A comparison of two model averaging techniques with an application to growth empirics

J.R. Magnus, O.R. Powell, P. Prüfer

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Parameter estimation under model uncertainty is a difficult and fundamental issue in econometrics. This paper compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-average least squares (WALS). The new method has two major advantages over BMA: its computational burden is trivial and it is based on a transparent definition of prior ignorance. The theory is applied to and sheds new light on growth empirics where a high degree of model uncertainty is typically present.
Original languageEnglish
Pages (from-to)139-153
JournalJournal of Econometrics
Volume154
DOIs
Publication statusPublished - 2010

Fingerprint

Empirics
Model averaging
Model uncertainty
Bayesian model averaging
Burden
Econometrics
Ignorance
Least squares
Parameter estimation

Cite this

@article{f2bf058189ed45ffa3520f07bec6fb68,
title = "A comparison of two model averaging techniques with an application to growth empirics",
abstract = "Parameter estimation under model uncertainty is a difficult and fundamental issue in econometrics. This paper compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-average least squares (WALS). The new method has two major advantages over BMA: its computational burden is trivial and it is based on a transparent definition of prior ignorance. The theory is applied to and sheds new light on growth empirics where a high degree of model uncertainty is typically present.",
author = "J.R. Magnus and O.R. Powell and P. Pr{\"u}fer",
note = "Appeared earlier as CentER DP 2008-39",
year = "2010",
doi = "10.1016/j.jeconom.2009.07.004",
language = "English",
volume = "154",
pages = "139--153",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",

}

A comparison of two model averaging techniques with an application to growth empirics. / Magnus, J.R.; Powell, O.R.; Prüfer, P.

In: Journal of Econometrics, Vol. 154, 2010, p. 139-153.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - A comparison of two model averaging techniques with an application to growth empirics

AU - Magnus, J.R.

AU - Powell, O.R.

AU - Prüfer, P.

N1 - Appeared earlier as CentER DP 2008-39

PY - 2010

Y1 - 2010

N2 - Parameter estimation under model uncertainty is a difficult and fundamental issue in econometrics. This paper compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-average least squares (WALS). The new method has two major advantages over BMA: its computational burden is trivial and it is based on a transparent definition of prior ignorance. The theory is applied to and sheds new light on growth empirics where a high degree of model uncertainty is typically present.

AB - Parameter estimation under model uncertainty is a difficult and fundamental issue in econometrics. This paper compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-average least squares (WALS). The new method has two major advantages over BMA: its computational burden is trivial and it is based on a transparent definition of prior ignorance. The theory is applied to and sheds new light on growth empirics where a high degree of model uncertainty is typically present.

U2 - 10.1016/j.jeconom.2009.07.004

DO - 10.1016/j.jeconom.2009.07.004

M3 - Article

VL - 154

SP - 139

EP - 153

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

ER -