Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Bias-Corrected Common Correlated Effects Pooled Estimation in Dynamic Panels

De Vos, Ignace LU and Everaert, Gerdie (2021) In Journal of Business & Economic Statistics 39(1). p.294-306
Abstract
This article extends the common correlated effects pooled (CCEP) estimator to homogenous dynamic panels. In this setting, CCEP suffers from a large bias when the time span (T) of the dataset is fixed. We develop a bias-corrected CCEP estimator that is consistent as the number of cross-sectional units (N) tends to infinity, for T fixed or growing large, provided that the specification is augmented with a sufficient number of cross-sectional averages, and lags thereof. Monte Carlo experiments show that the correction offers strong improvements in terms of bias and variance. We apply our approach to estimate the dynamic impact of temperature shocks on aggregate output growth.
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Common correlated effects, Dynamic panel bias, Factor augmented regression, Multifactor error structure
in
Journal of Business & Economic Statistics
volume
39
issue
1
pages
13 pages
publisher
American Statistical Association
external identifiers
  • scopus:85071843335
ISSN
1537-2707
DOI
10.1080/07350015.2019.1654879
language
English
LU publication?
yes
id
3f758b0a-b296-4d4a-a0aa-917f341ae56b
date added to LUP
2019-09-03 16:13:28
date last changed
2022-04-26 03:52:36
@article{3f758b0a-b296-4d4a-a0aa-917f341ae56b,
  abstract     = {{This article extends the common correlated effects pooled (CCEP) estimator to homogenous dynamic panels. In this setting, CCEP suffers from a large bias when the time span (T) of the dataset is fixed. We develop a bias-corrected CCEP estimator that is consistent as the number of cross-sectional units (N) tends to infinity, for T fixed or growing large, provided that the specification is augmented with a sufficient number of cross-sectional averages, and lags thereof. Monte Carlo experiments show that the correction offers strong improvements in terms of bias and variance. We apply our approach to estimate the dynamic impact of temperature shocks on aggregate output growth.}},
  author       = {{De Vos, Ignace and Everaert, Gerdie}},
  issn         = {{1537-2707}},
  keywords     = {{Common correlated effects; Dynamic panel bias; Factor augmented regression; Multifactor error structure}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{294--306}},
  publisher    = {{American Statistical Association}},
  series       = {{Journal of Business & Economic Statistics}},
  title        = {{Bias-Corrected Common Correlated Effects Pooled Estimation in Dynamic Panels}},
  url          = {{https://lup.lub.lu.se/search/files/69080341/CCEPbc_ACCEPTED_AUTHOR_VERSION.pdf}},
  doi          = {{10.1080/07350015.2019.1654879}},
  volume       = {{39}},
  year         = {{2021}},
}