Blunt Instruments: On Establishing the Causes of Economic Growth

Michael Clemens and Samuel Bazzi

No 171, Working Papers from Center for Global Development

Abstract: Concern has intensified in recent years that many instrumental variables used in widely-cited growth regressions may be invalid, weak, or both. Attempts to remedy this general problem remain inadequate. We demonstrate that a range of published growth regressions may contain spurious results because of hidden problems with the instrumental variables they use. We urge several steps to surpass these difficulties: grounding of growth regressions in slightly more generalized theoretical models, deployment of the latest methods for estimating sensitivity to violations of exclusion restrictions, opening the black box of GMM with supportive evidence of instrument strength, and utilization of weak-instrument robust tests and estimators.

Keywords: IV; instrumental variables; 2SLS; two-stage least squares; Generalized Method of Moments; GMM; Blundell-Bond; Arellano-Bond; exclusion restriction; economic growth; regression; weak instruments; valid instruments; overidentification; underidentification; identification problem; growth determinants; foreign aid; institutions; geography; legal origins; too many instruments. (search for similar items in EconPapers)
JEL-codes: C12 F35 O4 (search for similar items in EconPapers)
Pages: 47 pages
Date: 2009-05
New Economics Papers: this item is included in nep-dev, nep-ecm and nep-fdg
References: Add references at CitEc
Citations: View citations in EconPapers (61)

Downloads: (external link)
http://www.cgdev.org/content/publications/detail/1422132/

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cgd:wpaper:171

Access Statistics for this paper

More papers in Working Papers from Center for Global Development Contact information at EDIRC.
Bibliographic data for series maintained by Publications Manager ().