Category

Number of Access this item:1,467（2024-04-23 16:45 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/10086/14340

Link to primary information 

File Format Size Views Description
cover_14340 pdf
D07-217 pdf 244 KB 2,513

Item Information

Output File

Title
An Alternative System GMM Estimation in Dynamic Panel Models
Creator
Creator Name
Jung, Hosun Jung, Hosun
Affiliation
Affiliation Name
Samsung Economic Research Institute
Creator Name
Kwon, Hyeog Ug Kwon, Hyeog Ug
権, 赫旭 権, 赫旭
Affiliation
Affiliation Name
Nihon University
Editor
Contributor Name
社会科学における統計分析拠点構築 = Research Unit for Statistical Analysis in Social Sciences
Key Word
Dynamic panel data
sub-optimal weighting matrix
KI upper bound
Abstract
The system GMM estimator in dynamic panel data models which combines two moment conditions, i.e., for the differenced equation and for the model in levels, is known to be more efficient than the first-difference GMM estimator. However, an initial optimal weight matrix is not known for the system estimation procedure. Therefore, we suggest the use of 'a suboptimal weight matrix' which may reduce the finite sample bias whilst increasing its efficiency. Using the Kantorovich inequality, we find that the potential efficiency gain becomes large when the variance of individual effects increases compared to the variance of the idiosyncratic errors. (Our Monte Carlo experiments show that the small sample properties of the suboptimal system estimator are shown to be much more reliable than any other conventional system GMM estimator in terms of bias and efficiency.
Description
References: p. 13-15
Publisher
Institute of Economic Research, Hitotsubashi University
Issued Date
2007-07
Language
English(eng)
Resource Type
technical report
Version Type
VoR
Is Part OfRelation -
Related Title
Hi-Stat Discussion paper series, No. 217
Relation
Related Identifier
URI
  http://21coe.ier.hit-u.ac.jp/english/index.html
Sponsorship
21世紀COEプログラム = 21st-Century COE Program
Appears in Collections
Hi-Stat Discussion paper series
URL
https://hdl.handle.net/10086/14340