The weak instrument problem of the system GMM estimator in dynamic panel data models
Abstract
The system GMM estimator for dynamic panel data models combines moment conditions for the model in first differences with moment conditions for the model in levels. It has been shown to improve on the GMM estimator in the first differenced model in terms of bias and root mean squared error. However, we show in this paper that in the covariance stationary panel data AR(1) model the expected values of the concentration parameters in the differenced and levels equations for the cross-section at time t are the same when the variances of the individual heterogeneity and idiosyncratic errors are the same. This indicates a weak instrument problem also for the equation in levels. We show that the 2SLS biases relative to that of the OLS biases are then similar for the equations in differences and levels, as are the size distortions of the Wald tests. These results are shown to extend to the panel data GMM estimators. Copyright (C) The Author(s). Journal compilation (C) Royal Economic Society 2010.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Sys-GMM suffers from the weak instrument problem particularly when the time series is large and substantial unobserved heterogeneity and cross-sectional dependence exists.
“However, it has come to light that Sys-GMM suffers from the weak instrument problem particularly when the time series is large and substantial unobserved heterogeneity and cross-sectional dependence exists (Bun & Windmeijer, 2010;Hayakawa, 2009)”
From Does investment in education and health impact youth employment outcomes? Evidence from Sub-Saharan Africa (2023) · cites this paper as Bun & Windmeijer, 2010
Cites
Initial conditions and moment restrictions in dynamic panel data models
Blundell, R., & Bond, S. (1998) · Journal of Econometrics · doi:10.1016/s0304-4076(98)00009-8 · Cited by 22,571 · see citing works
Instrumental Variables Regression with Weak Instruments
Staiger, D., & Stock, J. (1994) · doi:10.3386/t0151 · Cited by 5,302 · cited 6× · see citing works
“Staiger and Stock (1997) develop weak instrument asymptotics by setting π = π n = C/ √ n , in which case the concentration parameter converges to a constant.”
InfluentialTesting for Weak Instruments in Linear IV Regression
Stock, J., & Yogo, M. (2002) · doi:10.3386/t0284 · Cited by 1,842 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Do natural resources fuel authoritarianism? A reappraisal of the resource curse
HABER, S., & MENALDO, V. (2011) · American Political Science Review · doi:10.1017/s0003055410000584 · Cited by 1,128 · see citing works
Dynamic panels with threshold effect and endogeneity
Seo, M. H., & Shin, Y. (2016) · Journal of Econometrics · doi:10.1016/j.jeconom.2016.03.005 · Cited by 698 · see citing works
Anowor, O. F., Ichoku, H. E., Onodugo, V. A., Ochinanwata, C., & Uzomba, P. C. (2023) · Cogent Economics & Finance · doi:10.1080/23322039.2022.2160128 · Cited by 18 · see citing works
“…weak instrument problem particularly when the time series is large and substantial unobserved heterogeneity and cross-sectional dependence exists (Bun & Windmeijer, 2010; Hayakawa, 2009), hence the bootstrap-based bias correction for the panel fixed effects (FE) estimator was employed to improve…”
MethodFertility Transitions in Developing Countries: Convergence, Timing, and Causes
Papagni, E. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3522996 · Cited by 1 · see citing works
- Authors
- Bun, M. J. G., & Windmeijer, F.
- Affiliations
- University of Amsterdam (NL)
- Institute for Fiscal Studies (GB)
- Venue
- The Econometrics Journal
- Publisher
- Oxford University Press (OUP)
- Published
- 2010-02-01
- Volume
- 13
- Issue
- 1
- Pages
- 95-126
- ISSN
- 1368-4221 (ISSN-L)
- 1368-423X
- OpenAlex
- W3121770345
- Cited by
- 498
- References
- 3
- Citations by year
- 2026: 41 · 2025: 45 · 2024: 39 · 2023: 44 · 2022: 29 · 2021: 31 · 2020: 25 · 2019: 31 · 2018: 24 · 2017: 23 · 2016: 34 · 2015: 32 · 2014: 28 · 2013: 22 · 2012: 22
- FWCI
- 49.05
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Econometrics Journal (publishedVersion)
- UvA-DARE (University of Amsterdam) (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Bristol Research (University of Bristol) (submittedVersion)
- Data Archiving and Networked Services (DANS) (submittedVersion)
- Funders
- Economic and Social Research Council (ES/F015879/1, ES/H005331/1)
- Topics
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Spatial and Panel Data Analysis
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Keywords
- system GMM, dynamic panel data, concentration parameter, cross-sectional heterogeneity, root mean square error
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
