Neighbourhood GMM estimation of dynamic panel data models

Research output: Contribution to journalArticleResearchpeer-review

Abstract

A new approach is developed for estimation of short dynamic panel data models with spatially correlated errors. The method employs an additional set of moment conditions that become available for each i—specifically, instruments with respect to the individual(s) which unit i is spatially correlated with. These moment conditions are non-redundant and remain informative even if the data generating process is close to a unit root one. The proposed GMM estimator is consistent and asymptotically normally distributed. An extensive Monte Carlo study also builds a GMM estimator that combines spatial and standard instruments. This estimator appears to perform very well under a wide range of parametrisations in terms of both bias and root mean square error. The proposed method is illustrated using crime data based on a panel of 153 local government areas in NSW, spanning a period of 5 years.

Original languageEnglish
Pages (from-to)526-544
Number of pages19
JournalComputational Statistics and Data Analysis
Volume100
DOIs
Publication statusPublished - 29 May 2016

Keywords

  • Dynamic panel data
  • Generalised Method of Moments
  • Spatial dependence

Cite this

@article{f2ad52b0c7e44a8394f3247b636acccc,
title = "Neighbourhood GMM estimation of dynamic panel data models",
abstract = "A new approach is developed for estimation of short dynamic panel data models with spatially correlated errors. The method employs an additional set of moment conditions that become available for each i—specifically, instruments with respect to the individual(s) which unit i is spatially correlated with. These moment conditions are non-redundant and remain informative even if the data generating process is close to a unit root one. The proposed GMM estimator is consistent and asymptotically normally distributed. An extensive Monte Carlo study also builds a GMM estimator that combines spatial and standard instruments. This estimator appears to perform very well under a wide range of parametrisations in terms of both bias and root mean square error. The proposed method is illustrated using crime data based on a panel of 153 local government areas in NSW, spanning a period of 5 years.",
keywords = "Dynamic panel data, Generalised Method of Moments, Spatial dependence",
author = "Vasilis Sarafidis",
year = "2016",
month = "5",
day = "29",
doi = "10.1016/j.csda.2015.11.015",
language = "English",
volume = "100",
pages = "526--544",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",

}

Neighbourhood GMM estimation of dynamic panel data models. / Sarafidis, Vasilis.

In: Computational Statistics and Data Analysis, Vol. 100, 29.05.2016, p. 526-544.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Neighbourhood GMM estimation of dynamic panel data models

AU - Sarafidis, Vasilis

PY - 2016/5/29

Y1 - 2016/5/29

N2 - A new approach is developed for estimation of short dynamic panel data models with spatially correlated errors. The method employs an additional set of moment conditions that become available for each i—specifically, instruments with respect to the individual(s) which unit i is spatially correlated with. These moment conditions are non-redundant and remain informative even if the data generating process is close to a unit root one. The proposed GMM estimator is consistent and asymptotically normally distributed. An extensive Monte Carlo study also builds a GMM estimator that combines spatial and standard instruments. This estimator appears to perform very well under a wide range of parametrisations in terms of both bias and root mean square error. The proposed method is illustrated using crime data based on a panel of 153 local government areas in NSW, spanning a period of 5 years.

AB - A new approach is developed for estimation of short dynamic panel data models with spatially correlated errors. The method employs an additional set of moment conditions that become available for each i—specifically, instruments with respect to the individual(s) which unit i is spatially correlated with. These moment conditions are non-redundant and remain informative even if the data generating process is close to a unit root one. The proposed GMM estimator is consistent and asymptotically normally distributed. An extensive Monte Carlo study also builds a GMM estimator that combines spatial and standard instruments. This estimator appears to perform very well under a wide range of parametrisations in terms of both bias and root mean square error. The proposed method is illustrated using crime data based on a panel of 153 local government areas in NSW, spanning a period of 5 years.

KW - Dynamic panel data

KW - Generalised Method of Moments

KW - Spatial dependence

UR - http://www.scopus.com/inward/record.url?scp=84950250026&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2015.11.015

DO - 10.1016/j.csda.2015.11.015

M3 - Article

VL - 100

SP - 526

EP - 544

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

ER -