the expansion of a spatial linear regression model with spatially lagged variables, conditional upon the results of misspecification tests. We investigate a Hendry-like specification strategy, starting from the spatial common factor model and subsequently reducing the number of spatially lagged variables on the basis of significance tests. The experimental simulations pertain to various small to large sample sizes, with spatial processes modeled on regular lattice surfaces. Our main conclusion is that the classical forward stepwise approach outperforms the Hendry strategy in terms of finding the true data generating process as well as in the observed accuracy of the estimators for spatial and non-spatial parameters. It also dominates concurrent forward stepwise strategies recently suggested in the literature.

KW - Autocorrelation

KW - Hendry methodology

KW - Pre-testing

KW - Spatial econometrics

KW - Specification strategy

UR - http://www.scopus.com/inward/record.url?scp=0012092887&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0012092887&partnerID=8YFLogxK

U2 - 10.1016/S0166-0462(03)00002-4

DO - 10.1016/S0166-0462(03)00002-4

M3 - Article

AN - SCOPUS:0012092887

VL - 33

SP - 557

EP - 579

JO - Regional Science and Urban Economics

JF - Regional Science and Urban Economics

SN - 0166-0462

IS - 5

ER -